POSTERS

Time Zone Information (click here for more information)

Blue font indicates for this time zone the corresponding time is the day before compared to the day in Glasgow time (UTC+1).
Red font indicates for this time zone the corresponding time is the day after compared to the day in Glasgow time (UTC+1).

San Francisco
UTC -7 hours		Boston 
UTC - 4 hours		UK
UTC + 1 hour		Europe
UTC + 2 hours		Dubai
UTC + 4 hours		India
UTC + 5:30 hours		Hong Kong
UTC + 8 hours		Japan
UTC + 9 hours		Sydney
UTC +10 hours		New Zealand
UTC +12 Hours
16:0019:0000:0001:0003:0004:3007:0008:0009:0011:00
16:3019:3000:3001:3003:3005:0007:3008:3009:3011:30
17:0020:0001:0002:0004:0005:3008:0009:0010:0012:00
17:3020:3001:3002:3004:3006:0008:3009:3010:3012:30
18:0021:0002:0003:0005:0006:3009:0010:0011:0013:00
18:3021:3002:3003:3005:3007:0009:3010:3011:3013:30
19:0022:0003:0004:0006:0007:3010:0011:0012:0014:00
19:3022:3003:3004:3006:3008:0010:3011:3012:3014:30
20:0023:0004:0005:0007:0008:3011:0012:0013:0015:00
20:3023:3004:3005:3007:3009:0011:3012:3013:3015:30
21:0000:0005:0006:0008:0009:3012:0013:0014:0016:00
21:3000:3005:3006:3008:3010:0012:3013:3014:3016:30
22:0001:0006:0007:0009:0010:3013:0014:0015:0017:00
22:3001:3006:3007:3009:3011:0013:3014:3015:3017:30
23:0002:0007:0008:0010:0011:3014:0015:0016:0018:00
23:3002:3007:3008:3010:3012:0014:3015:3016:3018:30
00:0003:0008:0009:0011:0012:3015:0016:0017:0019:00
00:3003:3008:3009:3011:3013:0015:3016:3017:3019:30
01:0004:0009:0010:0012:0013:3016:0017:0018:0020:00
01:3004:3009:3010:3012:3014:0016:3017:3018:3020:30
02:0005:0010:0011:0013:0014:3017:0018:0019:0021:00
02:3005:3010:3011:3013:3015:0017:3018:3019:3021:30
03:0006:0011:0012:0014:0015:3018:0019:0020:0022:00
03:3006:3011:3012:3014:3016:0018:3019:3020:3022:30
04:0007:0012:0013:0015:0016:3019:0020:0021:0023:00
04:3007:3012:3013:3015:3017:0019:3020:3021:3023:30
05:0008:0013:0014:0016:0017:3020:0021:0022:0000:00
05:3008:3013:3014:3016:3018:0020:3021:3022:3000:30
06:0009:0014:0015:0017:0018:3021:0022:0023:0001:00
06:3009:3014:3015:3017:3019:0021:3022:3023:3001:30
07:0010:0015:0016:0018:0019:3022:0023:0000:0002:00
07:3010:3015:3016:3018:3020:0022:3023:3000:3002:30
08:0011:0016:0017:0019:0020:3023:0000:0001:0003:00
08:3011:3016:3017:3019:3021:0023:3000:3001:3003:30
09:0012:0017:0018:0020:0021:3000:0001:0002:0004:00
09:3012:3017:3018:3020:3022:0000:3001:3002:3004:30
10:0013:0018:0019:0021:0022:3001:0002:0003:0005:00
10:3013:3018:3019:3021:3023:0001:3002:3003:3005:30
11:0014:0019:0020:0022:0023:3002:0003:0004:0006:00
11:3014:3019:3020:3022:3000:0002:3003:3004:3006:30
12:0015:0020:0021:0023:0000:3003:0004:0005:0007:00
12:3015:3020:3021:3023:3001:0003:3004:3005:3007:30
13:0016:0021:0022:0000:0001:3004:0005:0006:0008:00
13:3016:3021:3022:3000:3002:0004:3005:3006:3008:30
14:0017:0022:0023:0001:0002:3005:0006:0007:0009:00
14:3017:3022:3023:3001:3003:0005:3006:3007:3009:30
15:0018:0023:0000:0002:0003:3006:0007:0008:0010:00
15:3018:3023:3000:3002:3004:0006:3007:3008:3010:30
Paper IDPresenter NamePresenter SurnameTitleNew Poster NumberPoster Presentation DatePoster Presentation TimeCategory
5AhmedOsmanSTAR: Sparse Trained Articulated Human Body Regressor1000Monday 24 August 202006:00:00Poster
5AhmedOsmanSTAR: Sparse Trained Articulated Human Body Regressor1000Monday 24 August 202014:00:00Poster
13XinghaoChenOptical Flow Distillation: Towards Efficient and Stable Video Style Transfer2000Tuesday 25 August 202000:00:00Poster
13XinghaoChenOptical Flow Distillation: Towards Efficient and Stable Video Style Transfer2000Tuesday 25 August 202006:00:00Poster
15SihuiLuoCollaboration by Competition: Self-coordinated Knowledge Amalgamation for Multi-talent Student Learning2001Tuesday 25 August 202000:00:00Poster
15SihuiLuoCollaboration by Competition: Self-coordinated Knowledge Amalgamation for Multi-talent Student Learning2001Tuesday 25 August 202006:00:00Poster
22LimingJiangTSIT: A Simple and Versatile Framework for Image-to-Image Translation3000Wednesday 26 August 202000:00:00Spotlight
22LimingJiangTSIT: A Simple and Versatile Framework for Image-to-Image Translation3000Wednesday 26 August 202006:00:00Spotlight
25ShizhenZhaoDo Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians2002Tuesday 25 August 202000:00:00Poster
25ShizhenZhaoDo Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians2002Tuesday 25 August 202006:00:00Poster
31YichenLiLearning 3D Part Assembly from a Single Image4224Thursday 27 August 202006:00:00Poster
31YichenLiLearning 3D Part Assembly from a Single Image4224Friday 28 August 202000:00:00Poster
32KaichunMoPT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions4225Thursday 27 August 202014:00:00Poster
32KaichunMoPT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions4225Friday 28 August 202000:00:00Poster
43XiangyuHeProxyBNN: Learning Binarized Neural Networks via Proxy Matrices3001Wednesday 26 August 202000:00:00Spotlight
43XiangyuHeProxyBNN: Learning Binarized Neural Networks via Proxy Matrices3001Wednesday 26 August 202006:00:00Spotlight
50ShanghuaGaoHighly Efficient Salient Object Detection with 100K Parameters4000Thursday 27 August 202000:00:00Poster
50ShanghuaGaoHighly Efficient Salient Object Detection with 100K Parameters4000Thursday 27 August 202006:00:00Poster
69Chia-WenLinHardGAN: A Haze-Aware Representation Distillation GAN for Single Image Dehazing2003Tuesday 25 August 202000:00:00Poster
69Chia-WenLinHardGAN: A Haze-Aware Representation Distillation GAN for Single Image Dehazing2003Tuesday 25 August 202006:00:00Poster
88RoyOr-ElLifespan Age Transformation Synthesis1001Monday 24 August 202006:00:00Poster
88RoyOr-ElLifespan Age Transformation Synthesis1001Monday 24 August 202014:00:00Poster
90XingchaoPengDomain2Vec: Domain Embedding for Unsupervised Domain Adaptation2261Tuesday 25 August 202014:00:00Poster
90XingchaoPengDomain2Vec: Domain Embedding for Unsupervised Domain Adaptation2261Wednesday 26 August 202000:00:00Poster
106YueYaoSimulating Content Consistent Vehicle Datasets with Attribute Descent3002Wednesday 26 August 202000:00:00Poster
106YueYaoSimulating Content Consistent Vehicle Datasets with Attribute Descent3002Wednesday 26 August 202006:00:00Poster
116YunzhongHouMultiview Detection with Feature Perspective Transformation3003Wednesday 26 August 202000:00:00Poster
116YunzhongHouMultiview Detection with Feature Perspective Transformation3003Wednesday 26 August 202006:00:00Poster
121HemingDuLearning Object Relation Graph and Tentative Policy for Visual Navigation2004Tuesday 25 August 202000:00:00Poster
121HemingDuLearning Object Relation Graph and Tentative Policy for Visual Navigation2004Tuesday 25 August 202006:00:00Poster
123ChenyangSiAdversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition4001Thursday 27 August 202000:00:00Poster
123ChenyangSiAdversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition4001Thursday 27 August 202006:00:00Poster
132LiadPollak ZuckermanAcross Scales \& Across Dimensions: Temporal Super-Resolution using Deep Internal Learning1002Monday 24 August 202006:00:00Poster
132LiadPollak ZuckermanAcross Scales \& Across Dimensions: Temporal Super-Resolution using Deep Internal Learning1002Monday 24 August 202014:00:00Poster
138BinodBhattaraiInducing Optimal Attribute Representations for Conditional GANs2262Tuesday 25 August 202014:00:00Poster
138BinodBhattaraiInducing Optimal Attribute Representations for Conditional GANs2262Wednesday 26 August 202000:00:00Poster
148JiefengLiHMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation3004Wednesday 26 August 202000:00:00Spotlight
148JiefengLiHMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation3004Wednesday 26 August 202006:00:00Spotlight
152YueMengAR-Net: Adaptive Frame Resolution for Efficient Action Recognition2263Tuesday 25 August 202014:00:00Poster
152YueMengAR-Net: Adaptive Frame Resolution for Efficient Action Recognition2263Wednesday 26 August 202000:00:00Poster
156VladimirKniazImage-to-Voxel Model Translation for 3D Scene Reconstruction and Segmentation1003Monday 24 August 202006:00:00Poster
156VladimirKniazImage-to-Voxel Model Translation for 3D Scene Reconstruction and Segmentation1003Monday 24 August 202014:00:00Poster
157YuhuaChenConsistency Guided Scene Flow Estimation1004Monday 24 August 202006:00:00Poster
157YuhuaChenConsistency Guided Scene Flow Estimation1004Monday 24 August 202014:00:00Poster
160YassineOualiAutoregressive Unsupervised Image Segmentation1005Monday 24 August 202006:00:00Poster
160YassineOualiAutoregressive Unsupervised Image Segmentation1005Monday 24 August 202014:00:00Poster
169Yen-ChiChengControllable Image Synthesis via SegVAE4002Thursday 27 August 202000:00:00Poster
169Yen-ChiChengControllable Image Synthesis via SegVAE4002Thursday 27 August 202006:00:00Poster
173YuanTianOff-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search1006Monday 24 August 202006:00:00Poster
173YuanTianOff-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search1006Monday 24 August 202014:00:00Poster
177MarikoIsogawaEfficient Non-Line-of-Sight Imaging from Transient Sinograms2005Tuesday 25 August 202000:00:00Poster
177MarikoIsogawaEfficient Non-Line-of-Sight Imaging from Transient Sinograms2005Tuesday 25 August 202006:00:00Poster
181YulunZhangTexture Hallucination for Large-Factor Painting Super-Resolution2264Tuesday 25 August 202014:00:00Poster
181YulunZhangTexture Hallucination for Large-Factor Painting Super-Resolution2264Wednesday 26 August 202000:00:00Poster
183YujunCaiLearning Progressive Joint Propagation for Human Motion Prediction3005Wednesday 26 August 202000:00:00Poster
183YujunCaiLearning Progressive Joint Propagation for Human Motion Prediction3005Wednesday 26 August 202006:00:00Poster
184BingbingZhuangImage Stitching and Rectification for Hand-Held Cameras3226Wednesday 26 August 202014:00:00Poster
184BingbingZhuangImage Stitching and Rectification for Hand-Held Cameras3226Thursday 27 August 202000:00:00Poster
186GopalSharmaA Parametric Surface Fitting Network for 3D Point Clouds2265Tuesday 25 August 202014:00:00Poster
186GopalSharmaA Parametric Surface Fitting Network for 3D Point Clouds2265Wednesday 26 August 202000:00:00Poster
188LauraLeal-TaixeThe Group Loss for Deep Metric Learning3167Wednesday 26 August 202006:00:00Poster
188LauraLeal-TaixeThe Group Loss for Deep Metric Learning3167Wednesday 26 August 202014:00:00Poster
193WeichengKuoMask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve2266Tuesday 25 August 202014:00:00Spotlight
193WeichengKuoMask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve2266Wednesday 26 August 202000:00:00Spotlight
203BrentGriffinLearning Object Depth from Camera Motion and Video Object Segmentation2267Tuesday 25 August 202014:00:00Poster
203BrentGriffinLearning Object Depth from Camera Motion and Video Object Segmentation2267Wednesday 26 August 202000:00:00Poster
206ZhiqiangTangOnlineAugment: Online Data Augmentation with Less Domain Knowledge1164Monday 24 August 202014:00:00Poster
206ZhiqiangTangOnlineAugment: Online Data Augmentation with Less Domain Knowledge1164Tuesday 25 August 202000:00:00Poster
209YimingQianLearning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction4226Thursday 27 August 202014:00:00Poster
209YimingQianLearning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction4226Friday 28 August 202000:00:00Poster
223LanlanLiuA Unified Framework of Surrogate Loss by Refactoring and Interpolation3227Wednesday 26 August 202014:00:00Spotlight
223LanlanLiuA Unified Framework of Surrogate Loss by Refactoring and Interpolation3227Thursday 27 August 202000:00:00Spotlight
230YongchaoXuIntra-class Feature Variation Distillation for Semantic Segmentation3006Wednesday 26 August 202000:00:00Poster
230YongchaoXuIntra-class Feature Variation Distillation for Semantic Segmentation3006Wednesday 26 August 202006:00:00Poster
233JunwuWengTemporal Distinct Representation Learning for Action Recognition2006Tuesday 25 August 202000:00:00Poster
233JunwuWengTemporal Distinct Representation Learning for Action Recognition2006Tuesday 25 August 202006:00:00Poster
241ChangqianYuRepresentative Graph Neural Network3007Wednesday 26 August 202000:00:00Poster
241ChangqianYuRepresentative Graph Neural Network3007Wednesday 26 August 202006:00:00Poster
264Mikaela AngelinaUyDeformation-Aware 3D Model Embedding and Retrieval2268Tuesday 25 August 202014:00:00Poster
264Mikaela AngelinaUyDeformation-Aware 3D Model Embedding and Retrieval2268Wednesday 26 August 202000:00:00Poster
267TolgaBirdalQuaternion Equivariant Capsule Networks for 3D Point Clouds1007Monday 24 August 202006:00:00Oral
267TolgaBirdalQuaternion Equivariant Capsule Networks for 3D Point Clouds1007Monday 24 August 202014:00:00Oral
277ZakMurezAtlas: End-to-End 3D Scene Reconstruction from Posed Images4227Thursday 27 August 202014:00:00Poster
277ZakMurezAtlas: End-to-End 3D Scene Reconstruction from Posed Images4227Friday 28 August 202000:00:00Poster
278VishalPatelMultiple Class Novelty Detection Under Data Distribution Shift4228Thursday 27 August 202014:00:00Poster
278VishalPatelMultiple Class Novelty Detection Under Data Distribution Shift4228Friday 28 August 202000:00:00Poster
281Wei-chenChiuColorization of Depth Map via Disentanglement4003Thursday 27 August 202000:00:00Poster
281Wei-chenChiuColorization of Depth Map via Disentanglement4003Thursday 27 August 202006:00:00Poster
283YizhakBen-shabatDeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares4004Thursday 27 August 202000:00:00Oral
283YizhakBen-shabatDeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares4004Thursday 27 August 202006:00:00Oral
287JohannaWaldBeyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes1008Monday 24 August 202006:00:00Poster
287JohannaWaldBeyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes1008Monday 24 August 202014:00:00Poster
292AhmedNassarGeoGraph: Graph-based multi-view object detection with geometric cues end-to-end2249Tuesday 25 August 202006:00:00Poster
292AhmedNassarGeoGraph: Graph-based multi-view object detection with geometric cues end-to-end2249Tuesday 25 August 202014:00:00Poster
300PengWanYangLocalizing the Common Action Among a Few Videos1009Monday 24 August 202006:00:00Poster
300PengWanYangLocalizing the Common Action Among a Few Videos1009Monday 24 August 202014:00:00Poster
306LeonidKarlinskyTAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification1010Monday 24 August 202006:00:00Poster
306LeonidKarlinskyTAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification1010Monday 24 August 202014:00:00Poster
312TackgeunYouTraffic Accident Benchmark for Causality Recognition2007Tuesday 25 August 202000:00:00Poster
312TackgeunYouTraffic Accident Benchmark for Causality Recognition2007Tuesday 25 August 202006:00:00Poster
318ZitongYuFace Anti-Spoofing with Human Material Perception1011Monday 24 August 202006:00:00Poster
318ZitongYuFace Anti-Spoofing with Human Material Perception1011Monday 24 August 202014:00:00Poster
328HuikunBiHow Can I See My Future? FvTraj: Using First-person View for Pedestrian Trajectory Prediction4005Thursday 27 August 202000:00:00Poster
328HuikunBiHow Can I See My Future? FvTraj: Using First-person View for Pedestrian Trajectory Prediction4005Thursday 27 August 202006:00:00Poster
338YunpengZhaiMultiple Expert Brainstorming for Domain Adaptive Person Re-identification2008Tuesday 25 August 202000:00:00Poster
338YunpengZhaiMultiple Expert Brainstorming for Domain Adaptive Person Re-identification2008Tuesday 25 August 202006:00:00Poster
343ZhichaoLuNSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search2009Tuesday 25 August 202000:00:00Oral
343ZhichaoLuNSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search2009Tuesday 25 August 202006:00:00Oral
344AndreaTagliasacchiNASA Neural Articulated Shape Approximation1165Monday 24 August 202014:00:00Poster
344AndreaTagliasacchiNASA Neural Articulated Shape Approximation1165Tuesday 25 August 202000:00:00Poster
350ZeyuWangTowards Unique and Informative Captioning of Images3228Wednesday 26 August 202014:00:00Poster
350ZeyuWangTowards Unique and Informative Captioning of Images3228Thursday 27 August 202000:00:00Poster
352Jong-ChyiSuWhen Does Self-supervision Improve Few-shot Learning?4229Thursday 27 August 202014:00:00Poster
352Jong-ChyiSuWhen Does Self-supervision Improve Few-shot Learning?4229Friday 28 August 202000:00:00Poster
355IacopoMasiTwo-branch Recurrent Network for Isolating Deepfakes in Videos2269Tuesday 25 August 202014:00:00Poster
355IacopoMasiTwo-branch Recurrent Network for Isolating Deepfakes in Videos2269Wednesday 26 August 202000:00:00Poster
360OrchidMajumderIncremental Few-Shot Meta-Learning via Indirect Discriminant Alignment2270Tuesday 25 August 202014:00:00Poster
360OrchidMajumderIncremental Few-Shot Meta-Learning via Indirect Discriminant Alignment2270Wednesday 26 August 202000:00:00Poster
362SaiBiDeep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images4230Thursday 27 August 202014:00:00Spotlight
362SaiBiDeep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images4230Friday 28 August 202000:00:00Spotlight
363JiahuiYuBigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models2271Tuesday 25 August 202014:00:00Poster
363JiahuiYuBigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models2271Wednesday 26 August 202000:00:00Poster
366TengdaHanMemory-augmented Dense Predictive Coding for Video Representation Learning4231Thursday 27 August 202014:00:00Spotlight
366TengdaHanMemory-augmented Dense Predictive Coding for Video Representation Learning4231Friday 28 August 202000:00:00Spotlight
378YunluChenPointMixup: Augmentation for Point Clouds1012Monday 24 August 202006:00:00Spotlight
378YunluChenPointMixup: Augmentation for Point Clouds1012Monday 24 August 202014:00:00Spotlight
384ChenyunWuDescribing Textures using Natural Language4232Thursday 27 August 202014:00:00Oral
384ChenyunWuDescribing Textures using Natural Language4232Friday 28 August 202000:00:00Oral
386ShengJinDifferentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation3008Wednesday 26 August 202000:00:00Poster
386ShengJinDifferentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation3008Wednesday 26 August 202006:00:00Poster
392CuilingLanGlobal Distance-distributions Separation for Unsupervised Person Re-identification4006Thursday 27 August 202000:00:00Poster
392CuilingLanGlobal Distance-distributions Separation for Unsupervised Person Re-identification4006Thursday 27 August 202006:00:00Poster
397GyeongsikMoonI2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image3009Wednesday 26 August 202000:00:00Poster
397GyeongsikMoonI2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image3009Wednesday 26 August 202006:00:00Poster
398HongsukChoiPose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose3010Wednesday 26 August 202000:00:00Poster
398HongsukChoiPose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose3010Wednesday 26 August 202006:00:00Poster
402MingzhuZhuALRe: Outlier Detection for Guided Refinement2010Tuesday 25 August 202000:00:00Poster
402MingzhuZhuALRe: Outlier Detection for Guided Refinement2010Tuesday 25 August 202006:00:00Poster
410Rizard Renanda AdhiPramonoEmpowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity Recognition2011Tuesday 25 August 202000:00:00Oral
410Rizard Renanda AdhiPramonoEmpowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity Recognition2011Tuesday 25 August 202006:00:00Oral
414YifanYangWeakly-Supervised Crowd Counting Learns from Sorting rather than Locations3011Wednesday 26 August 202000:00:00Poster
414YifanYangWeakly-Supervised Crowd Counting Learns from Sorting rather than Locations3011Wednesday 26 August 202006:00:00Poster
415KuanZhuIdentity-Guided Human Semantic Parsing for Person Re-Identification2012Tuesday 25 August 202000:00:00Spotlight
415KuanZhuIdentity-Guided Human Semantic Parsing for Person Re-Identification2012Tuesday 25 August 202006:00:00Spotlight
429KeleiHeUnsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition4007Thursday 27 August 202000:00:00Poster
429KeleiHeUnsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition4007Thursday 27 August 202006:00:00Poster
438CarloBiffiMany-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection1013Monday 24 August 202006:00:00Poster
438CarloBiffiMany-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection1013Monday 24 August 202014:00:00Poster
441YueqiDuanCurriculum DeepSDF3229Wednesday 26 August 202014:00:00Poster
441YueqiDuanCurriculum DeepSDF3229Thursday 27 August 202000:00:00Poster
444MinghuaLiuMeshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance4233Thursday 27 August 202014:00:00Poster
444MinghuaLiuMeshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance4233Friday 28 August 202000:00:00Poster
445ShiChenAiR: Attention with Reasoning Capability2272Tuesday 25 August 202014:00:00Oral
445ShiChenAiR: Attention with Reasoning Capability2272Wednesday 26 August 202000:00:00Oral
457YuanhaoXiongImproved Adversarial Training via Learned Optimizer3230Wednesday 26 August 202014:00:00Poster
457YuanhaoXiongImproved Adversarial Training via Learned Optimizer3230Thursday 27 August 202000:00:00Poster
462RuojinCaiLearning Gradient Fields for Shape Generation2273Tuesday 25 August 202014:00:00Spotlight
462RuojinCaiLearning Gradient Fields for Shape Generation2273Wednesday 26 August 202000:00:00Spotlight
467KuniakiSaitoCOCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder2274Tuesday 25 August 202014:00:00Spotlight
467KuniakiSaitoCOCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder2274Wednesday 26 August 202000:00:00Spotlight
471PengxuWeiComponent Divide-and-Conquer for Real-World Image Super-Resolution4008Thursday 27 August 202000:00:00Poster
471PengxuWeiComponent Divide-and-Conquer for Real-World Image Super-Resolution4008Thursday 27 August 202006:00:00Poster
479YunhangShenEnabling Deep Residual Networks for Weakly Supervised Object Detection2013Tuesday 25 August 202000:00:00Poster
479YunhangShenEnabling Deep Residual Networks for Weakly Supervised Object Detection2013Tuesday 25 August 202006:00:00Poster
492KaiwenDuanCorner Proposal Network for Anchor-free, Two-stage Object Detection3012Wednesday 26 August 202000:00:00Spotlight
492KaiwenDuanCorner Proposal Network for Anchor-free, Two-stage Object Detection3012Wednesday 26 August 202006:00:00Spotlight
494HiroakiSantoDeep near-light photometric stereo for spatially varying reflectances4009Thursday 27 August 202000:00:00Poster
494HiroakiSantoDeep near-light photometric stereo for spatially varying reflectances4009Thursday 27 August 202006:00:00Poster
495HenghuiDingPhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click1166Monday 24 August 202014:00:00Spotlight
495HenghuiDingPhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click1166Tuesday 25 August 202000:00:00Spotlight
498Mert BülentSarıyıldızLearning Visual Representations with Caption Annotations1014Monday 24 August 202006:00:00Poster
498Mert BülentSarıyıldızLearning Visual Representations with Caption Annotations1014Monday 24 August 202014:00:00Poster
500GuWangSelf6D: Self-Supervised Monocular 6D Object Pose Estimation2250Tuesday 25 August 202006:00:00Oral
500GuWangSelf6D: Self-Supervised Monocular 6D Object Pose Estimation2250Tuesday 25 August 202014:00:00Oral
509Tz-YingWuSolving Long-tailed Recognition with Deep Realistic Taxonomic Classifier2275Tuesday 25 August 202014:00:00Poster
509Tz-YingWuSolving Long-tailed Recognition with Deep Realistic Taxonomic Classifier2275Wednesday 26 August 202000:00:00Poster
512YandaMengRegression of Instance Boundary by Aggregated CNN and GCN3231Wednesday 26 August 202014:00:00Poster
512YandaMengRegression of Instance Boundary by Aggregated CNN and GCN3231Thursday 27 August 202000:00:00Poster
513YapengTianUnified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing2276Tuesday 25 August 202014:00:00Spotlight
513YapengTianUnified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing2276Wednesday 26 August 202000:00:00Spotlight
520RuiYanSocial Adaptive Module for Weakly-supervised Group Activity Recognition2014Tuesday 25 August 202000:00:00Poster
520RuiYanSocial Adaptive Module for Weakly-supervised Group Activity Recognition2014Tuesday 25 August 202006:00:00Poster
521ChongyiLiRGB-D Salient Object Detection with Cross-Modality Modulation and Selection3013Wednesday 26 August 202000:00:00Poster
521ChongyiLiRGB-D Salient Object Detection with Cross-Modality Modulation and Selection3013Wednesday 26 August 202006:00:00Poster
524WeilongYangRetrieveGAN: Image Synthesis via Differentiable Patch Retrieval3232Wednesday 26 August 202014:00:00Poster
524WeilongYangRetrieveGAN: Image Synthesis via Differentiable Patch Retrieval3232Thursday 27 August 202000:00:00Poster
526YuanhaoCaiLearning Delicate Local Representations for Multi-Person Pose Estimation4010Thursday 27 August 202000:00:00Spotlight
526YuanhaoCaiLearning Delicate Local Representations for Multi-Person Pose Estimation4010Thursday 27 August 202006:00:00Spotlight
529ShuxinZhengInvertible Image Rescaling2015Tuesday 25 August 202000:00:00Oral
529ShuxinZhengInvertible Image Rescaling2015Tuesday 25 August 202006:00:00Oral
536DongzhanZhouCheaper Pre-training Lunch: An Efficient Paradigm for Object Detection4011Thursday 27 August 202000:00:00Poster
536DongzhanZhouCheaper Pre-training Lunch: An Efficient Paradigm for Object Detection4011Thursday 27 August 202006:00:00Poster
544EdwardBeechingLearning to Plan with Uncertain Topological Maps1015Monday 24 August 202006:00:00Spotlight
544EdwardBeechingLearning to Plan with Uncertain Topological Maps1015Monday 24 August 202014:00:00Spotlight
566Guan'anWangFaster Person Re-Identification4234Thursday 27 August 202014:00:00Poster
566Guan'anWangFaster Person Re-Identification4234Friday 28 August 202000:00:00Poster
570MaxEhrlichQuantization Guided JPEG Artifact Correction4235Thursday 27 August 202014:00:00Poster
570MaxEhrlichQuantization Guided JPEG Artifact Correction4235Friday 28 August 202000:00:00Poster
571YujunChen3PointTM: Faster Measurement of High-Dimensional Transmission Matrices4236Thursday 27 August 202014:00:00Poster
571YujunChen3PointTM: Faster Measurement of High-Dimensional Transmission Matrices4236Friday 28 August 202000:00:00Poster
574Hsin-YingLeeNeural Design Network: Graphic Layout Generation with Constraints4237Thursday 27 August 202014:00:00Spotlight
574Hsin-YingLeeNeural Design Network: Graphic Layout Generation with Constraints4237Friday 28 August 202000:00:00Spotlight
575ZhengSunJoint Bilateral Learning for Real-time Universal Photorealistic Style Transfer4238Thursday 27 August 202014:00:00Poster
575ZhengSunJoint Bilateral Learning for Real-time Universal Photorealistic Style Transfer4238Friday 28 August 202000:00:00Poster
581XiangyuZhuBeyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction4012Thursday 27 August 202000:00:00Poster
581XiangyuZhuBeyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction4012Thursday 27 August 202006:00:00Poster
587ArunMallyaWorld-Consistent Video-to-Video Synthesis3233Wednesday 26 August 202014:00:00Poster
587ArunMallyaWorld-Consistent Video-to-Video Synthesis3233Thursday 27 August 202000:00:00Poster
591GuangyaoChenLearning Open Set Network with Discriminative Reciprocal Points4013Thursday 27 August 202000:00:00Spotlight
591GuangyaoChenLearning Open Set Network with Discriminative Reciprocal Points4013Thursday 27 August 202006:00:00Spotlight
596QiFanCommonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation2016Tuesday 25 August 202000:00:00Poster
596QiFanCommonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation2016Tuesday 25 August 202006:00:00Poster
597SongyouPengConvolutional Occupancy Networks1016Monday 24 August 202006:00:00Spotlight
597SongyouPengConvolutional Occupancy Networks1016Monday 24 August 202014:00:00Spotlight
598UmbertoMichieliGMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild1017Monday 24 August 202006:00:00Poster
598UmbertoMichieliGMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild1017Monday 24 August 202014:00:00Poster
600NicoMessikommerEvent-based Asynchronous Sparse Convolutional Networks1018Monday 24 August 202006:00:00Poster
600NicoMessikommerEvent-based Asynchronous Sparse Convolutional Networks1018Monday 24 August 202014:00:00Poster
604GiovanniPintoreAtlantaNet: Inferring the 3D Indoor Layout from a Single $360^\circ$ Image beyond the Manhattan World Assumption1019Monday 24 August 202006:00:00Poster
604GiovanniPintoreAtlantaNet: Inferring the 3D Indoor Layout from a Single $360^\circ$ Image beyond the Manhattan World Assumption1019Monday 24 August 202014:00:00Poster
607XiaofangWangAttentionNAS: Spatiotemporal Attention Cell Search for Video Classification4239Thursday 27 August 202014:00:00Poster
607XiaofangWangAttentionNAS: Spatiotemporal Attention Cell Search for Video Classification4239Friday 28 August 202000:00:00Poster
609TylerHayesREMIND Your Neural Network to Prevent Catastrophic Forgetting4240Thursday 27 August 202014:00:00Poster
609TylerHayesREMIND Your Neural Network to Prevent Catastrophic Forgetting4240Friday 28 August 202000:00:00Poster
611StanleyChanImage Classification in the Dark using Quanta Image Sensors4241Thursday 27 August 202014:00:00Poster
611StanleyChanImage Classification in the Dark using Quanta Image Sensors4241Friday 28 August 202000:00:00Poster
612YingdaXiaSynthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation4242Thursday 27 August 202014:00:00Oral
612YingdaXiaSynthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation4242Friday 28 August 202000:00:00Oral
615YanLuon-Reference Transfer Learning for Saliency Prediction4243Thursday 27 August 202014:00:00Poster
615YanLuon-Reference Transfer Learning for Saliency Prediction4243Friday 28 August 202000:00:00Poster
618ShuhanChenProgressively Guided Alternate Refinement Network for RGB-D Salient Object Detection2017Tuesday 25 August 202000:00:00Poster
618ShuhanChenProgressively Guided Alternate Refinement Network for RGB-D Salient Object Detection2017Tuesday 25 August 202006:00:00Poster
622PeisenZhaoBottom-Up Temporal Action Localization with Mutual Regularization4014Thursday 27 August 202000:00:00Poster
622PeisenZhaoBottom-Up Temporal Action Localization with Mutual Regularization4014Thursday 27 August 202006:00:00Poster
623ChristianSimonOn Modulating the Gradient for Meta-Learning2018Tuesday 25 August 202000:00:00Poster
623ChristianSimonOn Modulating the Gradient for Meta-Learning2018Tuesday 25 August 202006:00:00Poster
634Yung-YuChuangDomain-Specific Mappings for Generative Adversarial Style Transfer4015Thursday 27 August 202000:00:00Poster
634Yung-YuChuangDomain-Specific Mappings for Generative Adversarial Style Transfer4015Thursday 27 August 202006:00:00Poster
636TimoMilbichDiVA: Diverse Visual Feature Aggregation for Deep Metric Learning1020Monday 24 August 202006:00:00Poster
636TimoMilbichDiVA: Diverse Visual Feature Aggregation for Deep Metric Learning1020Monday 24 August 202014:00:00Poster
637YaweiLiDHP: Differentiable Meta Pruning via HyperNetworks3168Wednesday 26 August 202006:00:00Poster
637YaweiLiDHP: Differentiable Meta Pruning via HyperNetworks3168Wednesday 26 August 202014:00:00Poster
639ZhengXieDeep Transferring Quantization2019Tuesday 25 August 202000:00:00Poster
639ZhengXieDeep Transferring Quantization2019Tuesday 25 August 202006:00:00Poster
645GuangyiChenDeep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification4016Thursday 27 August 202000:00:00Poster
645GuangyiChenDeep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification4016Thursday 27 August 202006:00:00Poster
648GuangyiChenTemporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?2020Tuesday 25 August 202000:00:00Poster
648GuangyiChenTemporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?2020Tuesday 25 August 202006:00:00Poster
666JunchiYanArbitrary-Oriented Object Detection with Circular Smooth Label3014Wednesday 26 August 202000:00:00Poster
666JunchiYanArbitrary-Oriented Object Detection with Circular Smooth Label3014Wednesday 26 August 202006:00:00Poster
671SongnanLinLearning Event-Driven Video Deblurring and Interpolation3015Wednesday 26 August 202000:00:00Poster
671SongnanLinLearning Event-Driven Video Deblurring and Interpolation3015Wednesday 26 August 202006:00:00Poster
672He(Crane)ChenMulti-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry3234Wednesday 26 August 202014:00:00Spotlight
672He(Crane)ChenMulti-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry3234Thursday 27 August 202000:00:00Spotlight
677NelsonNauataHouse-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation2277Tuesday 25 August 202014:00:00Oral
677NelsonNauataHouse-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation2277Wednesday 26 August 202000:00:00Oral
678NelsonNauataVectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference3235Wednesday 26 August 202014:00:00Poster
678NelsonNauataVectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference3235Thursday 27 August 202000:00:00Poster
692HangWangLearning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation4244Thursday 27 August 202014:00:00Poster
692HangWangLearning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation4244Friday 28 August 202000:00:00Poster
696JiahuaDongCSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation2021Tuesday 25 August 202000:00:00Poster
696JiahuaDongCSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation2021Tuesday 25 August 202006:00:00Poster
700BoyuYangPrototype Mixture Models for Few-shot Semantic Segmentation2022Tuesday 25 August 202000:00:00Poster
700BoyuYangPrototype Mixture Models for Few-shot Semantic Segmentation2022Tuesday 25 August 202006:00:00Poster
701JingkangYangWebly Supervised Image Classification with Self-Contained Confidence4017Thursday 27 August 202000:00:00Poster
701JingkangYangWebly Supervised Image Classification with Self-Contained Confidence4017Thursday 27 August 202006:00:00Poster
704HaibaoYuSearch What You Want: Barrier Panelty NAS for Mixed Precision Quantization4245Thursday 27 August 202014:00:00Poster
704HaibaoYuSearch What You Want: Barrier Panelty NAS for Mixed Precision Quantization4245Friday 28 August 202000:00:00Poster
709XiaoqingYeMonocular 3D Object Detection via Feature Domain Adaptation4018Thursday 27 August 202000:00:00Poster
709XiaoqingYeMonocular 3D Object Detection via Feature Domain Adaptation4018Thursday 27 August 202006:00:00Poster
718LeleChenTalking-head Generation with Rhythmic Head Motion4246Thursday 27 August 202014:00:00Poster
718LeleChenTalking-head Generation with Rhythmic Head Motion4246Friday 28 August 202000:00:00Poster
719XiaofengLiuAUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation4247Thursday 27 August 202014:00:00Poster
719XiaofengLiuAUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation4247Friday 28 August 202000:00:00Poster
720SrijanDasVPN: Learning Video-Pose Embedding for Activities of Daily Living3169Wednesday 26 August 202006:00:00Poster
720SrijanDasVPN: Learning Video-Pose Embedding for Activities of Daily Living3169Wednesday 26 August 202014:00:00Poster
721ChenchenZhuSoft Anchor-Point Object Detection1167Monday 24 August 202014:00:00Poster
721ChenchenZhuSoft Anchor-Point Object Detection1167Tuesday 25 August 202000:00:00Poster
735JunGaoBeyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid2278Tuesday 25 August 202014:00:00Poster
735JunGaoBeyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid2278Wednesday 26 August 202000:00:00Poster
736ZhengqiLiCrowdsampling the Plenoptic Function4248Thursday 27 August 202014:00:00Oral
736ZhengqiLiCrowdsampling the Plenoptic Function4248Friday 28 August 202000:00:00Oral
738HanyueTuVoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment3016Wednesday 26 August 202000:00:00Oral
738HanyueTuVoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment3016Wednesday 26 August 202006:00:00Oral
751HuWangSoft Expert Reward Learning for Vision-and-Language Navigation2023Tuesday 25 August 202000:00:00Poster
751HuWangSoft Expert Reward Learning for Vision-and-Language Navigation2023Tuesday 25 August 202006:00:00Poster
754XiangyiZhangPart-aware Prototype Network for Few-shot Semantic Segmentation3017Wednesday 26 August 202000:00:00Poster
754XiangyiZhangPart-aware Prototype Network for Few-shot Semantic Segmentation3017Wednesday 26 August 202006:00:00Poster
759ShujunWangLearning from Extrinsic and Intrinsic Supervisions for Domain Generalization3018Wednesday 26 August 202000:00:00Poster
759ShujunWangLearning from Extrinsic and Intrinsic Supervisions for Domain Generalization3018Wednesday 26 August 202006:00:00Poster
761MahsaEhsanpourJoint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos3019Wednesday 26 August 202000:00:00Poster
761MahsaEhsanpourJoint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos3019Wednesday 26 August 202006:00:00Poster
768ShengJinWhole-Body Human Pose Estimation in the Wild2024Tuesday 25 August 202000:00:00Poster
768ShengJinWhole-Body Human Pose Estimation in the Wild2024Tuesday 25 August 202006:00:00Poster
770BoLiRelative Pose Estimation of Calibrated Cameras with Known $\mathrm{SE(3)$ Invariants3020Wednesday 26 August 202000:00:00Poster
770BoLiRelative Pose Estimation of Calibrated Cameras with Known $\mathrm{SE(3)$ Invariants3020Wednesday 26 August 202006:00:00Poster
777RunkaiZhengSequential Convolution and Runge-Kutta Residual Architecture for Image Compressed Sensing\thanks{This research is supported by National Natural Science Foundation of China grant No.61772232.4019Thursday 27 August 202000:00:00Poster
777RunkaiZhengSequential Convolution and Runge-Kutta Residual Architecture for Image Compressed Sensing\thanks{This research is supported by National Natural Science Foundation of China grant No.61772232.4019Thursday 27 August 202006:00:00Poster
779QiHanDeep Hough Transform for Semantic Line Detection4020Thursday 27 August 202000:00:00Poster
779QiHanDeep Hough Transform for Semantic Line Detection4020Thursday 27 August 202006:00:00Poster
781ShunMiaoStructured Landmark Detection via Topology-Adapting Deep Graph Learning4249Thursday 27 August 202014:00:00Poster
781ShunMiaoStructured Landmark Detection via Topology-Adapting Deep Graph Learning4249Friday 28 August 202000:00:00Poster
787XiangyuXu3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning4250Thursday 27 August 202014:00:00Poster
787XiangyuXu3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning4250Friday 28 August 202000:00:00Poster
790PrithvijitChattopadhyayLearning to Balance Specificity and Invariance for In and Out of Domain Generalization2279Tuesday 25 August 202014:00:00Poster
790PrithvijitChattopadhyayLearning to Balance Specificity and Invariance for In and Out of Domain Generalization2279Wednesday 26 August 202000:00:00Poster
792Jun-YanZhuContrastive Learning for Unpaired Image-to-Image Translation2280Tuesday 25 August 202014:00:00Poster
792Jun-YanZhuContrastive Learning for Unpaired Image-to-Image Translation2280Wednesday 26 August 202000:00:00Poster
794YeYuanDLow: Diversifying Latent Flows for Diverse Human Motion Prediction2281Tuesday 25 August 202014:00:00Poster
794YeYuanDLow: Diversifying Latent Flows for Diverse Human Motion Prediction2281Wednesday 26 August 202000:00:00Poster
798HaozheXieGRNet: Gridding Residual Network for Dense Point Cloud Completion3021Wednesday 26 August 202000:00:00Poster
798HaozheXieGRNet: Gridding Residual Network for Dense Point Cloud Completion3021Wednesday 26 August 202006:00:00Poster
800SaihuiHouGait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition2025Tuesday 25 August 202000:00:00Poster
800SaihuiHouGait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition2025Tuesday 25 August 202006:00:00Poster
806XiaomingLiBlind Face Restoration via Deep Multi-scale Component Dictionaries4021Thursday 27 August 202000:00:00Poster
806XiaomingLiBlind Face Restoration via Deep Multi-scale Component Dictionaries4021Thursday 27 August 202006:00:00Poster
832NicolasCarionEnd-to-End Object Detection with Transformers3170Wednesday 26 August 202006:00:00Oral
832NicolasCarionEnd-to-End Object Detection with Transformers3170Wednesday 26 August 202014:00:00Oral
840XingkuiWeiDeepSFM: Structure From Motion Via Deep Bundle Adjustment4251Thursday 27 August 202014:00:00Oral
840XingkuiWeiDeepSFM: Structure From Motion Via Deep Bundle Adjustment4251Friday 28 August 202000:00:00Oral
849DanielBolyaTIDE: A General Toolbox for Identifying Object Detection Errors2282Tuesday 25 August 202014:00:00Spotlight
849DanielBolyaTIDE: A General Toolbox for Identifying Object Detection Errors2282Wednesday 26 August 202000:00:00Spotlight
866JinyoungParkRobust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods2026Tuesday 25 August 202000:00:00Poster
866JinyoungParkRobust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods2026Tuesday 25 August 202006:00:00Poster
867EvangelosSariyanidiInequality-Constrained and Robust 3D Face Model Fitting2283Tuesday 25 August 202014:00:00Poster
867EvangelosSariyanidiInequality-Constrained and Robust 3D Face Model Fitting2283Wednesday 26 August 202000:00:00Poster
869PabloArbelaezGabor Layers Enhance Network Robustness2284Tuesday 25 August 202014:00:00Poster
869PabloArbelaezGabor Layers Enhance Network Robustness2284Wednesday 26 August 202000:00:00Poster
871ShuchenWengConditional Image Repainting via Semantic Bridge and Piecewise Value Function4022Thursday 27 August 202000:00:00Poster
871ShuchenWengConditional Image Repainting via Semantic Bridge and Piecewise Value Function4022Thursday 27 August 202006:00:00Poster
872TaihongXiaoLearnable Cost Volume Using the Cayley Representation4252Thursday 27 August 202014:00:00Poster
872TaihongXiaoLearnable Cost Volume Using the Cayley Representation4252Friday 28 August 202000:00:00Poster
884ChaojianLiHALO: Hardware-Aware Learning to Optimize2285Tuesday 25 August 202014:00:00Poster
884ChaojianLiHALO: Hardware-Aware Learning to Optimize2285Wednesday 26 August 202000:00:00Poster
890JiaZhengStructured3D: A Large Photo-realistic Dataset for Structured 3D Modeling3022Wednesday 26 August 202000:00:00Poster
890JiaZhengStructured3D: A Large Photo-realistic Dataset for Structured 3D Modeling3022Wednesday 26 August 202006:00:00Poster
893SainingXiePointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding4253Thursday 27 August 202014:00:00Spotlight
893SainingXiePointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding4253Friday 28 August 202000:00:00Spotlight
894Yonghyun KimKImBroadFace: Looking at Tens of Thousands of People at Once for Face Recognition4023Thursday 27 August 202000:00:00Poster
894Yonghyun KimKImBroadFace: Looking at Tens of Thousands of People at Once for Face Recognition4023Thursday 27 August 202006:00:00Poster
895XinzheHanInterpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision3023Wednesday 26 August 202000:00:00Poster
895XinzheHanInterpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision3023Wednesday 26 August 202006:00:00Poster
896SujoyPaulDomain Adaptive Semantic Segmentation Using Weak Labels4254Thursday 27 August 202014:00:00Poster
896SujoyPaulDomain Adaptive Semantic Segmentation Using Weak Labels4254Friday 28 August 202000:00:00Poster
898GuodongXuKnowledge Distillation Meets Self-Supervision2027Tuesday 25 August 202000:00:00Poster
898GuodongXuKnowledge Distillation Meets Self-Supervision2027Tuesday 25 August 202006:00:00Poster
909IgnacioRoccoEfficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions1021Monday 24 August 202006:00:00Poster
909IgnacioRoccoEfficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions1021Monday 24 August 202014:00:00Poster
910IoannisMarrasReconstructing the Noise Variance Manifold for Image Denoising1022Monday 24 August 202006:00:00Poster
910IoannisMarrasReconstructing the Noise Variance Manifold for Image Denoising1022Monday 24 August 202014:00:00Poster
916XiaoxiaoLongOcclusion-Aware Depth Estimation with Adaptive Normal Constraints3024Wednesday 26 August 202000:00:00Poster
916XiaoxiaoLongOcclusion-Aware Depth Estimation with Adaptive Normal Constraints3024Wednesday 26 August 202006:00:00Poster
922XuefeiNingDSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation4024Thursday 27 August 202000:00:00Spotlight
922XuefeiNingDSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation4024Thursday 27 August 202006:00:00Spotlight
927RuohanGaoSpatial Image Representation Learning through Echolocation4255Thursday 27 August 202014:00:00Poster
927RuohanGaoSpatial Image Representation Learning through Echolocation4255Friday 28 August 202000:00:00Poster
929VickyKalogeitonSmooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval2286Tuesday 25 August 202014:00:00Poster
929VickyKalogeitonSmooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval2286Wednesday 26 August 202000:00:00Poster
942Liang-ChiehChenNaive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation4256Thursday 27 August 202014:00:00Poster
942Liang-ChiehChenNaive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation4256Friday 28 August 202000:00:00Poster
946YashKantSpatially Aware Multimodal Transformers for TextVQA3236Wednesday 26 August 202014:00:00Poster
946YashKantSpatially Aware Multimodal Transformers for TextVQA3236Thursday 27 August 202000:00:00Poster
948Cheng-chunHsuEvery Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector2028Tuesday 25 August 202000:00:00Poster
948Cheng-chunHsuEvery Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector2028Tuesday 25 August 202006:00:00Poster
960TaeyoungSonURIE: Universal Image Enhancement for Visual Recognition in the Wild2029Tuesday 25 August 202000:00:00Poster
960TaeyoungSonURIE: Universal Image Enhancement for Visual Recognition in the Wild2029Tuesday 25 August 202006:00:00Poster
961HongweiYiPyramid Multi-view Stereo Net with Self-adaptive View Aggregation2030Tuesday 25 August 202000:00:00Poster
961HongweiYiPyramid Multi-view Stereo Net with Self-adaptive View Aggregation2030Tuesday 25 August 202006:00:00Poster
977JunbingLiSPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning3025Wednesday 26 August 202000:00:00Poster
977JunbingLiSPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning3025Wednesday 26 August 202006:00:00Poster
978YihaoZhaoUnpaired Image-to-Image Translation using Adversarial Consistency Loss2031Tuesday 25 August 202000:00:00Poster
978YihaoZhaoUnpaired Image-to-Image Translation using Adversarial Consistency Loss2031Tuesday 25 August 202006:00:00Poster
981ManyuanZhangDiscriminability Distillation in Group Representation Learning4025Thursday 27 August 202000:00:00Poster
981ManyuanZhangDiscriminability Distillation in Group Representation Learning4025Thursday 27 August 202006:00:00Poster
983VasileiosChoutasMonocular Expressive Body Regression through Body-Driven Attention1023Monday 24 August 202006:00:00Poster
983VasileiosChoutasMonocular Expressive Body Regression through Body-Driven Attention1023Monday 24 August 202014:00:00Poster
984ZongshengYueDual Adversarial Network: Toward Real-world Noise Removal and Noise Generation2032Tuesday 25 August 202000:00:00Poster
984ZongshengYueDual Adversarial Network: Toward Real-world Noise Removal and Noise Generation2032Tuesday 25 August 202006:00:00Poster
986SiLiuLinguistic Structure Guided Context Modeling for Referring Image Segmentation3026Wednesday 26 August 202000:00:00Poster
986SiLiuLinguistic Structure Guided Context Modeling for Referring Image Segmentation3026Wednesday 26 August 202006:00:00Poster
990LonghuiWeiCircumventing Outliers of AutoAugment with Knowledge Distillation2033Tuesday 25 August 202000:00:00Spotlight
990LonghuiWeiCircumventing Outliers of AutoAugment with Knowledge Distillation2033Tuesday 25 August 202006:00:00Spotlight
994Tzu-mingHsuFederated Visual Classification with Real-World Data Distribution4026Thursday 27 August 202000:00:00Poster
994Tzu-mingHsuFederated Visual Classification with Real-World Data Distribution4026Thursday 27 August 202006:00:00Poster
996AngeloPorrelloRobust Re-Identification by Multiple Views Knowledge Distillation1024Monday 24 August 202006:00:00Poster
996AngeloPorrelloRobust Re-Identification by Multiple Views Knowledge Distillation1024Monday 24 August 202014:00:00Poster
997HugoGermainS2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching1025Monday 24 August 202006:00:00Spotlight
997HugoGermainS2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching1025Monday 24 August 202014:00:00Spotlight
1003AbdullahAbuolaimDefocus Deblurring Using Dual-Pixel Data2287Tuesday 25 August 202014:00:00Poster
1003AbdullahAbuolaimDefocus Deblurring Using Dual-Pixel Data2287Wednesday 26 August 202000:00:00Poster
1008TianshuYuRhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos4257Thursday 27 August 202014:00:00Poster
1008TianshuYuRhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos4257Friday 28 August 202000:00:00Poster
1012UttaranBhattacharyaTake an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping1168Monday 24 August 202014:00:00Poster
1012UttaranBhattacharyaTake an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping1168Tuesday 25 August 202000:00:00Poster
1022LiangLiuWeighing Counts: Sequential Crowd Counting by Reinforcement Learning2034Tuesday 25 August 202000:00:00Poster
1022LiangLiuWeighing Counts: Sequential Crowd Counting by Reinforcement Learning2034Tuesday 25 August 202006:00:00Poster
1024FengLuReflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks4027Thursday 27 August 202000:00:00Poster
1024FengLuReflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks4027Thursday 27 August 202006:00:00Poster
1035YingjunDuLearning to Learn with Variational Information Bottleneck for Domain Generalization2035Tuesday 25 August 202000:00:00Poster
1035YingjunDuLearning to Learn with Variational Information Bottleneck for Domain Generalization2035Tuesday 25 August 202006:00:00Poster
1044YifanXuLadybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry1026Monday 24 August 202006:00:00Oral
1044YifanXuLadybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry1026Monday 24 August 202014:00:00Oral
1045RuixuanYuDeep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis4028Thursday 27 August 202000:00:00Poster
1045RuixuanYuDeep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis4028Thursday 27 August 202006:00:00Poster
1046GilShomronThanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks1027Monday 24 August 202006:00:00Poster
1046GilShomronThanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks1027Monday 24 August 202014:00:00Poster
1051JunchiYanLayered Neighborhood Expansion for Incremental Multiple Graph Matching3027Wednesday 26 August 202000:00:00Poster
1051JunchiYanLayered Neighborhood Expansion for Incremental Multiple Graph Matching3027Wednesday 26 August 202006:00:00Poster
1054PeixuanLiRTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving2036Tuesday 25 August 202000:00:00Spotlight
1054PeixuanLiRTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving2036Tuesday 25 August 202006:00:00Spotlight
1057WouterVan GansbekeSCAN: Learning to Classify Images without Labels1028Monday 24 August 202006:00:00Poster
1057WouterVan GansbekeSCAN: Learning to Classify Images without Labels1028Monday 24 August 202014:00:00Poster
1059ZhenboXuSegment as Points for Efficient Online Multi-Object Tracking and Segmentation4029Thursday 27 August 202000:00:00Oral
1059ZhenboXuSegment as Points for Efficient Online Multi-Object Tracking and Segmentation4029Thursday 27 August 202006:00:00Oral
1060YannisAvrithisGraph convolutional networks for learning with few clean and many noisy labels4218Thursday 27 August 202006:00:00Poster
1060YannisAvrithisGraph convolutional networks for learning with few clean and many noisy labels4218Thursday 27 August 202014:00:00Poster
1062XiankaiLuVideo Object Segmentation with Episodic Graph Memory Networks2288Tuesday 25 August 202014:00:00Spotlight
1062XiankaiLuVideo Object Segmentation with Episodic Graph Memory Networks2288Wednesday 26 August 202000:00:00Spotlight
1078YuankaiQiObject-and-Action Aware Model for Visual Language Navigation3028Wednesday 26 August 202000:00:00Poster
1078YuankaiQiObject-and-Action Aware Model for Visual Language Navigation3028Wednesday 26 August 202006:00:00Poster
1079KenkunLiuA Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose Estimation4258Thursday 27 August 202014:00:00Poster
1079KenkunLiuA Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose Estimation4258Friday 28 August 202000:00:00Poster
1086WenboLiMuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution4030Thursday 27 August 202000:00:00Poster
1086WenboLiMuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution4030Thursday 27 August 202006:00:00Poster
1094JingdongWangEfficient Semantic Video Segmentation with Per-frame Inference4031Thursday 27 August 202000:00:00Poster
1094JingdongWangEfficient Semantic Video Segmentation with Per-frame Inference4031Thursday 27 August 202006:00:00Poster
1097ChristophKamannIncreasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers1029Monday 24 August 202006:00:00Poster
1097ChristophKamannIncreasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers1029Monday 24 August 202014:00:00Poster
1101ZhouDaquanRethinking Bottleneck Structure for Efficient Mobile Network Design3029Wednesday 26 August 202000:00:00Spotlight
1101ZhouDaquanRethinking Bottleneck Structure for Efficient Mobile Network Design3029Wednesday 26 August 202006:00:00Spotlight
1103BingHanDeep Spiking Neural Network: Energy Efficiency Through Time based Coding1169Monday 24 August 202014:00:00Poster
1103BingHanDeep Spiking Neural Network: Energy Efficiency Through Time based Coding1169Tuesday 25 August 202000:00:00Poster
1104Jeffrey OuyangZhangSide-Tuning: A Baseline for Network Adaptation via Additive Side Networks4259Thursday 27 August 202014:00:00Spotlight
1104Jeffrey OuyangZhangSide-Tuning: A Baseline for Network Adaptation via Additive Side Networks4259Friday 28 August 202000:00:00Spotlight
1105ZhiTianConditional Convolutions for Instance Segmentation4032Thursday 27 August 202000:00:00Oral
1105ZhiTianConditional Convolutions for Instance Segmentation4032Thursday 27 August 202006:00:00Oral
1121ZeruiChenTowards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach4033Thursday 27 August 202000:00:00Spotlight
1121ZeruiChenTowards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach4033Thursday 27 August 202006:00:00Spotlight
1137JunWangInfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling3237Wednesday 26 August 202014:00:00Poster
1137JunWangInfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling3237Thursday 27 August 202000:00:00Poster
1139PoojanOzaUtilizing Patch-level Category Activation Patterns for Multiple Class Novelty Detection2289Tuesday 25 August 202014:00:00Poster
1139PoojanOzaUtilizing Patch-level Category Activation Patterns for Multiple Class Novelty Detection2289Wednesday 26 August 202000:00:00Poster
1143YifanWangPeople as Scene Probes4260Thursday 27 August 202014:00:00Poster
1143YifanWangPeople as Scene Probes4260Friday 28 August 202000:00:00Poster
1147LeiYangMapping in a Cycle: Sinkhorn Regularized Unsupervised Learning for Point Cloud Shapes3030Wednesday 26 August 202000:00:00Poster
1147LeiYangMapping in a Cycle: Sinkhorn Regularized Unsupervised Learning for Point Cloud Shapes3030Wednesday 26 August 202006:00:00Poster
1148MatheusGadelhaLabel-Efficient Learning on Point Clouds using Approximate Convex Decompositions2290Tuesday 25 August 202014:00:00Poster
1148MatheusGadelhaLabel-Efficient Learning on Point Clouds using Approximate Convex Decompositions2290Wednesday 26 August 202000:00:00Poster
1152MinhVoTexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video3238Wednesday 26 August 202014:00:00Poster
1152MinhVoTexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video3238Thursday 27 August 202000:00:00Poster
1153ZizhaoZhangConsistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost2291Tuesday 25 August 202014:00:00Poster
1153ZizhaoZhangConsistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost2291Wednesday 26 August 202000:00:00Poster
1162FangyunWeiPoint-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation2037Tuesday 25 August 202000:00:00Poster
1162FangyunWeiPoint-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation2037Tuesday 25 August 202006:00:00Poster
1163ChengLinModeling 3D Shapes by Reinforcement Learning4034Thursday 27 August 202000:00:00Poster
1163ChengLinModeling 3D Shapes by Reinforcement Learning4034Thursday 27 August 202006:00:00Poster
1164LidaLiLST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform4035Thursday 27 August 202000:00:00Poster
1164LidaLiLST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform4035Thursday 27 August 202006:00:00Poster
1165DamienTeneyLearning What Makes a Difference from Counterfactual Examples and Gradient Supervision2038Tuesday 25 August 202000:00:00Poster
1165DamienTeneyLearning What Makes a Difference from Counterfactual Examples and Gradient Supervision2038Tuesday 25 August 202006:00:00Poster
1171ZetongYangCN: Channel Normalization For Point Cloud Recognition2039Tuesday 25 August 202000:00:00Poster
1171ZetongYangCN: Channel Normalization For Point Cloud Recognition2039Tuesday 25 August 202006:00:00Poster
1182JunchiYanRethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD Model2040Tuesday 25 August 202000:00:00Poster
1182JunchiYanRethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD Model2040Tuesday 25 August 202006:00:00Poster
1184JunchiYanAutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning3031Wednesday 26 August 202000:00:00Poster
1184JunchiYanAutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning3031Wednesday 26 August 202006:00:00Poster
1186WenjiaWangScene Text Image Super-resolution in the wild4036Thursday 27 August 202000:00:00Poster
1186WenjiaWangScene Text Image Super-resolution in the wild4036Thursday 27 August 202006:00:00Poster
1196TaojiannanYangMutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution2292Tuesday 25 August 202014:00:00Oral
1196TaojiannanYangMutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution2292Wednesday 26 August 202000:00:00Oral
1203MenglinJiaFashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset3239Wednesday 26 August 202014:00:00Oral
1203MenglinJiaFashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset3239Thursday 27 August 202000:00:00Oral
1207AngelinaWangREVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets4261Thursday 27 August 202014:00:00Spotlight
1207AngelinaWangREVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets4261Friday 28 August 202000:00:00Spotlight
1220OmidPoursaeedCoupling Explicit and Implicit Surface Representations for Generative 3D Modeling4262Thursday 27 August 202014:00:00Poster
1220OmidPoursaeedCoupling Explicit and Implicit Surface Representations for Generative 3D Modeling4262Friday 28 August 202000:00:00Poster
1227XinqiZhuLearning Disentangled Representations with Latent Variation Predictability3032Wednesday 26 August 202000:00:00Poster
1227XinqiZhuLearning Disentangled Representations with Latent Variation Predictability3032Wednesday 26 August 202006:00:00Poster
1232JaeyeonKangDeep Space-Time Video Upsampling Networks4037Thursday 27 August 202000:00:00Poster
1232JaeyeonKangDeep Space-Time Video Upsampling Networks4037Thursday 27 August 202006:00:00Poster
1242ShuoWangLarge-Scale Few-Shot Learning via Multi-Modal Knowledge Discovery2041Tuesday 25 August 202000:00:00Poster
1242ShuoWangLarge-Scale Few-Shot Learning via Multi-Modal Knowledge Discovery2041Tuesday 25 August 202006:00:00Poster
1248YuLiFast Video Object Segmentation using the Global Context Module3033Wednesday 26 August 202000:00:00Poster
1248YuLiFast Video Object Segmentation using the Global Context Module3033Wednesday 26 August 202006:00:00Poster
1263AnuragArnabUncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos1030Monday 24 August 202006:00:00Poster
1263AnuragArnabUncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos1030Monday 24 August 202014:00:00Poster
1267NikitaDvornikSelecting Relevant Features from a Multi-domain Representation for Few-shot Classification3240Wednesday 26 August 202014:00:00Poster
1267NikitaDvornikSelecting Relevant Features from a Multi-domain Representation for Few-shot Classification3240Thursday 27 August 202000:00:00Poster
1273MarcelGeppertPrivacy Preserving Structure-from-Motion1031Monday 24 August 202006:00:00Oral
1273MarcelGeppertPrivacy Preserving Structure-from-Motion1031Monday 24 August 202014:00:00Oral
1276ZhongangCaiMessyTable: Instance Association in Multiple Camera Views2042Tuesday 25 August 202000:00:00Poster
1276ZhongangCaiMessyTable: Instance Association in Multiple Camera Views2042Tuesday 25 August 202006:00:00Poster
1277AnyiRaoA Unified Framework for Shot Type Classification Based on Subject Centric Lens2043Tuesday 25 August 202000:00:00Poster
1277AnyiRaoA Unified Framework for Shot Type Classification Based on Subject Centric Lens2043Tuesday 25 August 202006:00:00Poster
1279SamuelALBANIEBSL-1K: Scaling up co-articulated sign language recognition using mouthing cues3241Wednesday 26 August 202014:00:00Poster
1279SamuelALBANIEBSL-1K: Scaling up co-articulated sign language recognition using mouthing cues3241Thursday 27 August 202000:00:00Poster
1280JiayiWangHTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization1032Monday 24 August 202006:00:00Poster
1280JiayiWangHTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization1032Monday 24 August 202014:00:00Poster
1290ZhongdaoWangCycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions3034Wednesday 26 August 202000:00:00Poster
1290ZhongdaoWangCycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions3034Wednesday 26 August 202006:00:00Poster
1291XihuiLiuOpen-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions4038Thursday 27 August 202000:00:00Poster
1291XihuiLiuOpen-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions4038Thursday 27 August 202006:00:00Poster
1292ZhongdaoWangTowards Real-Time Multi-Object Tracking4039Thursday 27 August 202000:00:00Poster
1292ZhongdaoWangTowards Real-Time Multi-Object Tracking4039Thursday 27 August 202006:00:00Poster
1294JianLiangA Balanced and Uncertainty-aware Approach for Partial Domain Adaptation3035Wednesday 26 August 202000:00:00Poster
1294JianLiangA Balanced and Uncertainty-aware Approach for Partial Domain Adaptation3035Wednesday 26 August 202006:00:00Poster
1295YangLiUnsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss4263Thursday 27 August 202014:00:00Poster
1295YangLiUnsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss4263Friday 28 August 202000:00:00Poster
1299AliAtharSTEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos3171Wednesday 26 August 202006:00:00Poster
1299AliAtharSTEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos3171Wednesday 26 August 202014:00:00Poster
1302JingweiXuHierarchical Style-based Networks for Motion Synthesis4264Thursday 27 August 202014:00:00Poster
1302JingweiXuHierarchical Style-based Networks for Motion Synthesis4264Friday 28 August 202000:00:00Poster
1303BenjaminBiggsWho Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop3242Wednesday 26 August 202014:00:00Poster
1303BenjaminBiggsWho Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop3242Thursday 27 August 202000:00:00Poster
1308RajeevYasarlaLearning to Count in the Crowd from Limited Labeled Data3243Wednesday 26 August 202014:00:00Poster
1308RajeevYasarlaLearning to Count in the Crowd from Limited Labeled Data3243Thursday 27 August 202000:00:00Poster
1314BoLiuSPOT: Selective Point Cloud Voting for Better Proposal in Point Cloud Object Detection4265Thursday 27 August 202014:00:00Poster
1314BoLiuSPOT: Selective Point Cloud Voting for Better Proposal in Point Cloud Object Detection4265Friday 28 August 202000:00:00Poster
1319BrandonMayExplainable Face Recognition3244Wednesday 26 August 202014:00:00Poster
1319BrandonMayExplainable Face Recognition3244Thursday 27 August 202000:00:00Poster
1321DimitrisSamarasFrom Shadow Segmentation to Shadow Removal4266Thursday 27 August 202014:00:00Poster
1321DimitrisSamarasFrom Shadow Segmentation to Shadow Removal4266Friday 28 August 202000:00:00Poster
1322Seong HyeonParkDiverse and Admissible Trajectory Prediction through Multimodal Context Understanding3036Wednesday 26 August 202000:00:00Poster
1322Seong HyeonParkDiverse and Admissible Trajectory Prediction through Multimodal Context Understanding3036Wednesday 26 August 202006:00:00Poster
1326DavidBauRewriting a Deep Generative Model4267Thursday 27 August 202014:00:00Oral
1326DavidBauRewriting a Deep Generative Model4267Friday 28 August 202000:00:00Oral
1327TanmayGuptaContrastive Learning for Weakly Supervised Phrase Grounding4268Thursday 27 August 202014:00:00Spotlight
1327TanmayGuptaContrastive Learning for Weakly Supervised Phrase Grounding4268Friday 28 August 202000:00:00Spotlight
1332MarekKowalskiCONFIG: Controllable Neural Face Image Generation3172Wednesday 26 August 202006:00:00Poster
1332MarekKowalskiCONFIG: Controllable Neural Face Image Generation3172Wednesday 26 August 202014:00:00Poster
1337RuiZhuSingle View Metrology in the Wild4269Thursday 27 August 202014:00:00Poster
1337RuiZhuSingle View Metrology in the Wild4269Friday 28 August 202000:00:00Poster
1340Chien-YiChangProcedure Planning in Instructional Videos4040Thursday 27 August 202000:00:00Poster
1340Chien-YiChangProcedure Planning in Instructional Videos4040Thursday 27 August 202006:00:00Poster
1342NingningMaFunnel Activation for Visual Recognition4041Thursday 27 August 202000:00:00Poster
1342NingningMaFunnel Activation for Visual Recognition4041Thursday 27 August 202006:00:00Poster
1354DongChenGIQA: Generated Image Quality Assessment3037Wednesday 26 August 202000:00:00Poster
1354DongChenGIQA: Generated Image Quality Assessment3037Wednesday 26 August 202006:00:00Poster
1355SaynaEbrahimiAdversarial Continual Learning3245Wednesday 26 August 202014:00:00Poster
1355SaynaEbrahimiAdversarial Continual Learning3245Thursday 27 August 202000:00:00Poster
1358PengSuAdapting Object Detectors with Conditional Domain Normalization4042Thursday 27 August 202000:00:00Poster
1358PengSuAdapting Object Detectors with Conditional Domain Normalization4042Thursday 27 August 202006:00:00Poster
1360TianjiaoLiHARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction2044Tuesday 25 August 202000:00:00Poster
1360TianjiaoLiHARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction2044Tuesday 25 August 202006:00:00Poster
1362SiyuanYangCollaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis4043Thursday 27 August 202000:00:00Spotlight
1362SiyuanYangCollaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis4043Thursday 27 August 202006:00:00Spotlight
1363LokenderTiwariPseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction1033Monday 24 August 202006:00:00Poster
1363LokenderTiwariPseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction1033Monday 24 August 202014:00:00Poster
1369ShengcaiLiaoInterpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting4270Thursday 27 August 202014:00:00Poster
1369ShengcaiLiaoInterpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting4270Thursday 27 August 202000:00:00Poster
1372HuiJiSelf-supervised Bayesian Deep Learning for Image Recovery with Applications to Compressive Sensing4044Thursday 27 August 202000:00:00Poster
1372HuiJiSelf-supervised Bayesian Deep Learning for Image Recovery with Applications to Compressive Sensing4044Thursday 27 August 202006:00:00Poster
1380JianWangGraph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement2045Tuesday 25 August 202000:00:00Poster
1380JianWangGraph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement2045Tuesday 25 August 202006:00:00Poster
1381MinchulShinSemi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction4045Thursday 27 August 202000:00:00Poster
1381MinchulShinSemi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction4045Thursday 27 August 202006:00:00Poster
1391FangZhaoUnsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification2293Tuesday 25 August 202014:00:00Poster
1391FangZhaoUnsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification2293Wednesday 26 August 202000:00:00Poster
1395DahliaUrbachDPDist: Comparing Point Clouds Using Deep Point Cloud Distance3173Wednesday 26 August 202006:00:00Poster
1395DahliaUrbachDPDist: Comparing Point Clouds Using Deep Point Cloud Distance3173Wednesday 26 August 202014:00:00Poster
1399XiaokangChenBi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation3038Wednesday 26 August 202000:00:00Poster
1399XiaokangChenBi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation3038Wednesday 26 August 202006:00:00Poster
1408ZhijianLiuDataMix: Efficient Privacy-Preserving Edge-Cloud Inference4271Thursday 27 August 202014:00:00Poster
1408ZhijianLiuDataMix: Efficient Privacy-Preserving Edge-Cloud Inference4271Friday 28 August 202000:00:00Poster
1415KripasindhuSarkarNeural Re-Rendering of Humans from a Single Image1034Monday 24 August 202006:00:00Poster
1415KripasindhuSarkarNeural Re-Rendering of Humans from a Single Image1034Monday 24 August 202014:00:00Poster
1417JiuniuWangCompare and Reweight: Distinctive Image Captioning Using Similar Images Sets3039Wednesday 26 August 202000:00:00Oral
1417JiuniuWangCompare and Reweight: Distinctive Image Captioning Using Similar Images Sets3039Wednesday 26 August 202006:00:00Oral
1420FilippoAleottiReversing the cycle: self-supervised deep stereo through enhanced monocular distillation1035Monday 24 August 202006:00:00Poster
1420FilippoAleottiReversing the cycle: self-supervised deep stereo through enhanced monocular distillation1035Monday 24 August 202014:00:00Poster
1421JinjinGuPIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration2046Tuesday 25 August 202000:00:00Poster
1421JinjinGuPIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration2046Tuesday 25 August 202006:00:00Poster
1422BryanPlummerWhy do These Match? Explaining the Behavior of Image Similarity Models4272Thursday 27 August 202014:00:00Poster
1422BryanPlummerWhy do These Match? Explaining the Behavior of Image Similarity Models4272Friday 28 August 202000:00:00Poster
1425ZuxuanWuMaking an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors2294Tuesday 25 August 202014:00:00Spotlight
1425ZuxuanWuMaking an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors2294Wednesday 26 August 202000:00:00Spotlight
1426XuanhongChenCooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing3040Wednesday 26 August 202000:00:00Poster
1426XuanhongChenCooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing3040Wednesday 26 August 202006:00:00Poster
1430BenSaundersProgressive Transformers for End-to-End Sign Language Production4273Thursday 27 August 202014:00:00Poster
1430BenSaundersProgressive Transformers for End-to-End Sign Language Production4273Friday 28 August 202000:00:00Poster
1436MinghuiLiaoMask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting2295Tuesday 25 August 202014:00:00Poster
1436MinghuiLiaoMask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting2295Wednesday 26 August 202000:00:00Poster
1440DanielBarathMaking Affine Correspondences Work in Camera Geometry Computation1036Monday 24 August 202006:00:00Poster
1440DanielBarathMaking Affine Correspondences Work in Camera Geometry Computation1036Monday 24 August 202014:00:00Poster
1445JiankangDengSub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces4274Thursday 27 August 202014:00:00Poster
1445JiankangDengSub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces4274Friday 28 August 202000:00:00Poster
1448ZheCaoLong-term Human Motion Prediction with Scene Context4275Thursday 27 August 202014:00:00Oral
1448ZheCaoLong-term Human Motion Prediction with Scene Context4275Friday 28 August 202000:00:00Oral
1449YingxuePangTuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images3041Wednesday 26 August 202000:00:00Spotlight
1449YingxuePangTuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images3041Wednesday 26 August 202006:00:00Spotlight
1450ChuangGanFoley Music: Learning to Generate Music from Videos4276Thursday 27 August 202014:00:00Poster
1450ChuangGanFoley Music: Learning to Generate Music from Videos4276Friday 28 August 202000:00:00Poster
1453YonglongTianContrastive Multiview Coding4277Thursday 27 August 202014:00:00Poster
1453YonglongTianContrastive Multiview Coding4277Friday 28 August 202000:00:00Poster
1456YingweiLiRegional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses2296Tuesday 25 August 202014:00:00Poster
1456YingweiLiRegional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses2296Wednesday 26 August 202000:00:00Poster
1469ShoukaiXuGenerative Low-bitwidth Data Free Quantization2047Tuesday 25 August 202000:00:00Poster
1469ShoukaiXuGenerative Low-bitwidth Data Free Quantization2047Tuesday 25 August 202006:00:00Poster
1470JianlongWuLocal Correlation Consistency for Knowledge Distillation2048Tuesday 25 August 202000:00:00Poster
1470JianlongWuLocal Correlation Consistency for Knowledge Distillation2048Tuesday 25 August 202006:00:00Poster
1473PratulSrinivasanNeRF: Representing Scenes as Neural Radiance Fields for View Synthesis4278Thursday 27 August 202014:00:00Oral
1473PratulSrinivasanNeRF: Representing Scenes as Neural Radiance Fields for View Synthesis4278Friday 28 August 202000:00:00Oral
1474JitendraMalikPerceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild2297Tuesday 25 August 202014:00:00Poster
1474JitendraMalikPerceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild2297Wednesday 26 August 202000:00:00Poster
1479HangDuSemi-Siamese Training for Shallow Face Learning2049Tuesday 25 August 202000:00:00Spotlight
1479HangDuSemi-Siamese Training for Shallow Face Learning2049Tuesday 25 August 202006:00:00Spotlight
1483HangZhouSep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation3042Wednesday 26 August 202000:00:00Poster
1483HangZhouSep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation3042Wednesday 26 August 202006:00:00Poster
1485JingShaoCelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations2050Tuesday 25 August 202000:00:00Poster
1485JingShaoCelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations2050Tuesday 25 August 202006:00:00Poster
1486GuojunYinThinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues3043Wednesday 26 August 202000:00:00Poster
1486GuojunYinThinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues3043Wednesday 26 August 202006:00:00Poster
1488HaotaoWangGAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework2298Tuesday 25 August 202014:00:00Spotlight
1488HaotaoWangGAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework2298Wednesday 26 August 202000:00:00Spotlight
1489KazuyaNihsimuraWeakly-Supervised Cell Tracking via Backward-and-Forward Propagation2051Tuesday 25 August 202000:00:00Poster
1489KazuyaNihsimuraWeakly-Supervised Cell Tracking via Backward-and-Forward Propagation2051Tuesday 25 August 202006:00:00Poster
1491JohnYangSeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape Estimation2052Tuesday 25 August 202000:00:00Poster
1491JohnYangSeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape Estimation2052Tuesday 25 August 202006:00:00Poster
1493ZijieZhuangRethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization2053Tuesday 25 August 202000:00:00Poster
1493ZijieZhuangRethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization2053Tuesday 25 August 202006:00:00Poster
1501PanagiotisAchlioptasReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes2299Tuesday 25 August 202014:00:00Oral
1501PanagiotisAchlioptasReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes2299Wednesday 26 August 202000:00:00Oral
1509XiaobingZhangAMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation2054Tuesday 25 August 202000:00:00Poster
1509XiaobingZhangAMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation2054Tuesday 25 August 202006:00:00Poster
1514AnyiRaoOnline Multi-modal Person Search in Videos3044Wednesday 26 August 202000:00:00Poster
1514AnyiRaoOnline Multi-modal Person Search in Videos3044Wednesday 26 August 202006:00:00Poster
1520LianpingYangSingle Image Super-Resolution via a Holistic Attention Network3045Wednesday 26 August 202000:00:00Poster
1520LianpingYangSingle Image Super-Resolution via a Holistic Attention Network3045Wednesday 26 August 202006:00:00Poster
1526YukunSuHuman Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition4046Thursday 27 August 202000:00:00Spotlight
1526YukunSuHuman Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition4046Thursday 27 August 202006:00:00Spotlight
1530JingweiXinBinarized Neural Network for Single Image Super Resolution2055Tuesday 25 August 202000:00:00Spotlight
1530JingweiXinBinarized Neural Network for Single Image Super Resolution2055Tuesday 25 August 202006:00:00Spotlight
1535AmirMarkovitzCan You Read Me Now? Content Aware Rectification using Angle Supervision2251Tuesday 25 August 202006:00:00Poster
1535AmirMarkovitzCan You Read Me Now? Content Aware Rectification using Angle Supervision2251Tuesday 25 August 202014:00:00Poster
1538HongweiYongMomentum Batch Normalization for Deep Learning with Small Batch Size3046Wednesday 26 August 202000:00:00Poster
1538HongweiYongMomentum Batch Normalization for Deep Learning with Small Batch Size3046Wednesday 26 August 202006:00:00Poster
1541AbdullahHamdiAdvPC: Transferable Adversarial Perturbations on 3D Point Clouds1170Monday 24 August 202014:00:00Poster
1541AbdullahHamdiAdvPC: Transferable Adversarial Perturbations on 3D Point Clouds1170Tuesday 25 August 202000:00:00Poster
1543YingluLiuEdge-aware Graph Representation Learning and Reasoning for Face Parsing4047Thursday 27 August 202000:00:00Poster
1543YingluLiuEdge-aware Graph Representation Learning and Reasoning for Face Parsing4047Thursday 27 August 202006:00:00Poster
1547Deng-pingFanBBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network4279Thursday 27 August 202014:00:00Poster
1547Deng-pingFanBBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network4279Friday 28 August 202000:00:00Poster
1557SarahOstadabbasG-LBM:Generative Low-dimensional Background Model Estimation from Video Sequences3246Wednesday 26 August 202014:00:00Poster
1557SarahOstadabbasG-LBM:Generative Low-dimensional Background Model Estimation from Video Sequences3246Thursday 27 August 202000:00:00Poster
1561ZaiweiZhangH3DNet: 3D Object Detection Using Hybrid Geometric Primitives3247Wednesday 26 August 202014:00:00Poster
1561ZaiweiZhangH3DNet: 3D Object Detection Using Hybrid Geometric Primitives3247Thursday 27 August 202000:00:00Poster
1564HuiyuWangAxial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation2300Tuesday 25 August 202014:00:00Spotlight
1564HuiyuWangAxial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation2300Wednesday 26 August 202000:00:00Spotlight
1567HangChuExpressive Telepresence via Modular Codec Avatars2301Tuesday 25 August 202014:00:00Poster
1567HangChuExpressive Telepresence via Modular Codec Avatars2301Wednesday 26 August 202000:00:00Poster
1571AoLuoCascade Graph Neural Networks for RGB-D Salient Object Detection4048Thursday 27 August 202000:00:00Poster
1571AoLuoCascade Graph Neural Networks for RGB-D Salient Object Detection4048Thursday 27 August 202006:00:00Poster
1585VishnuLokhandeFairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret2302Tuesday 25 August 202014:00:00Poster
1585VishnuLokhandeFairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret2302Wednesday 26 August 202000:00:00Poster
1586MeghaNawhalGenerating Videos of Zero-Shot Compositions of Actions and Objects4280Thursday 27 August 202014:00:00Poster
1586MeghaNawhalGenerating Videos of Zero-Shot Compositions of Actions and Objects4280Friday 28 August 202000:00:00Poster
1593ZhiyuanFangVisual-Textual Attributes Alignment in Person Search by Natural Language3047Wednesday 26 August 202000:00:00Poster
1593ZhiyuanFangVisual-Textual Attributes Alignment in Person Search by Natural Language3047Wednesday 26 August 202006:00:00Poster
1600LuYangRenovating Parsing R-CNN for Accurate Multiple Human Parsing3048Wednesday 26 August 202000:00:00Poster
1600LuYangRenovating Parsing R-CNN for Accurate Multiple Human Parsing3048Wednesday 26 August 202006:00:00Poster
1605ZhipengFanAdaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation4281Thursday 27 August 202014:00:00Spotlight
1605ZhipengFanAdaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation4281Friday 28 August 202000:00:00Spotlight
1612QingYuMulti-Task Curriculum Framework for Open-Set Semi-Supervised Learning2056Tuesday 25 August 202000:00:00Poster
1612QingYuMulti-Task Curriculum Framework for Open-Set Semi-Supervised Learning2056Tuesday 25 August 202006:00:00Poster
1615ZhaoZhangGradient-Induced Co-Saliency Detection3049Wednesday 26 August 202000:00:00Poster
1615ZhaoZhangGradient-Induced Co-Saliency Detection3049Wednesday 26 August 202006:00:00Poster
1616YANWendingNighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color Networks4049Thursday 27 August 202000:00:00Poster
1616YANWendingNighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color Networks4049Thursday 27 August 202006:00:00Poster
1624JinlongPengChained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking3050Wednesday 26 August 202000:00:00Spotlight
1624JinlongPengChained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking3050Wednesday 26 August 202006:00:00Spotlight
1631TongWuDistribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets3051Wednesday 26 August 202000:00:00Spotlight
1631TongWuDistribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets3051Wednesday 26 August 202006:00:00Spotlight
1633JingyiXieSegFix: Model-Agnostic Boundary Refinement for Segmentation2057Tuesday 25 August 202000:00:00Poster
1633JingyiXieSegFix: Model-Agnostic Boundary Refinement for Segmentation2057Tuesday 25 August 202006:00:00Poster
1636CunjunYuSpatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction2058Tuesday 25 August 202000:00:00Poster
1636CunjunYuSpatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction2058Tuesday 25 August 202006:00:00Poster
1637EgorZakharovFast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars2252Tuesday 25 August 202006:00:00Poster
1637EgorZakharovFast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars2252Tuesday 25 August 202014:00:00Poster
1644JunhoKimNeural Geometric Parser for Single Image Camera Calibration3052Wednesday 26 August 202000:00:00Poster
1644JunhoKimNeural Geometric Parser for Single Image Camera Calibration3052Wednesday 26 August 202006:00:00Poster
1647YuxiangWeiLearning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision2059Tuesday 25 August 202000:00:00Poster
1647YuxiangWeiLearning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision2059Tuesday 25 August 202006:00:00Poster
1652DahyunKimLearning Architectures for Binary Networks3053Wednesday 26 August 202000:00:00Poster
1652DahyunKimLearning Architectures for Binary Networks3053Wednesday 26 August 202006:00:00Poster
1653Jia-binHuangSemantic View Synthesis4282Thursday 27 August 202014:00:00Poster
1653Jia-binHuangSemantic View Synthesis4282Friday 28 August 202000:00:00Poster
1659YasuyukiMatsushitaAn Analysis of Sketched IRLS for Accelerated Sparse Residual Regression4050Thursday 27 August 202000:00:00Poster
1659YasuyukiMatsushitaAn Analysis of Sketched IRLS for Accelerated Sparse Residual Regression4050Thursday 27 August 202006:00:00Poster
1676MarvinEisenbergerHamiltonian Dynamics for Real-World Shape Interpolation3174Wednesday 26 August 202006:00:00Spotlight
1676MarvinEisenbergerHamiltonian Dynamics for Real-World Shape Interpolation3174Wednesday 26 August 202014:00:00Spotlight
1677IvanEichhardtRelative Pose from Deep Learned Depth and a Single Affine Correspondence1037Monday 24 August 202006:00:00Poster
1677IvanEichhardtRelative Pose from Deep Learned Depth and a Single Affine Correspondence1037Monday 24 August 202014:00:00Poster
1694AndreaBurnsLearning to Scale Multilingual Representations for Vision-Language Tasks4283Thursday 27 August 202014:00:00Spotlight
1694AndreaBurnsLearning to Scale Multilingual Representations for Vision-Language Tasks4283Friday 28 August 202000:00:00Spotlight
1698TakashiIsobeVideo Super-Resolution with Recurrent Structure-Detail Network4051Thursday 27 August 202000:00:00Poster
1698TakashiIsobeVideo Super-Resolution with Recurrent Structure-Detail Network4051Thursday 27 August 202006:00:00Poster
1702ShikunLiuShape Adaptor: A Learnable Resizing Module3248Wednesday 26 August 202014:00:00Poster
1702ShikunLiuShape Adaptor: A Learnable Resizing Module3248Thursday 27 August 202000:00:00Poster
1710ValentinGabeurMulti-modal Transformer for Video Retrieval3175Wednesday 26 August 202006:00:00Spotlight
1710ValentinGabeurMulti-modal Transformer for Video Retrieval3175Wednesday 26 August 202014:00:00Spotlight
1712JinwooChoiShuffle and Attend: Video Domain Adaptation4284Thursday 27 August 202014:00:00Poster
1712JinwooChoiShuffle and Attend: Video Domain Adaptation4284Friday 28 August 202000:00:00Poster
1714Jia-binHuangDRG: Dual Relation Graph for Human-Object Interaction Detection3249Wednesday 26 August 202014:00:00Poster
1714Jia-binHuangDRG: Dual Relation Graph for Human-Object Interaction Detection3249Thursday 27 August 202000:00:00Poster
1715ChenGaoFlow-edge Guided Video Completion2303Tuesday 25 August 202014:00:00Poster
1715ChenGaoFlow-edge Guided Video Completion2303Wednesday 26 August 202000:00:00Poster
1721AliHatamizadehEnd-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagery2304Tuesday 25 August 202014:00:00Poster
1721AliHatamizadehEnd-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagery2304Wednesday 26 August 202000:00:00Poster
1728SeonwookParkTowards End-to-end Video-based Eye-Tracking3054Wednesday 26 August 202000:00:00Poster
1728SeonwookParkTowards End-to-end Video-based Eye-Tracking3054Wednesday 26 August 202006:00:00Poster
1732JamesTompkinGenerating Handwriting via Decoupled Style Descriptors4052Thursday 27 August 202000:00:00Poster
1732JamesTompkinGenerating Handwriting via Decoupled Style Descriptors4052Thursday 27 August 202006:00:00Poster
1737BenjaminAttalMatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images1171Monday 24 August 202014:00:00Oral
1737BenjaminAttalMatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images1171Tuesday 25 August 202000:00:00Oral
1742RongliangWuLEED: Label-Free Expression Editing via Disentanglement4053Thursday 27 August 202000:00:00Poster
1742RongliangWuLEED: Label-Free Expression Editing via Disentanglement4053Thursday 27 August 202006:00:00Poster
1761YanchunXieFeature Representation Matters: End-to-End Learning for Reference-based Image Super-resolution3055Wednesday 26 August 202000:00:00Spotlight
1761YanchunXieFeature Representation Matters: End-to-End Learning for Reference-based Image Super-resolution3055Wednesday 26 August 202006:00:00Spotlight
1763XuewenYangFashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards3250Wednesday 26 August 202014:00:00Poster
1763XuewenYangFashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards3250Thursday 27 August 202000:00:00Poster
1765GouthamanKVReducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder1038Monday 24 August 202006:00:00Poster
1765GouthamanKVReducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder1038Monday 24 August 202014:00:00Poster
1766Venkatesh BabuRadhakrishnanUnsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation1039Monday 24 August 202006:00:00Poster
1766Venkatesh BabuRadhakrishnanUnsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation1039Monday 24 August 202014:00:00Poster
1769Rahul MysoreVenkateshClass-Incremental Domain Adaptation2253Tuesday 25 August 202006:00:00Poster
1769Rahul MysoreVenkateshClass-Incremental Domain Adaptation2253Tuesday 25 August 202014:00:00Poster
1789BaochangZhangAnti-Bandit Neural Architecture Search for Model Defense2060Tuesday 25 August 202000:00:00Poster
1789BaochangZhangAnti-Bandit Neural Architecture Search for Model Defense2060Tuesday 25 August 202006:00:00Poster
1792ShanxinYuanWavelet-Based Dual-Branch Network for Image Demoir\'{eing3251Wednesday 26 August 202014:00:00Poster
1792ShanxinYuanWavelet-Based Dual-Branch Network for Image Demoir\'{eing3251Thursday 27 August 202000:00:00Poster
1793GeorgiosToliasLearning and Aggregating Deep Local Descriptors for Instance-level Recognition3176Wednesday 26 August 202006:00:00Oral
1793GeorgiosToliasLearning and Aggregating Deep Local Descriptors for Instance-level Recognition3176Wednesday 26 August 202014:00:00Oral
1802ZhuoSuRobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera4054Thursday 27 August 202000:00:00Spotlight
1802ZhuoSuRobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera4054Thursday 27 August 202006:00:00Spotlight
1809DanaiTriantafyllidouLow Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping4285Thursday 27 August 202014:00:00Poster
1809DanaiTriantafyllidouLow Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mapping4285Friday 28 August 202000:00:00Poster
1810JinsunParkNon-Local Spatial Propagation Network for Depth Completion2061Tuesday 25 August 202000:00:00Poster
1810JinsunParkNon-Local Spatial Propagation Network for Depth Completion2061Tuesday 25 August 202006:00:00Poster
1816YiJiDanbooRegion: An Illustration Region Dataset3056Wednesday 26 August 202000:00:00Poster
1816YiJiDanbooRegion: An Illustration Region Dataset3056Wednesday 26 August 202006:00:00Poster
1819LeiYuEvent Enhanced High-Quality Image Recovery4055Thursday 27 August 202000:00:00Poster
1819LeiYuEvent Enhanced High-Quality Image Recovery4055Thursday 27 August 202006:00:00Poster
1821KunDingPackDet: Packed Long-Head Object Detector3057Wednesday 26 August 202000:00:00Poster
1821KunDingPackDet: Packed Long-Head Object Detector3057Wednesday 26 August 202006:00:00Poster
1825XuefeiNingA Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS2062Tuesday 25 August 202000:00:00Poster
1825XuefeiNingA Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS2062Tuesday 25 August 202006:00:00Poster
1829RuyiJiLearning Semantic Neural Tree for Human Parsing4056Thursday 27 August 202000:00:00Poster
1829RuyiJiLearning Semantic Neural Tree for Human Parsing4056Thursday 27 August 202006:00:00Poster
1834WenbinWangSketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation3058Wednesday 26 August 202000:00:00Poster
1834WenbinWangSketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation3058Wednesday 26 August 202006:00:00Poster
1848XuejianRongBurst Denoising via Temporally Shifted Wavelet Transforms2305Tuesday 25 August 202014:00:00Poster
1848XuejianRongBurst Denoising via Temporally Shifted Wavelet Transforms2305Wednesday 26 August 202000:00:00Poster
1849FengzeLiuJSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans3252Wednesday 26 August 202014:00:00Poster
1849FengzeLiuJSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans3252Thursday 27 August 202000:00:00Poster
1850LuJiangLearning Robust Representations from Simulation for Trajectory Prediction4286Thursday 27 August 202014:00:00Poster
1850LuJiangLearning Robust Representations from Simulation for Trajectory Prediction4286Friday 28 August 202000:00:00Poster
1851HuanLingScribbleBox: Interactive Annotation Framework for Video Object Segmentation4287Thursday 27 August 202014:00:00Poster
1851HuanLingScribbleBox: Interactive Annotation Framework for Video Object Segmentation4287Friday 28 August 202000:00:00Poster
1862XinzhuMaRethinking Pseudo-LiDAR Representation4057Thursday 27 August 202000:00:00Poster
1862XinzhuMaRethinking Pseudo-LiDAR Representation4057Thursday 27 August 202006:00:00Poster
1868Kai-enLinDeep Multi Depth Panoramas for View Synthesis3253Wednesday 26 August 202014:00:00Poster
1868Kai-enLinDeep Multi Depth Panoramas for View Synthesis3253Thursday 27 August 202000:00:00Poster
1880FatingHongMINI-Net: Multiple Instance Ranking Network for Video Highlight Detection2063Tuesday 25 August 202000:00:00Poster
1880FatingHongMINI-Net: Multiple Instance Ranking Network for Video Highlight Detection2063Tuesday 25 August 202006:00:00Poster
1886TienDoSurface Normal Estimation of Tilted Images via Spatial Rectifier4288Thursday 27 August 202014:00:00Spotlight
1886TienDoSurface Normal Estimation of Tilted Images via Spatial Rectifier4288Friday 28 August 202000:00:00Spotlight
1889SamarthBrahmbhattContactPose: A Dataset of Grasps with Object Contact and Hand Pose2306Tuesday 25 August 202014:00:00Poster
1889SamarthBrahmbhattContactPose: A Dataset of Grasps with Object Contact and Hand Pose2306Wednesday 26 August 202000:00:00Poster
1895XinshuaiDongAPI-Net: Robust Generative Classifier via a Single Discriminator2064Tuesday 25 August 202000:00:00Poster
1895XinshuaiDongAPI-Net: Robust Generative Classifier via a Single Discriminator2064Tuesday 25 August 202006:00:00Poster
1905JiakaiWangBias-based Universal Adversarial Patch Attack for Automatic Check-out3059Wednesday 26 August 202000:00:00Poster
1905JiakaiWangBias-based Universal Adversarial Patch Attack for Automatic Check-out3059Wednesday 26 August 202006:00:00Poster
1912Chris DongjooKimImbalanced Continual Learning with Partitioning Reservoir Sampling4058Thursday 27 August 202000:00:00Poster
1912Chris DongjooKimImbalanced Continual Learning with Partitioning Reservoir Sampling4058Thursday 27 August 202006:00:00Poster
1915RundiWuMultimodal Shape Completion via Conditional Generative Adversarial Networks3060Wednesday 26 August 202000:00:00Spotlight
1915RundiWuMultimodal Shape Completion via Conditional Generative Adversarial Networks3060Wednesday 26 August 202006:00:00Spotlight
1932ZhanghanKeGuided Collaborative Training for Pixel-wise Semi-Supervised Learning4059Thursday 27 August 202000:00:00Poster
1932ZhanghanKeGuided Collaborative Training for Pixel-wise Semi-Supervised Learning4059Thursday 27 August 202006:00:00Poster
1938HaixinWangStacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework2065Tuesday 25 August 202000:00:00Poster
1938HaixinWangStacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework2065Tuesday 25 August 202006:00:00Poster
1942MingSunEfficient Transfer Learning via Joint Adaptation of Network Architecture and Weight2066Tuesday 25 August 202000:00:00Poster
1942MingSunEfficient Transfer Learning via Joint Adaptation of Network Architecture and Weight2066Tuesday 25 August 202006:00:00Poster
1951libozhangSpatial Attention Pyramid Network for Unsupervised Domain Adaptation2067Tuesday 25 August 202000:00:00Poster
1951libozhangSpatial Attention Pyramid Network for Unsupervised Domain Adaptation2067Tuesday 25 August 202006:00:00Poster
1955JianrenWangGSIR: Generalizable 3D Shape Interpretation and Reconstruction4289Thursday 27 August 202014:00:00Poster
1955JianrenWangGSIR: Generalizable 3D Shape Interpretation and Reconstruction4289Friday 28 August 202000:00:00Poster
1956JianbingShenWeakly Supervised 3D Object Detection from Lidar Point Cloud4060Thursday 27 August 202000:00:00Poster
1956JianbingShenWeakly Supervised 3D Object Detection from Lidar Point Cloud4060Thursday 27 August 202006:00:00Poster
1960InkyuShinTwo-phase Pseudo Label Densification for Self-training based Domain Adaptation3061Wednesday 26 August 202000:00:00Poster
1960InkyuShinTwo-phase Pseudo Label Densification for Self-training based Domain Adaptation3061Wednesday 26 August 202006:00:00Poster
1969GeorgeTerzakisA Consistently Fast and Globally Optimal Solution to the Perspective-n-Point Problem2307Tuesday 25 August 202014:00:00Oral
1969GeorgeTerzakisA Consistently Fast and Globally Optimal Solution to the Perspective-n-Point Problem2307Wednesday 26 August 202000:00:00Oral
1972TianlangChenAdaptive Offline Quintuplet Loss for Image-Text Matching2308Tuesday 25 August 202014:00:00Poster
1972TianlangChenAdaptive Offline Quintuplet Loss for Image-Text Matching2308Wednesday 26 August 202000:00:00Poster
1973LingzhiZhangLearning Object Placement by Inpainting for Compositional Data Augmentation4290Thursday 27 August 202014:00:00Poster
1973LingzhiZhangLearning Object Placement by Inpainting for Compositional Data Augmentation4290Friday 28 August 202000:00:00Poster
1977JunyoungGwakGenerative Sparse Detection Networks for 3D Single-shot Object Detection3254Wednesday 26 August 202014:00:00Spotlight
1977JunyoungGwakGenerative Sparse Detection Networks for 3D Single-shot Object Detection3254Thursday 27 August 202000:00:00Spotlight
1978AlexeyArtemovDeep Vectorization of Technical Drawings1040Monday 24 August 202006:00:00Poster
1978AlexeyArtemovDeep Vectorization of Technical Drawings1040Monday 24 August 202014:00:00Poster
1979EvgenyBurnaevCAD-Deform: Deformable Fitting of CAD Models to 3D Scans3177Wednesday 26 August 202006:00:00Poster
1979EvgenyBurnaevCAD-Deform: Deformable Fitting of CAD Models to 3D Scans3177Wednesday 26 August 202014:00:00Poster
1987SarahPrattGrounded Situation Recognition2309Tuesday 25 August 202014:00:00Spotlight
1987SarahPrattGrounded Situation Recognition2309Wednesday 26 August 202000:00:00Spotlight
1991XiaolongMaAn Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices4291Thursday 27 August 202014:00:00Poster
1991XiaolongMaAn Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices4291Friday 28 August 202000:00:00Poster
2006YuexinMaAutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points4061Thursday 27 August 202000:00:00Poster
2006YuexinMaAutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points4061Thursday 27 August 202006:00:00Poster
2013SinanTanMulti-Agent Embodied Question Answering in Interactive Environments3062Wednesday 26 August 202000:00:00Poster
2013SinanTanMulti-Agent Embodied Question Answering in Interactive Environments3062Wednesday 26 August 202006:00:00Poster
2014YihaoLiuConditional Sequential Modulation for Efficient Global Image Retouching4062Thursday 27 August 202000:00:00Poster
2014YihaoLiuConditional Sequential Modulation for Efficient Global Image Retouching4062Thursday 27 August 202006:00:00Poster
2016EnzeXieSegmenting Transparent Objects in the Wild4063Thursday 27 August 202000:00:00Poster
2016EnzeXieSegmenting Transparent Objects in the Wild4063Thursday 27 August 202006:00:00Poster
2019ShaoxiangChenLearning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos3063Wednesday 26 August 202000:00:00Spotlight
2019ShaoxiangChenLearning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos3063Wednesday 26 August 202006:00:00Spotlight
2035NingDingLength-Controllable Image Captioning4064Thursday 27 August 202000:00:00Poster
2035NingDingLength-Controllable Image Captioning4064Thursday 27 August 202006:00:00Poster
2042haochenwangFew-Shot Semantic Segmentation with Democratic Attention Networks2068Tuesday 25 August 202000:00:00Poster
2042haochenwangFew-Shot Semantic Segmentation with Democratic Attention Networks2068Tuesday 25 August 202006:00:00Poster
2044Chi-manPunDefocus Blur Detection via Depth Distillation4065Thursday 27 August 202000:00:00Poster
2044Chi-manPunDefocus Blur Detection via Depth Distillation4065Thursday 27 August 202006:00:00Poster
2054JingboWangMotion Guided 3D Pose Estimation from Videos2069Tuesday 25 August 202000:00:00Poster
2054JingboWangMotion Guided 3D Pose Estimation from Videos2069Tuesday 25 August 202006:00:00Poster
2055RuiLiReflection Separation via Multi-bounce Polarization State Tracing3178Wednesday 26 August 202006:00:00Poster
2055RuiLiReflection Separation via Multi-bounce Polarization State Tracing3178Wednesday 26 August 202014:00:00Poster
2057JialeCaoSipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation4292Thursday 27 August 202014:00:00Poster
2057JialeCaoSipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation4292Friday 28 August 202000:00:00Poster
2059BoLiSemanticAdv: Generating Adversarial Examples \\via Attribute-conditioned Image Editing4293Thursday 27 August 202014:00:00Poster
2059BoLiSemanticAdv: Generating Adversarial Examples \\via Attribute-conditioned Image Editing4293Friday 28 August 202000:00:00Poster
2062LongRongYangLearning with Noisy Class Labels for Instance Segmentation4066Thursday 27 August 202000:00:00Poster
2062LongRongYangLearning with Noisy Class Labels for Instance Segmentation4066Thursday 27 August 202006:00:00Poster
2085JunjieZhaoDeep Image Clustering with Category-Style Representation2070Tuesday 25 August 202000:00:00Poster
2085JunjieZhaoDeep Image Clustering with Category-Style Representation2070Tuesday 25 August 202006:00:00Poster
2090YuanTianSelf-supervised Motion Representation via Scattering Local Motion Cues4067Thursday 27 August 202000:00:00Poster
2090YuanTianSelf-supervised Motion Representation via Scattering Local Motion Cues4067Thursday 27 August 202006:00:00Poster
2094TianChenImproving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets2071Tuesday 25 August 202000:00:00Poster
2094TianChenImproving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets2071Tuesday 25 August 202006:00:00Poster
2095JunheumParkBMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation3064Wednesday 26 August 202000:00:00Poster
2095JunheumParkBMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation3064Wednesday 26 August 202006:00:00Poster
2096Guangming WuWuLearn to Recover Visible Color for Video Surveillance in a Day4068Thursday 27 August 202000:00:00Oral
2096Guangming WuWuLearn to Recover Visible Color for Video Surveillance in a Day4068Thursday 27 August 202006:00:00Oral
2100HongXuanHard negative examples are hard, but useful2310Tuesday 25 August 202014:00:00Poster
2100HongXuanHard negative examples are hard, but useful2310Wednesday 26 August 202000:00:00Poster
2106ZhiqiangShenReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions4294Thursday 27 August 202014:00:00Poster
2106ZhiqiangShenReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions4294Friday 28 August 202000:00:00Poster
2107Chun-hanYaoVideo Object Detection via Object-level Temporal Aggregation4295Thursday 27 August 202014:00:00Poster
2107Chun-hanYaoVideo Object Detection via Object-level Temporal Aggregation4295Friday 28 August 202000:00:00Poster
2113XiangyunZhaoObject Detection with a Unified Label Space from Multiple Datasets4296Thursday 27 August 202014:00:00Poster
2113XiangyunZhaoObject Detection with a Unified Label Space from Multiple Datasets4296Friday 28 August 202000:00:00Poster
2114JonahPhilionLift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D4297Thursday 27 August 202014:00:00Poster
2114JonahPhilionLift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D4297Friday 28 August 202000:00:00Poster
2115YiwuZhongComprehensive Image Captioning via Scene Graph Decomposition3255Wednesday 26 August 202014:00:00Poster
2115YiwuZhongComprehensive Image Captioning via Scene Graph Decomposition3255Thursday 27 August 202000:00:00Poster
2116YutongCaoSymbiotic Adversarial Learning for Attribute-based Person Search2072Tuesday 25 August 202000:00:00Poster
2116YutongCaoSymbiotic Adversarial Learning for Attribute-based Person Search2072Tuesday 25 August 202006:00:00Poster
2117YangLiuAmplifying Key Cues for Human-Object-Interaction Detection2073Tuesday 25 August 202000:00:00Poster
2117YangLiuAmplifying Key Cues for Human-Object-Interaction Detection2073Tuesday 25 August 202006:00:00Poster
2118YueWangRethinking Few-shot Image Classification: A Good Embedding is All You Need?2311Tuesday 25 August 202014:00:00Poster
2118YueWangRethinking Few-shot Image Classification: A Good Embedding is All You Need?2311Wednesday 26 August 202000:00:00Poster
2121JasonCorsoAdversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization4298Thursday 27 August 202014:00:00Poster
2121JasonCorsoAdversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization4298Friday 28 August 202000:00:00Poster
2129SathyanarayananAakurAction Localization through Continual Predictive Learning4299Thursday 27 August 202014:00:00Poster
2129SathyanarayananAakurAction Localization through Continual Predictive Learning4299Friday 28 August 202000:00:00Poster
2130YunyuLiuGenerative View-Correlation Adaptation for Semi-Supervised Multi-View Learning4300Thursday 27 August 202014:00:00Poster
2130YunyuLiuGenerative View-Correlation Adaptation for Semi-Supervised Multi-View Learning4300Friday 28 August 202000:00:00Poster
2135MinhoShimREAD: Reciprocal Attention Discriminator for Image-to-Video Re-Identification2074Tuesday 25 August 202000:00:00Poster
2135MinhoShimREAD: Reciprocal Attention Discriminator for Image-to-Video Re-Identification2074Tuesday 25 August 202006:00:00Poster
2136LiCheng3D Human Shape Reconstruction from a Polarization Image4301Thursday 27 August 202014:00:00Poster
2136LiCheng3D Human Shape Reconstruction from a Polarization Image4301Friday 28 August 202000:00:00Poster
2142PirazhKhorramshahiThe Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification2312Tuesday 25 August 202014:00:00Poster
2142PirazhKhorramshahiThe Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification2312Wednesday 26 August 202000:00:00Poster
2149HemingZhuDeep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images3065Wednesday 26 August 202000:00:00Oral
2149HemingZhuDeep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images3065Wednesday 26 August 202006:00:00Oral
2152ZhengyuanYangImproving One-stage Visual Grounding by Recursive Sub-query Construction2313Tuesday 25 August 202014:00:00Poster
2152ZhengyuanYangImproving One-stage Visual Grounding by Recursive Sub-query Construction2313Wednesday 26 August 202000:00:00Poster
2157XiaoheWuUnpaired Learning of Deep Image Denoising3066Wednesday 26 August 202000:00:00Spotlight
2157XiaoheWuUnpaired Learning of Deep Image Denoising3066Wednesday 26 August 202006:00:00Spotlight
2160JianyiWangMulti-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video2075Tuesday 25 August 202000:00:00Poster
2160JianyiWangMulti-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video2075Tuesday 25 August 202006:00:00Poster
2168JieboLuoExample-Guided Image Synthesis using Masked Spatial-Channel Attention and Self-Supervision4302Thursday 27 August 202014:00:00Poster
2168JieboLuoExample-Guided Image Synthesis using Masked Spatial-Channel Attention and Self-Supervision4302Friday 28 August 202000:00:00Poster
2178GuangruiLiContent-Consistent Matching for Domain Adaptive Semantic Segmentation2076Tuesday 25 August 202000:00:00Poster
2178GuangruiLiContent-Consistent Matching for Domain Adaptive Semantic Segmentation2076Tuesday 25 August 202006:00:00Poster
2183WenhaiWangAE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting3067Wednesday 26 August 202000:00:00Poster
2183WenhaiWangAE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting3067Wednesday 26 August 202006:00:00Poster
2186WeiMaoHistory Repeats Itself: Human Motion Prediction via Motion Attention2077Tuesday 25 August 202000:00:00Poster
2186WeiMaoHistory Repeats Itself: Human Motion Prediction via Motion Attention2077Tuesday 25 August 202006:00:00Poster
2189JianmingZhangUnsupervised Video Object Segmentation with Joint Hotspot Tracking4303Thursday 27 August 202014:00:00Poster
2189JianmingZhangUnsupervised Video Object Segmentation with Joint Hotspot Tracking4303Friday 28 August 202000:00:00Poster
2191YixiaoGeSelf-supervising Fine-grained Region Similarities for Large-scale Image Localization2078Tuesday 25 August 202000:00:00Spotlight
2191YixiaoGeSelf-supervising Fine-grained Region Similarities for Large-scale Image Localization2078Tuesday 25 August 202006:00:00Spotlight
2193ZhendaXieSpatially Adaptive Inference with Stochastic Feature Sampling and Interpolation3068Wednesday 26 August 202000:00:00Oral
2193ZhendaXieSpatially Adaptive Inference with Stochastic Feature Sampling and Interpolation3068Wednesday 26 August 202006:00:00Oral
2201XiaoSunSRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach2079Tuesday 25 August 202000:00:00Poster
2201XiaoSunSRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach2079Tuesday 25 August 202006:00:00Poster
2202Jeong giKwakCAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature2080Tuesday 25 August 202000:00:00Poster
2202Jeong giKwakCAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature2080Tuesday 25 August 202006:00:00Poster
2209XinLuMimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection3069Wednesday 26 August 202000:00:00Poster
2209XinLuMimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection3069Wednesday 26 August 202006:00:00Poster
2211HanQiuBorderDet: Border Feature for Dense Object Detection4069Thursday 27 August 202000:00:00Oral
2211HanQiuBorderDet: Border Feature for Dense Object Detection4069Thursday 27 August 202006:00:00Oral
2212JianghongMaLatent Topic-aware Multi-Label Classification4070Thursday 27 August 202000:00:00Poster
2212JianghongMaLatent Topic-aware Multi-Label Classification4070Thursday 27 August 202006:00:00Poster
2215YoungjoongKwonRotationally-Temporally Consistent Novel View Synthesis of Human Performance Video3256Wednesday 26 August 202014:00:00Spotlight
2215YoungjoongKwonRotationally-Temporally Consistent Novel View Synthesis of Human Performance Video3256Thursday 27 August 202000:00:00Spotlight
2216JiuxiangGuFinding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning4071Thursday 27 August 202000:00:00Poster
2216JiuxiangGuFinding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning4071Thursday 27 August 202006:00:00Poster
2235TaekyungKimAttract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation4072Thursday 27 August 202000:00:00Poster
2235TaekyungKimAttract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation4072Thursday 27 August 202006:00:00Poster
2238LuyuYangCurriculum Manager for Source Selection\\ in Multi-Source Domain Adaptation\\2314Tuesday 25 August 202014:00:00Poster
2238LuyuYangCurriculum Manager for Source Selection\\ in Multi-Source Domain Adaptation\\2314Wednesday 26 August 202000:00:00Poster
2244RonghaoGuoPowering One-shot Topological NAS with Stabilized Share-parameter Proxy2081Tuesday 25 August 202000:00:00Poster
2244RonghaoGuoPowering One-shot Topological NAS with Stabilized Share-parameter Proxy2081Tuesday 25 August 202006:00:00Poster
2246TongShenClasses Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation1041Monday 24 August 202006:00:00Poster
2246TongShenClasses Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation1041Monday 24 August 202014:00:00Poster
2252TianhengChengBoundary-preserving Mask R-CNN4073Thursday 27 August 202000:00:00Poster
2252TianhengChengBoundary-preserving Mask R-CNN4073Thursday 27 August 202006:00:00Poster
2253SifeiLiuSelf-supervised Single-view 3D Reconstruction via Semantic Consistency4304Thursday 27 August 202014:00:00Poster
2253SifeiLiuSelf-supervised Single-view 3D Reconstruction via Semantic Consistency4304Friday 28 August 202000:00:00Poster
2255BenlinLiuMetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation4305Thursday 27 August 202014:00:00Poster
2255BenlinLiuMetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation4305Friday 28 August 202000:00:00Poster
2256YuliangZouLearning Monocular Visual Odometry via Self-Supervised Long-Term Modeling4306Thursday 27 August 202014:00:00Poster
2256YuliangZouLearning Monocular Visual Odometry via Self-Supervised Long-Term Modeling4306Friday 28 August 202000:00:00Poster
2257TaoWangThe Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation2082Tuesday 25 August 202000:00:00Poster
2257TaoWangThe Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation2082Tuesday 25 August 202006:00:00Poster
2258GenkiOsadaRegularization with Latent Space Virtual Adversarial Training2083Tuesday 25 August 202000:00:00Oral
2258GenkiOsadaRegularization with Latent Space Virtual Adversarial Training2083Tuesday 25 August 202006:00:00Oral
2263YindaZhangDu$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels2084Tuesday 25 August 202000:00:00Oral
2263YindaZhangDu$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels2084Tuesday 25 August 202006:00:00Oral
2266GuanyingChenWhat is Learned in Deep Uncalibrated Photometric Stereo?3070Wednesday 26 August 202000:00:00Poster
2266GuanyingChenWhat is Learned in Deep Uncalibrated Photometric Stereo?3070Wednesday 26 August 202006:00:00Poster
2270VishwanathSindagiPrior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions2315Tuesday 25 August 202014:00:00Poster
2270VishwanathSindagiPrior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions2315Wednesday 26 August 202000:00:00Poster
2272JiaqiWangSide-Aware Boundary Localization for More Precise Object Detection4074Thursday 27 August 202000:00:00Spotlight
2272JiaqiWangSide-Aware Boundary Localization for More Precise Object Detection4074Thursday 27 August 202006:00:00Spotlight
2274MoZhouAdversarial Ranking Attack and Defense4075Thursday 27 August 202000:00:00Poster
2274MoZhouAdversarial Ranking Attack and Defense4075Thursday 27 August 202006:00:00Poster
2279SaimunurRahmanReDro: Efficiently Learning Large-sized SPD Visual Representation3257Wednesday 26 August 202014:00:00Poster
2279SaimunurRahmanReDro: Efficiently Learning Large-sized SPD Visual Representation3257Thursday 27 August 202000:00:00Poster
2287WanhuaLiGraph-Based Social Relation Reasoning2085Tuesday 25 August 202000:00:00Poster
2287WanhuaLiGraph-Based Social Relation Reasoning2085Tuesday 25 August 202006:00:00Poster
2290XiangBaiEPNet: Enhancing Point Features with Image Semantics for 3D Object Detection3071Wednesday 26 August 202000:00:00Poster
2290XiangBaiEPNet: Enhancing Point Features with Image Semantics for 3D Object Detection3071Wednesday 26 August 202006:00:00Poster
2293ShangJiaxiangSelf-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware \\ Multi-view Geometry Consistency3072Wednesday 26 August 202000:00:00Poster
2293ShangJiaxiangSelf-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware \\ Multi-view Geometry Consistency3072Wednesday 26 August 202006:00:00Poster
2295JiajunTangAsynchronous Interaction Aggregation for Action Detection4076Thursday 27 August 202000:00:00Poster
2295JiajunTangAsynchronous Interaction Aggregation for Action Detection4076Thursday 27 August 202006:00:00Poster
2305ShubhamGoelShape and Viewpoint without Keypoints4307Thursday 27 August 202014:00:00Poster
2305ShubhamGoelShape and Viewpoint without Keypoints4307Friday 28 August 202000:00:00Poster
2306JiaxinChenLearning Attentive and Hierarchical Representations for 3D Shape Recognition4308Thursday 27 August 202014:00:00Poster
2306JiaxinChenLearning Attentive and Hierarchical Representations for 3D Shape Recognition4308Friday 28 August 202000:00:00Poster
2307JaekyeomKimModel-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning3073Wednesday 26 August 202000:00:00Oral
2307JaekyeomKimModel-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning3073Wednesday 26 August 202006:00:00Oral
2308RanHeTF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search2086Tuesday 25 August 202000:00:00Poster
2308RanHeTF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search2086Tuesday 25 August 202006:00:00Poster
2313ShengyiQianAssociative3D: Volumetric Reconstruction from Sparse Views3258Wednesday 26 August 202014:00:00Poster
2313ShengyiQianAssociative3D: Volumetric Reconstruction from Sparse Views3258Thursday 27 August 202000:00:00Poster
2314FanMaSF-Net: Single-Frame Supervision for Temporal Action Localization4077Thursday 27 August 202000:00:00Spotlight
2314FanMaSF-Net: Single-Frame Supervision for Temporal Action Localization4077Thursday 27 August 202006:00:00Spotlight
2317BinLiuNegative Margin Matters: Understanding Margin in Few-shot Classification4078Thursday 27 August 202000:00:00Spotlight
2317BinLiuNegative Margin Matters: Understanding Margin in Few-shot Classification4078Thursday 27 August 202006:00:00Spotlight
2318YongqiangMouPlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit2087Tuesday 25 August 202000:00:00Poster
2318YongqiangMouPlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit2087Tuesday 25 August 202006:00:00Poster
2319RuizhengWuMemory Selection Network for Video Propagation3074Wednesday 26 August 202000:00:00Poster
2319RuizhengWuMemory Selection Network for Video Propagation3074Wednesday 26 August 202006:00:00Poster
2323RuizhengWuParticularity beyond Commonality: Unpaired Identity Transfer with Multiple References4079Thursday 27 August 202000:00:00Spotlight
2323RuizhengWuParticularity beyond Commonality: Unpaired Identity Transfer with Multiple References4079Thursday 27 August 202006:00:00Spotlight
2325MinghaoYinDisentangled Non-local Neural Networks2088Tuesday 25 August 202000:00:00Poster
2325MinghaoYinDisentangled Non-local Neural Networks2088Tuesday 25 August 202006:00:00Poster
2327SeongukSeoURVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark4080Thursday 27 August 202000:00:00Poster
2327SeongukSeoURVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark4080Thursday 27 August 202006:00:00Poster
2329ChuanchenLuoGeneralizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain Mixup2089Tuesday 25 August 202000:00:00Poster
2329ChuanchenLuoGeneralizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain Mixup2089Tuesday 25 August 202006:00:00Poster
2330YinjieLeiSemi-Supervised Crowd Counting via Self-Training on Surrogate Tasks3259Wednesday 26 August 202014:00:00Poster
2330YinjieLeiSemi-Supervised Crowd Counting via Self-Training on Surrogate Tasks3259Thursday 27 August 202000:00:00Poster
2335HongChangDynamic R-CNN: Towards High Quality Object Detection via Dynamic Training2090Tuesday 25 August 202000:00:00Poster
2335HongChangDynamic R-CNN: Towards High Quality Object Detection via Dynamic Training2090Tuesday 25 August 202006:00:00Poster
2336WeilunChenBoosting Decision-based Black-box Adversarial Attacks with Random Sign Flip4081Thursday 27 August 202000:00:00Poster
2336WeilunChenBoosting Decision-based Black-box Adversarial Attacks with Random Sign Flip4081Thursday 27 August 202006:00:00Poster
2338AnbangYaoKnowledge Transfer via Dense Cross-Layer Mutual-Distillation3075Wednesday 26 August 202000:00:00Poster
2338AnbangYaoKnowledge Transfer via Dense Cross-Layer Mutual-Distillation3075Wednesday 26 August 202006:00:00Poster
2339KaiyuYueMatching Guided Distillation4082Thursday 27 August 202000:00:00Poster
2339KaiyuYueMatching Guided Distillation4082Thursday 27 August 202006:00:00Poster
2341ZhigangTuClustering Driven Deep Autoencoder for Video Anomaly Detection4083Thursday 27 August 202000:00:00Poster
2341ZhigangTuClustering Driven Deep Autoencoder for Video Anomaly Detection4083Thursday 27 August 202006:00:00Poster
2342XingyiZhouTracking Objects as Points3260Wednesday 26 August 202014:00:00Spotlight
2342XingyiZhouTracking Objects as Points3260Thursday 27 August 202000:00:00Spotlight
2343JuhongMinLearning to Compose Hypercolumns for Visual Correspondence2091Tuesday 25 August 202000:00:00Poster
2343JuhongMinLearning to Compose Hypercolumns for Visual Correspondence2091Tuesday 25 August 202006:00:00Poster
2348LeiZhouStochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction4084Thursday 27 August 202000:00:00Poster
2348LeiZhouStochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction4084Thursday 27 August 202006:00:00Poster
2353GuojunChenObject-based Illumination Estimation with Rendering-aware Neural Networks2092Tuesday 25 August 202000:00:00Poster
2353GuojunChenObject-based Illumination Estimation with Rendering-aware Neural Networks2092Tuesday 25 August 202006:00:00Poster
2354LeHuiProgressive Point Cloud Deconvolution Generation Network2093Tuesday 25 August 202000:00:00Poster
2354LeHuiProgressive Point Cloud Deconvolution Generation Network2093Tuesday 25 August 202006:00:00Poster
2356WenqingChuSSCGAN: Facial Attribute Editing via Style Skip Connections2094Tuesday 25 August 202000:00:00Poster
2356WenqingChuSSCGAN: Facial Attribute Editing via Style Skip Connections2094Tuesday 25 August 202006:00:00Poster
2374RyomaBiseNegative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathology2095Tuesday 25 August 202000:00:00Poster
2374RyomaBiseNegative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathology2095Tuesday 25 August 202006:00:00Poster
2376LeiYangLearn to Propagate Reliably on Noisy Affinity Graphs2096Tuesday 25 August 202000:00:00Poster
2376LeiYangLearn to Propagate Reliably on Noisy Affinity Graphs2096Tuesday 25 August 202006:00:00Poster
2382BoZhangFair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search2097Tuesday 25 August 202000:00:00Poster
2382BoZhangFair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search2097Tuesday 25 August 202006:00:00Poster
2383GuodongWeiTANet: Towards Fully Automatic Tooth Arrangement4085Thursday 27 August 202000:00:00Poster
2383GuodongWeiTANet: Towards Fully Automatic Tooth Arrangement4085Thursday 27 August 202006:00:00Poster
2390JiadongLiangCPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis4086Thursday 27 August 202000:00:00Spotlight
2390JiadongLiangCPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis4086Thursday 27 August 202006:00:00Spotlight
2391BumsooKimUnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection4087Thursday 27 August 202000:00:00Poster
2391BumsooKimUnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection4087Thursday 27 August 202006:00:00Poster
2393LeiKeGSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision4088Thursday 27 August 202000:00:00Poster
2393LeiKeGSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision4088Thursday 27 August 202006:00:00Poster
2394YikaiWangResolution Switchable Networks for Runtime Efficient Image Recognition4089Thursday 27 August 202000:00:00Poster
2394YikaiWangResolution Switchable Networks for Runtime Efficient Image Recognition4089Thursday 27 August 202006:00:00Poster
2395QiFangSMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation4090Thursday 27 August 202000:00:00Poster
2395QiFangSMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation4090Thursday 27 August 202006:00:00Poster
2396BoFuLearning to Detect Open Classes for Universal Domain Adaptation2098Tuesday 25 August 202000:00:00Poster
2396BoFuLearning to Detect Open Classes for Universal Domain Adaptation2098Tuesday 25 August 202006:00:00Poster
2400ZhiHouVisual Compositional Learning for Human-Object Interaction Detection3076Wednesday 26 August 202000:00:00Poster
2400ZhiHouVisual Compositional Learning for Human-Object Interaction Detection3076Wednesday 26 August 202006:00:00Poster
2402FariborzTaherkhaniTransporting Labels via Hierarchical Optimal Transport for Semi-Supervised Learning4309Thursday 27 August 202014:00:00Spotlight
2402FariborzTaherkhaniTransporting Labels via Hierarchical Optimal Transport for Semi-Supervised Learning4309Friday 28 August 202000:00:00Spotlight
2422ShuaiYangDeep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches3261Wednesday 26 August 202014:00:00Poster
2422ShuaiYangDeep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches3261Thursday 27 August 202000:00:00Poster
2423JunhyugNohRethinking Class Activation Mapping for Weakly Supervised Object Localization2099Tuesday 25 August 202000:00:00Poster
2423JunhyugNohRethinking Class Activation Mapping for Weakly Supervised Object Localization2099Tuesday 25 August 202006:00:00Poster
2424AntonOsokinOS2D: One-Stage One-Shot Object Detection by Matching Anchor Features4219Thursday 27 August 202006:00:00Poster
2424AntonOsokinOS2D: One-Stage One-Shot Object Detection by Matching Anchor Features4219Thursday 27 August 202014:00:00Poster
2426YuchaoLiInterpretable Neural Network Decoupling2100Tuesday 25 August 202000:00:00Poster
2426YuchaoLiInterpretable Neural Network Decoupling2100Tuesday 25 August 202006:00:00Poster
2433HaodongDuanOmni-sourced Webly-supervised Learning for Video Recognition4310Thursday 27 August 202014:00:00Poster
2433HaodongDuanOmni-sourced Webly-supervised Learning for Video Recognition4310Friday 28 August 202000:00:00Poster
2437HangXuCurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending4091Thursday 27 August 202000:00:00Poster
2437HangXuCurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending4091Thursday 27 August 202006:00:00Poster
2442JiaxingHuangContextual-Relation Consistent Domain Adaptation for Semantic Segmentation2101Tuesday 25 August 202000:00:00Poster
2442JiaxingHuangContextual-Relation Consistent Domain Adaptation for Semantic Segmentation2101Tuesday 25 August 202006:00:00Poster
2449SimonVandenhendeMTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning1042Monday 24 August 202006:00:00Spotlight
2449SimonVandenhendeMTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning1042Monday 24 August 202014:00:00Spotlight
2455WeizheLiuEstimating People Flows to Better Count Them in Crowded Scenes1043Monday 24 August 202006:00:00Poster
2455WeizheLiuEstimating People Flows to Better Count Them in Crowded Scenes1043Monday 24 August 202014:00:00Poster
2456HanFangGenerate to Adapt: Resolution Adaption Network for Surveillance Face Recognition3077Wednesday 26 August 202000:00:00Poster
2456HanFangGenerate to Adapt: Resolution Adaption Network for Surveillance Face Recognition3077Wednesday 26 August 202006:00:00Poster
2460LinyuZhengLearning Feature Embeddings for Discriminant Model based Tracking2102Tuesday 25 August 202000:00:00Poster
2460LinyuZhengLearning Feature Embeddings for Discriminant Model based Tracking2102Tuesday 25 August 202006:00:00Poster
2461NingningMaWeightNet: Revisiting the Design Space of Weight Networks2103Tuesday 25 August 202000:00:00Poster
2461NingningMaWeightNet: Revisiting the Design Space of Weight Networks2103Tuesday 25 August 202006:00:00Poster
2463JiawangBaiTargeted Attack for Deep Hashing based Retrieval2104Tuesday 25 August 202000:00:00Oral
2463JiawangBaiTargeted Attack for Deep Hashing based Retrieval2104Tuesday 25 August 202006:00:00Oral
2471HongweiYongGradient Centralization: A New Optimization Technique for Deep Neural Networks4092Thursday 27 August 202000:00:00Oral
2471HongweiYongGradient Centralization: A New Optimization Technique for Deep Neural Networks4092Thursday 27 August 202006:00:00Oral
2472MasaakiIiyamaPartially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift2105Tuesday 25 August 202000:00:00Poster
2472MasaakiIiyamaPartially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift2105Tuesday 25 August 202006:00:00Poster
2473AndrewLiuLearning to Factorize and Relight a City3262Wednesday 26 August 202014:00:00Spotlight
2473AndrewLiuLearning to Factorize and Relight a City3262Thursday 27 August 202000:00:00Spotlight
2475ZhengkaiJiangLearning Where to Focus for Efficient Video Object Detection4093Thursday 27 August 202000:00:00Poster
2475ZhengkaiJiangLearning Where to Focus for Efficient Video Object Detection4093Thursday 27 August 202006:00:00Poster
2481OfriKleinfeldLearning Object Permanence from Video2254Tuesday 25 August 202006:00:00Poster
2481OfriKleinfeldLearning Object Permanence from Video2254Tuesday 25 August 202014:00:00Poster
2492AndrewZissermanAdaptive Text Recognition through Visual Matching2316Tuesday 25 August 202014:00:00Poster
2492AndrewZissermanAdaptive Text Recognition through Visual Matching2316Wednesday 26 August 202000:00:00Poster
2495GuosenXieRegion Graph Embedding Network for Zero-Shot Learning4311Thursday 27 August 202014:00:00Spotlight
2495GuosenXieRegion Graph Embedding Network for Zero-Shot Learning4311Friday 28 August 202000:00:00Spotlight
2497YixuanLiActions as Moving Points2106Tuesday 25 August 202000:00:00Poster
2497YixuanLiActions as Moving Points2106Tuesday 25 August 202006:00:00Poster
2499YuhuangHuLearning to Exploit Multiple Vision Modalities by Using Grafted Networks1044Monday 24 August 202006:00:00Poster
2499YuhuangHuLearning to Exploit Multiple Vision Modalities by Using Grafted Networks1044Monday 24 August 202014:00:00Poster
2501AlexanderGrabnerGeometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild1045Monday 24 August 202006:00:00Poster
2501AlexanderGrabnerGeometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild1045Monday 24 August 202014:00:00Poster
2503JirongZhangContent-Aware Unsupervised Deep Homography Estimation4094Thursday 27 August 202000:00:00Oral
2503JirongZhangContent-Aware Unsupervised Deep Homography Estimation4094Thursday 27 August 202006:00:00Oral
2505JinweiYe3D Fluid Flow Reconstruction Using Compact Light Field PIV4312Thursday 27 August 202014:00:00Poster
2505JinweiYe3D Fluid Flow Reconstruction Using Compact Light Field PIV4312Friday 28 August 202000:00:00Poster
2510SaketAnandContextual Diversity for Active Learning1046Monday 24 August 202006:00:00Poster
2510SaketAnandContextual Diversity for Active Learning1046Monday 24 August 202014:00:00Poster
2515FadimeSenerTemporal Aggregate Representations for Long-Range Video Understanding1047Monday 24 August 202006:00:00Poster
2515FadimeSenerTemporal Aggregate Representations for Long-Range Video Understanding1047Monday 24 August 202014:00:00Poster
2527ZheNiuStochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition2107Tuesday 25 August 202000:00:00Poster
2527ZheNiuStochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition2107Tuesday 25 August 202006:00:00Poster
2530SinisaStekovicGeneral 3D Room Layout from a Single View by Render-and-Compare1048Monday 24 August 202006:00:00Poster
2530SinisaStekovicGeneral 3D Room Layout from a Single View by Render-and-Compare1048Monday 24 August 202014:00:00Poster
2532VladislavGolyanikNeural Dense Non-Rigid Structure from Motion with Latent Space Constraints3179Wednesday 26 August 202006:00:00Poster
2532VladislavGolyanikNeural Dense Non-Rigid Structure from Motion with Latent Space Constraints3179Wednesday 26 August 202014:00:00Poster
2534OmidTaheriGRAB: A Dataset of Whole-Body Human Grasping of Objects3180Wednesday 26 August 202006:00:00Spotlight
2534OmidTaheriGRAB: A Dataset of Whole-Body Human Grasping of Objects3180Wednesday 26 August 202014:00:00Spotlight
2535AneliseNewmanMultimodal Memorability: Modeling Effects of Semantics and Decay on Video Memorability2317Tuesday 25 August 202014:00:00Poster
2535AneliseNewmanMultimodal Memorability: Modeling Effects of Semantics and Decay on Video Memorability2317Wednesday 26 August 202000:00:00Poster
2538QizhangLiYet Another Intermediate-Level Attack4095Thursday 27 August 202000:00:00Poster
2538QizhangLiYet Another Intermediate-Level Attack4095Thursday 27 August 202006:00:00Poster
2540ChaoLiTopology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction1172Monday 24 August 202014:00:00Poster
2540ChaoLiTopology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction1172Tuesday 25 August 202000:00:00Poster
2544QunliangXingEarly Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images4096Thursday 27 August 202000:00:00Poster
2544QunliangXingEarly Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images4096Thursday 27 August 202006:00:00Poster
2547EdgarTretschkPatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations1049Monday 24 August 202006:00:00Poster
2547EdgarTretschkPatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations1049Monday 24 August 202014:00:00Poster
2548YipengQinHow does Lipschitz Regularization Influence GAN Training?3263Wednesday 26 August 202014:00:00Poster
2548YipengQinHow does Lipschitz Regularization Influence GAN Training?3263Thursday 27 August 202000:00:00Poster
2550YukaiLinInfrastructure-based Multi-Camera Calibration using Radial Projections2108Tuesday 25 August 202000:00:00Poster
2550YukaiLinInfrastructure-based Multi-Camera Calibration using Radial Projections2108Tuesday 25 August 202006:00:00Poster
2553HeeseungKwonMotionSqueeze: Neural Motion Feature Learning for Video Understanding4097Thursday 27 August 202000:00:00Poster
2553HeeseungKwonMotionSqueeze: Neural Motion Feature Learning for Video Understanding4097Thursday 27 August 202006:00:00Poster
2556MihaiDusmanuMulti-View Optimization of Local Feature Geometry1050Monday 24 August 202006:00:00Oral
2556MihaiDusmanuMulti-View Optimization of Local Feature Geometry1050Monday 24 August 202014:00:00Oral
2559MasadaTzabariPolarized Optical-Flow Gyroscope4313Thursday 27 August 202014:00:00Poster
2559MasadaTzabariPolarized Optical-Flow Gyroscope4313Friday 28 August 202000:00:00Poster
2561DaLiOnline Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation4314Thursday 27 August 202014:00:00Poster
2561DaLiOnline Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation4314Friday 28 August 202000:00:00Poster
2562YaoyaoLiuAn Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning1051Monday 24 August 202006:00:00Poster
2562YaoyaoLiuAn Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning1051Monday 24 August 202014:00:00Poster
2568SilviaBucciOn the Effectiveness of Image Rotation for Open Set Domain Adaptation1052Monday 24 August 202006:00:00Poster
2568SilviaBucciOn the Effectiveness of Image Rotation for Open Set Domain Adaptation1052Monday 24 August 202014:00:00Poster
2569Kwang InKimCombining Task Predictors via Enhancing Joint Predictability3078Wednesday 26 August 202000:00:00Poster
2569Kwang InKimCombining Task Predictors via Enhancing Joint Predictability3078Wednesday 26 August 202006:00:00Poster
2581DiHuangMulti-Scale Positive Sample Refinement for Few-Shot Object Detection4098Thursday 27 August 202000:00:00Poster
2581DiHuangMulti-Scale Positive Sample Refinement for Few-Shot Object Detection4098Thursday 27 August 202006:00:00Poster
2583DaniyarTurmukhambetovSingle-Image Depth Prediction Makes Feature Matching Easier1053Monday 24 August 202006:00:00Poster
2583DaniyarTurmukhambetovSingle-Image Depth Prediction Makes Feature Matching Easier1053Monday 24 August 202014:00:00Poster
2586DuoLiDeep Reinforced Attention Learning for Quality-Aware Visual Recognition4099Thursday 27 August 202000:00:00Poster
2586DuoLiDeep Reinforced Attention Learning for Quality-Aware Visual Recognition4099Thursday 27 August 202006:00:00Poster
2588YuxiLiCFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization4100Thursday 27 August 202000:00:00Poster
2588YuxiLiCFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization4100Thursday 27 August 202006:00:00Poster
2590YanhongZengLearning Joint Spatial-Temporal Transformations for Video Inpainting3079Wednesday 26 August 202000:00:00Poster
2590YanhongZengLearning Joint Spatial-Temporal Transformations for Video Inpainting3079Wednesday 26 August 202006:00:00Poster
2593ZichaoGuoSingle Path One-Shot Neural Architecture Search with Uniform Sampling3080Wednesday 26 August 202000:00:00Poster
2593ZichaoGuoSingle Path One-Shot Neural Architecture Search with Uniform Sampling3080Wednesday 26 August 202006:00:00Poster
2595KaiyangZhouLearning to Generate Novel Domains for Domain Generalization4315Thursday 27 August 202014:00:00Poster
2595KaiyangZhouLearning to Generate Novel Domains for Domain Generalization4315Friday 28 August 202000:00:00Poster
2597JingjingShenThe Phong Surface: Efficient 3D Model Fitting using Lifted Optimization4316Thursday 27 August 202014:00:00Oral
2597JingjingShenThe Phong Surface: Efficient 3D Model Fitting using Lifted Optimization4316Friday 28 August 202000:00:00Oral
2599MichaelGygliContinuous Adaptation for Interactive Object Segmentation by Learning from Corrections1054Monday 24 August 202006:00:00Poster
2599MichaelGygliContinuous Adaptation for Interactive Object Segmentation by Learning from Corrections1054Monday 24 August 202014:00:00Poster
2601OthmanSbaiImpact of base dataset design on few-shot image classification1055Monday 24 August 202006:00:00Poster
2601OthmanSbaiImpact of base dataset design on few-shot image classification1055Monday 24 August 202014:00:00Poster
2605JieQinInvertible Zero-Shot Recognition Flows3264Wednesday 26 August 202014:00:00Poster
2605JieQinInvertible Zero-Shot Recognition Flows3264Thursday 27 August 202000:00:00Poster
2606WeidongZhangGeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes2109Tuesday 25 August 202000:00:00Poster
2606WeidongZhangGeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes2109Tuesday 25 August 202006:00:00Poster
2607RaulGomezLocation Sensitive Image Retrieval and Tagging1056Monday 24 August 202006:00:00Poster
2607RaulGomezLocation Sensitive Image Retrieval and Tagging1056Monday 24 August 202014:00:00Poster
2608WeiZengJoint 3D Layout and Depth Prediction from a Single Indoor Panorama Image3181Wednesday 26 August 202006:00:00Poster
2608WeiZengJoint 3D Layout and Depth Prediction from a Single Indoor Panorama Image3181Wednesday 26 August 202014:00:00Poster
2612WeiPangGuessing State Tracking for Visual Dialogue4101Thursday 27 August 202000:00:00Poster
2612WeiPangGuessing State Tracking for Visual Dialogue4101Thursday 27 August 202006:00:00Poster
2614AhmetIscenMemory-Efficient Incremental Learning Through Feature Adaptation3182Wednesday 26 August 202006:00:00Poster
2614AhmetIscenMemory-Efficient Incremental Learning Through Feature Adaptation3182Wednesday 26 August 202014:00:00Poster
2616EdgarTretschkDEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects3183Wednesday 26 August 202006:00:00Spotlight
2616EdgarTretschkDEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects3183Wednesday 26 August 202014:00:00Spotlight
2619JustusThiesNeural Voice Puppetry: Audio-driven Facial Reenactment1057Monday 24 August 202006:00:00Poster
2619JustusThiesNeural Voice Puppetry: Audio-driven Facial Reenactment1057Monday 24 August 202014:00:00Poster
2621TatianaTommasiOne-Shot Unsupervised Cross-Domain Detection3184Wednesday 26 August 202006:00:00Poster
2621TatianaTommasiOne-Shot Unsupervised Cross-Domain Detection3184Wednesday 26 August 202014:00:00Poster
2623XiShenRANSAC-Flow: Generic Two-stage Image Alignment1058Monday 24 August 202006:00:00Spotlight
2623XiShenRANSAC-Flow: Generic Two-stage Image Alignment1058Monday 24 August 202014:00:00Spotlight
2629MajedEl HelouStochastic Frequency Masking to Improve Super-Resolution and Denoising Networks1059Monday 24 August 202006:00:00Poster
2629MajedEl HelouStochastic Frequency Masking to Improve Super-Resolution and Denoising Networks1059Monday 24 August 202014:00:00Poster
2630AnthonyHuProbabilistic Future Prediction for Video Scene Understanding2318Tuesday 25 August 202014:00:00Poster
2630AnthonyHuProbabilistic Future Prediction for Video Scene Understanding2318Wednesday 26 August 202000:00:00Poster
2632Arun BalajeeVasudevanSemantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds2255Tuesday 25 August 202006:00:00Spotlight
2632Arun BalajeeVasudevanSemantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds2255Tuesday 25 August 202014:00:00Spotlight
2633KaiWangSuppressing Mislabeled Data via Grouping and Self-Attention4102Thursday 27 August 202000:00:00Poster
2633KaiWangSuppressing Mislabeled Data via Grouping and Self-Attention4102Thursday 27 August 202006:00:00Poster
2636KiruParkNeural Object Learning for 6D Pose Estimation Using a Few Cluttered Images1060Monday 24 August 202006:00:00Spotlight
2636KiruParkNeural Object Learning for 6D Pose Estimation Using a Few Cluttered Images1060Monday 24 August 202014:00:00Spotlight
2638HanzheHuClass-wise Dynamic Graph Convolution for Semantic Segmentation2110Tuesday 25 August 202000:00:00Poster
2638HanzheHuClass-wise Dynamic Graph Convolution for Semantic Segmentation2110Tuesday 25 August 202006:00:00Poster
2639Yun-zhuSongCharacter-Preserving Coherent Story Visualization2111Tuesday 25 August 202000:00:00Poster
2639Yun-zhuSongCharacter-Preserving Coherent Story Visualization2111Tuesday 25 August 202006:00:00Poster
2640TianyiWuGINet: Graph Interaction Network for Scene Parsing4103Thursday 27 August 202000:00:00Poster
2640TianyiWuGINet: Graph Interaction Network for Scene Parsing4103Thursday 27 August 202006:00:00Poster
2641MiaoLiuForecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video2319Tuesday 25 August 202014:00:00Oral
2641MiaoLiuForecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video2319Wednesday 26 August 202000:00:00Oral
2662WanliChenTensor Low-Rank Reconstruction for Semantic Segmentation4104Thursday 27 August 202000:00:00Poster
2662WanliChenTensor Low-Rank Reconstruction for Semantic Segmentation4104Thursday 27 August 202006:00:00Poster
2666HongweiYiDense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking4105Thursday 27 August 202000:00:00Spotlight
2666HongweiYiDense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking4105Thursday 27 August 202006:00:00Spotlight
2668TianfuWuAttentive Normalization4317Thursday 27 August 202014:00:00Poster
2668TianfuWuAttentive Normalization4317Friday 28 August 202000:00:00Poster
2678JinXieCount- and Similarity-aware R-CNN for Pedestrian Detection3265Wednesday 26 August 202014:00:00Poster
2678JinXieCount- and Similarity-aware R-CNN for Pedestrian Detection3265Thursday 27 August 202000:00:00Poster
2682GianniFranchiTRADI: Tracking Deep Neural network Weight Distributions3185Wednesday 26 August 202006:00:00Poster
2682GianniFranchiTRADI: Tracking Deep Neural network Weight Distributions3185Wednesday 26 August 202014:00:00Poster
2683JamesWatsonLearning Stereo from Single Images4318Thursday 27 August 202014:00:00Oral
2683JamesWatsonLearning Stereo from Single Images4318Friday 28 August 202000:00:00Oral
2686AishanLiuSpatiotemporal Attacks for Embodied Agents4106Thursday 27 August 202000:00:00Poster
2686AishanLiuSpatiotemporal Attacks for Embodied Agents4106Thursday 27 August 202006:00:00Poster
2697QingqiuHuangCaption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation2112Tuesday 25 August 202000:00:00Poster
2697QingqiuHuangCaption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation2112Tuesday 25 August 202006:00:00Poster
2701LiqianMaUnselfie: Translating Selfies to Neutral-pose Portraits in the Wild1061Monday 24 August 202006:00:00Poster
2701LiqianMaUnselfie: Translating Selfies to Neutral-pose Portraits in the Wild1061Monday 24 August 202014:00:00Poster
2707XuchongQiuPixel-Pair Occlusion Relationship Map (P2ORM): Formulation, Inference \& Application1062Monday 24 August 202006:00:00Spotlight
2707XuchongQiuPixel-Pair Occlusion Relationship Map (P2ORM): Formulation, Inference \& Application1062Monday 24 August 202014:00:00Spotlight
2709XiaoYangDesign and Interpretation of Universal Adversarial Patches in Face Detection3081Wednesday 26 August 202000:00:00Poster
2709XiaoYangDesign and Interpretation of Universal Adversarial Patches in Face Detection3081Wednesday 26 August 202006:00:00Poster
2710YuXiongMovieNet: A Holistic Dataset for Movie Understanding3082Wednesday 26 August 202000:00:00Spotlight
2710YuXiongMovieNet: A Holistic Dataset for Movie Understanding3082Wednesday 26 August 202006:00:00Spotlight
2712YangXiaoFew-Shot Object Detection and Viewpoint Estimation for Objects in the Wild1063Monday 24 August 202006:00:00Poster
2712YangXiaoFew-Shot Object Detection and Viewpoint Estimation for Objects in the Wild1063Monday 24 August 202014:00:00Poster
2715AdrianSpurrWeakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints1064Monday 24 August 202006:00:00Poster
2715AdrianSpurrWeakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints1064Monday 24 August 202014:00:00Poster
2716MangYeDynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification4107Thursday 27 August 202000:00:00Poster
2716MangYeDynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification4107Thursday 27 August 202006:00:00Poster
2718HaiWangContextual Heterogeneous Graph Network for Human-Object Interaction Detection3083Wednesday 26 August 202000:00:00Poster
2718HaiWangContextual Heterogeneous Graph Network for Human-Object Interaction Detection3083Wednesday 26 August 202006:00:00Poster
2721XiChengZero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning4108Thursday 27 August 202000:00:00Poster
2721XiChengZero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning4108Thursday 27 August 202006:00:00Poster
2723AngLiShort-Term and Long-Term Context Aggregation Network for Video Inpainting4109Thursday 27 August 202000:00:00Spotlight
2723AngLiShort-Term and Long-Term Context Aggregation Network for Video Inpainting4109Thursday 27 August 202006:00:00Spotlight
2724DennisMadsenA Closest Point Proposal for MCMC-based Probabilistic Surface Registration1065Monday 24 August 202006:00:00Poster
2724DennisMadsenA Closest Point Proposal for MCMC-based Probabilistic Surface Registration1065Monday 24 August 202014:00:00Poster
2729YukHeoInteractive Video Object Segmentation Using Global and Local Transfer Modules4110Thursday 27 August 202000:00:00Poster
2729YukHeoInteractive Video Object Segmentation Using Global and Local Transfer Modules4110Thursday 27 August 202006:00:00Poster
2748JinluLiuPrototype Rectification for Few-Shot Learning4111Thursday 27 August 202000:00:00Oral
2748JinluLiuPrototype Rectification for Few-Shot Learning4111Thursday 27 August 202006:00:00Oral
2749ThomasEBOLIEnd-to-end Interpretable Learning of Non-blind Image Deblurring3186Wednesday 26 August 202006:00:00Poster
2749ThomasEBOLIEnd-to-end Interpretable Learning of Non-blind Image Deblurring3186Wednesday 26 August 202014:00:00Poster
2754JuanDuDH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization1066Monday 24 August 202006:00:00Spotlight
2754JuanDuDH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization1066Monday 24 August 202014:00:00Spotlight
2755XiaobinHuFace Super-Resolution Guided by 3D Facial Priors1067Monday 24 August 202006:00:00Spotlight
2755XiaobinHuFace Super-Resolution Guided by 3D Facial Priors1067Monday 24 August 202014:00:00Spotlight
2756JunsongFanEmploying Multi-Estimations for Weakly-Supervised Semantic Segmentation3084Wednesday 26 August 202000:00:00Poster
2756JunsongFanEmploying Multi-Estimations for Weakly-Supervised Semantic Segmentation3084Wednesday 26 August 202006:00:00Poster
2760JingZhangLearning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection4112Thursday 27 August 202000:00:00Poster
2760JingZhangLearning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection4112Thursday 27 August 202006:00:00Poster
2761YinglongWangRethinking Image Deraining via Rain Streaks and Vapors4113Thursday 27 August 202000:00:00Poster
2761YinglongWangRethinking Image Deraining via Rain Streaks and Vapors4113Thursday 27 August 202006:00:00Poster
2763YabinZhangLabel Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation2113Tuesday 25 August 202000:00:00Spotlight
2763YabinZhangLabel Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation2113Tuesday 25 August 202006:00:00Spotlight
2767ChenxiLiuAre Labels Necessary for Neural Architecture Search?2320Tuesday 25 August 202014:00:00Spotlight
2767ChenxiLiuAre Labels Necessary for Neural Architecture Search?2320Wednesday 26 August 202000:00:00Spotlight
2775MarceloGennari do NascimentoFinding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes4319Thursday 27 August 202014:00:00Poster
2775MarceloGennari do NascimentoFinding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes4319Friday 28 August 202000:00:00Poster
2776HaoyangWangBLSM: A Bone-Level Skinned Model of the Human Mesh3266Wednesday 26 August 202014:00:00Spotlight
2776HaoyangWangBLSM: A Bone-Level Skinned Model of the Human Mesh3266Thursday 27 August 202000:00:00Spotlight
2781DakshThaparIs Sharing of Egocentric Video Giving Away Your Biometric Signature?1068Monday 24 August 202006:00:00Poster
2781DakshThaparIs Sharing of Egocentric Video Giving Away Your Biometric Signature?1068Monday 24 August 202014:00:00Poster
2783DannaGurariCaptioning Images Taken by People Who Are Blind3267Wednesday 26 August 202014:00:00Poster
2783DannaGurariCaptioning Images Taken by People Who Are Blind3267Thursday 27 August 202000:00:00Poster
2784QianqianWangLearning Feature Descriptors using Camera Pose Supervision2321Tuesday 25 August 202014:00:00Oral
2784QianqianWangLearning Feature Descriptors using Camera Pose Supervision2321Wednesday 26 August 202000:00:00Oral
2785XiangtaiLiSemantic Flow for Fast and Accurate Scene Parsing2114Tuesday 25 August 202000:00:00Oral
2785XiangtaiLiSemantic Flow for Fast and Accurate Scene Parsing2114Tuesday 25 August 202006:00:00Oral
2788Jogendra NathKunduAppearance Consensus Driven Self-Supervised Human Mesh Recovery3187Wednesday 26 August 202006:00:00Oral
2788Jogendra NathKunduAppearance Consensus Driven Self-Supervised Human Mesh Recovery3187Wednesday 26 August 202014:00:00Oral
2800XiangtaiLiImproving Semantic Segmentation via Decoupled Body and Edge Supervision3085Wednesday 26 August 202000:00:00Poster
2800XiangtaiLiImproving Semantic Segmentation via Decoupled Body and Edge Supervision3085Wednesday 26 August 202006:00:00Poster
2805JerryLiuConditional Entropy Coding for Efficient Video Compression3268Wednesday 26 August 202014:00:00Poster
2805JerryLiuConditional Entropy Coding for Efficient Video Compression3268Thursday 27 August 202000:00:00Poster
2810YushuoGuanDifferentiable Feature Aggregation Search for Knowledge Distillation4114Thursday 27 August 202000:00:00Poster
2810YushuoGuanDifferentiable Feature Aggregation Search for Knowledge Distillation4114Thursday 27 August 202006:00:00Poster
2813AbhijitMahalanobisAttention Guided Anomaly Localization in Images2322Tuesday 25 August 202014:00:00Poster
2813AbhijitMahalanobisAttention Guided Anomaly Localization in Images2322Wednesday 26 August 202000:00:00Poster
2819JiangliuWangSelf-supervised Video Representation Learning by Pace Prediction3086Wednesday 26 August 202000:00:00Poster
2819JiangliuWangSelf-supervised Video Representation Learning by Pace Prediction3086Wednesday 26 August 202006:00:00Poster
2820ChrisRockwellFull-Body Awareness from Partial Observations1173Monday 24 August 202014:00:00Poster
2820ChrisRockwellFull-Body Awareness from Partial Observations1173Tuesday 25 August 202000:00:00Poster
2822LijieLiuReinforced Axial Refinement Network for Monocular 3D Object Detection3087Wednesday 26 August 202000:00:00Poster
2822LijieLiuReinforced Axial Refinement Network for Monocular 3D Object Detection3087Wednesday 26 August 202006:00:00Poster
2825MarkSheininDiffraction Line Imaging2323Tuesday 25 August 202014:00:00Oral
2825MarkSheininDiffraction Line Imaging2323Wednesday 26 August 202000:00:00Oral
2826ArmanAfrasiyabiAssociative Alignment for Few-shot Image Classification1174Monday 24 August 202014:00:00Spotlight
2826ArmanAfrasiyabiAssociative Alignment for Few-shot Image Classification1174Tuesday 25 August 202000:00:00Spotlight
2830EhsanElhamifarSelf-Supervised Multi-Task Procedure Learning from Instructional Videos2324Tuesday 25 August 202014:00:00Poster
2830EhsanElhamifarSelf-Supervised Multi-Task Procedure Learning from Instructional Videos2324Wednesday 26 August 202000:00:00Poster
2834MinyoungHuhAligning and Projecting Images to Class-conditional Generative Networks4320Thursday 27 August 202014:00:00Oral
2834MinyoungHuhAligning and Projecting Images to Class-conditional Generative Networks4320Friday 28 August 202000:00:00Oral
2838YannLabbéCosyPose: Consistent multi-view multi-object 6D pose estimation1069Monday 24 August 202006:00:00Poster
2838YannLabbéCosyPose: Consistent multi-view multi-object 6D pose estimation1069Monday 24 August 202014:00:00Poster
2839JiapengZhuIn-Domain GAN Inversion for Real Image Editing2115Tuesday 25 August 202000:00:00Poster
2839JiapengZhuIn-Domain GAN Inversion for Real Image Editing2115Tuesday 25 August 202006:00:00Poster
2841OctaviaCampsKey Frame Proposal Network for Efficient Pose Estimation in Videos4321Thursday 27 August 202014:00:00Poster
2841OctaviaCampsKey Frame Proposal Network for Efficient Pose Estimation in Videos4321Friday 28 August 202000:00:00Poster
2844YukiSaitoExchangeable Deep Neural Networks for Set-to-Set Matching and Learning2116Tuesday 25 August 202000:00:00Poster
2844YukiSaitoExchangeable Deep Neural Networks for Set-to-Set Matching and Learning2116Tuesday 25 August 202006:00:00Poster
2852XiaoqiZhaoSuppress and Balance: A Simple Gated Network for Salient Object Detection3088Wednesday 26 August 202000:00:00Oral
2852XiaoqiZhaoSuppress and Balance: A Simple Gated Network for Salient Object Detection3088Wednesday 26 August 202006:00:00Oral
2861RobinRombachMaking Sense of CNNs: Interpreting Deep Representations \& Their Invariances with INNs3188Wednesday 26 August 202006:00:00Poster
2861RobinRombachMaking Sense of CNNs: Interpreting Deep Representations \& Their Invariances with INNs3188Wednesday 26 August 202014:00:00Poster
2864GongyangLiCross-Modal Weighting Network for RGB-D Salient Object Detection2117Tuesday 25 August 202006:00:00Poster
2864GongyangLiCross-Modal Weighting Network for RGB-D Salient Object Detection2117Tuesday 25 August 202006:00:00Poster
2865RuiShaoOpen-set Adversarial Defense4115Thursday 27 August 202000:00:00Poster
2865RuiShaoOpen-set Adversarial Defense4115Thursday 27 August 202006:00:00Poster
2866SharonAyzikDeep Image Compression using Decoder Side Information3189Wednesday 26 August 202006:00:00Poster
2866SharonAyzikDeep Image Compression using Decoder Side Information3189Wednesday 26 August 202014:00:00Poster
2873DvirGinzburgCyclic Functional Mapping: Self-supervised Correspondence between Non-isometric Deformable Shapes1070Monday 24 August 202006:00:00Spotlight
2873DvirGinzburgCyclic Functional Mapping: Self-supervised Correspondence between Non-isometric Deformable Shapes1070Monday 24 August 202014:00:00Spotlight
2874AmlanKarMeta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation3269Wednesday 26 August 202014:00:00Poster
2874AmlanKarMeta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation3269Thursday 27 August 202000:00:00Poster
2883AhmedTahaA Generic Visualization Approach for Convolutional Neural Networks3270Wednesday 26 August 202014:00:00Poster
2883AhmedTahaA Generic Visualization Approach for Convolutional Neural Networks3270Thursday 27 August 202000:00:00Poster
2888TianchangShenInteractive Annotation of 3D Object Geometry using 2D Scribbles4322Thursday 27 August 202014:00:00Poster
2888TianchangShenInteractive Annotation of 3D Object Geometry using 2D Scribbles4322Friday 28 August 202000:00:00Poster
2889SrikrishnaKaranamHierarchical Kinematic Human Mesh Recovery4323Thursday 27 August 202014:00:00Poster
2889SrikrishnaKaranamHierarchical Kinematic Human Mesh Recovery4323Friday 28 August 202000:00:00Poster
2890Jae-hanLeeMulti-Loss Rebalancing Algorithm for Monocular Depth Estimation4116Thursday 27 August 202000:00:00Poster
2890Jae-hanLeeMulti-Loss Rebalancing Algorithm for Monocular Depth Estimation4116Thursday 27 August 202006:00:00Poster
2897MarcBadger3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View2325Tuesday 25 August 202014:00:00Poster
2897MarcBadger3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View2325Wednesday 26 August 202000:00:00Poster
2903CamiloFoscoWe Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos1175Monday 24 August 202014:00:00Poster
2903CamiloFoscoWe Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos1175Tuesday 25 August 202000:00:00Poster
2904ChenWangVisual Memorability for Robotic Interestingness via Unsupervised Online Learning4324Thursday 27 August 202014:00:00Oral
2904ChenWangVisual Memorability for Robotic Interestingness via Unsupervised Online Learning4324Friday 28 August 202000:00:00Oral
2905JenniferSunView-Invariant Probabilistic Embedding for Human Pose2326Tuesday 25 August 202014:00:00Spotlight
2905JenniferSunView-Invariant Probabilistic Embedding for Human Pose2326Wednesday 26 August 202000:00:00Spotlight
2908SamuelZeitvogelJoint Optimization for Multi-Person Shape Models from Markerless 3D-Scans1071Monday 24 August 202006:00:00Poster
2908SamuelZeitvogelJoint Optimization for Multi-Person Shape Models from Markerless 3D-Scans1071Monday 24 August 202014:00:00Poster
2916MiaoZhangAccurate RGB-D Salient Object Detection via Collaborative Learning4117Thursday 27 August 202000:00:00Poster
2916MiaoZhangAccurate RGB-D Salient Object Detection via Collaborative Learning4117Thursday 27 August 202006:00:00Poster
2918DavisRempeContact and Human Dynamics from Monocular Video3271Wednesday 26 August 202014:00:00Spotlight
2918DavisRempeContact and Human Dynamics from Monocular Video3271Thursday 27 August 202000:00:00Spotlight
2919DavidGriffithsFinding Your (3D) Center: 3D Object Detection Using a Learned Loss2327Tuesday 25 August 202014:00:00Poster
2919DavidGriffithsFinding Your (3D) Center: 3D Object Detection Using a Learned Loss2327Wednesday 26 August 202000:00:00Poster
2920GanlongZhaoCollaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection4118Thursday 27 August 202000:00:00Poster
2920GanlongZhaoCollaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection4118Thursday 27 August 202006:00:00Poster
2924ZudiLinTwo Stream Active Query Suggestion for Active Learning in Connectomics4325Thursday 27 August 202014:00:00Poster
2924ZudiLinTwo Stream Active Query Suggestion for Active Learning in Connectomics4325Friday 28 August 202000:00:00Poster
2941JiahuiLeiPix2Surf: Learning Parametric 3D Surface Models of Objects from Images3272Wednesday 26 August 202014:00:00Poster
2941JiahuiLeiPix2Surf: Learning Parametric 3D Surface Models of Objects from Images3272Thursday 27 August 202000:00:00Poster
2942MaiBui6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference1072Monday 24 August 202006:00:00Poster
2942MaiBui6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference1072Monday 24 August 202014:00:00Poster
2943YijunLiModeling Artistic Workflows for Image Generation and Editing4326Thursday 27 August 202014:00:00Poster
2943YijunLiModeling Artistic Workflows for Image Generation and Editing4326Friday 28 August 202000:00:00Poster
2945SangpilKimA Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks4327Thursday 27 August 202014:00:00Poster
2945SangpilKimA Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks4327Friday 28 August 202000:00:00Poster
2946JinSunHidden Footprints: Learning Contextual Walkability from 3D Human Trails2328Tuesday 25 August 202014:00:00Poster
2946JinSunHidden Footprints: Learning Contextual Walkability from 3D Human Trails2328Wednesday 26 August 202000:00:00Poster
2949JunFangPost-Training Piecewise Linear Quantization for Deep Neural Networks4328Thursday 27 August 202014:00:00Oral
2949JunFangPost-Training Piecewise Linear Quantization for Deep Neural Networks4328Friday 28 August 202000:00:00Oral
2950WenxuanWuPointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation4329Thursday 27 August 202014:00:00Spotlight
2950WenxuanWuPointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation4329Friday 28 August 202000:00:00Spotlight
2957TriantafyllosAfourasSelf-Supervised Learning of Audio-Visual Objects from Video4330Thursday 27 August 202014:00:00Poster
2957TriantafyllosAfourasSelf-Supervised Learning of Audio-Visual Objects from Video4330Friday 28 August 202000:00:00Poster
2959KwangheeJeongGAN-based Garment Generation Using Sewing Pattern Images4331Thursday 27 August 202014:00:00Poster
2959KwangheeJeongGAN-based Garment Generation Using Sewing Pattern Images4331Friday 28 August 202000:00:00Poster
2962ChaitanyaAhujaStyle Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach4332Thursday 27 August 202014:00:00Poster
2962ChaitanyaAhujaStyle Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach4332Friday 28 August 202000:00:00Poster
2965PhilippErlerPoints2Surf Learning Implicit Surfaces from Point Clouds1073Monday 24 August 202006:00:00Spotlight
2965PhilippErlerPoints2Surf Learning Implicit Surfaces from Point Clouds1073Monday 24 August 202014:00:00Spotlight
2966RuiHuangAn LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds2329Tuesday 25 August 202014:00:00Poster
2966RuiHuangAn LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds2329Wednesday 26 August 202000:00:00Poster
2970TamarLoeubMonotonicity Prior for Cloud Tomography1074Monday 24 August 202006:00:00Poster
2970TamarLoeubMonotonicity Prior for Cloud Tomography1074Monday 24 August 202014:00:00Poster
2971DongLiuLearning Trailer Moments in Full-Length Movies with Co-Contrastive Attention2330Tuesday 25 August 202014:00:00Poster
2971DongLiuLearning Trailer Moments in Full-Length Movies with Co-Contrastive Attention2330Wednesday 26 August 202000:00:00Poster
2974YangZouJoint Disentangling and Adaptation for Cross-Domain Person Re-Identification2331Tuesday 25 August 202014:00:00Oral
2974YangZouJoint Disentangling and Adaptation for Cross-Domain Person Re-Identification2331Wednesday 26 August 202000:00:00Oral
2976ChristopherThomasPreserving Semantic Neighborhoods for Robust Cross-modal Retrieval2332Tuesday 25 August 202014:00:00Poster
2976ChristopherThomasPreserving Semantic Neighborhoods for Robust Cross-modal Retrieval2332Wednesday 26 August 202000:00:00Poster
2978LijieFanIn-Home Daily-Life Captioning Using Radio Signals4333Thursday 27 August 202014:00:00Oral
2978LijieFanIn-Home Daily-Life Captioning Using Radio Signals4333Friday 28 August 202000:00:00Oral
2979VishvakMurahariLarge-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline4334Thursday 27 August 202014:00:00Poster
2979VishvakMurahariLarge-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline4334Friday 28 August 202000:00:00Poster
2981MarcusRohrbachLearning to Generate Grounded Visual Captions without Localization Supervision4335Thursday 27 August 202014:00:00Poster
2981MarcusRohrbachLearning to Generate Grounded Visual Captions without Localization Supervision4335Friday 28 August 202000:00:00Poster
2983YiweiLuFew-Shot Scene-Adaptive Anomaly Detection4336Thursday 27 August 202014:00:00Spotlight
2983YiweiLuFew-Shot Scene-Adaptive Anomaly Detection4336Friday 28 August 202000:00:00Spotlight
2985MengleiChaiNeural Hair Rendering2333Tuesday 25 August 202014:00:00Poster
2985MengleiChaiNeural Hair Rendering2333Wednesday 26 August 202000:00:00Poster
2986BinditaChaudhuriPersonalized Face Modeling for Improved Face Reconstruction and Motion Retargeting2334Tuesday 25 August 202014:00:00Spotlight
2986BinditaChaudhuriPersonalized Face Modeling for Improved Face Reconstruction and Motion Retargeting2334Wednesday 26 August 202000:00:00Spotlight
2988UrbanoNunesEntropy Minimisation Framework for Event-based Vision Model Estimation2335Tuesday 25 August 202014:00:00Spotlight
2988UrbanoNunesEntropy Minimisation Framework for Event-based Vision Model Estimation2335Wednesday 26 August 202000:00:00Spotlight
2989NoranartVesdapuntJNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling4337Thursday 27 August 202014:00:00Poster
2989NoranartVesdapuntJNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling4337Friday 28 August 202000:00:00Poster
2992LuyangZhuReconstructing NBA Players3273Wednesday 26 August 202014:00:00Spotlight
2992LuyangZhuReconstructing NBA Players3273Thursday 27 August 202000:00:00Spotlight
3004YaojieLiuOn Disentangling Spoof Trace for Generic Face Anti-Spoofing4338Thursday 27 August 202014:00:00Poster
3004YaojieLiuOn Disentangling Spoof Trace for Generic Face Anti-Spoofing4338Friday 28 August 202000:00:00Poster
3005WeiHanStreaming Object Detection for 3-D Point Clouds2336Tuesday 25 August 202014:00:00Poster
3005WeiHanStreaming Object Detection for 3-D Point Clouds2336Wednesday 26 August 202000:00:00Poster
3006Yun-ChunChenNAS-DIP: Learning Deep Image Prior with Neural Architecture Search3089Wednesday 26 August 202000:00:00Poster
3006Yun-ChunChenNAS-DIP: Learning Deep Image Prior with Neural Architecture Search3089Wednesday 26 August 202006:00:00Poster
3007Yu-chiang FrankWangLearning to Learn in a Semi-Supervised Fashion2118Tuesday 25 August 202000:00:00Poster
3007Yu-chiang FrankWangLearning to Learn in a Semi-Supervised Fashion2118Tuesday 25 August 202006:00:00Poster
3009Chia-wenKuoFeatMatch: Feature-Based Augmentation for Semi-Supervised Learning1176Monday 24 August 202014:00:00Poster
3009Chia-wenKuoFeatMatch: Feature-Based Augmentation for Semi-Supervised Learning1176Tuesday 25 August 202000:00:00Poster
3017BinYangRadarNet: Exploiting Radar for Robust Perception of Dynamic Objects4339Thursday 27 August 202014:00:00Poster
3017BinYangRadarNet: Exploiting Radar for Robust Perception of Dynamic Objects4339Friday 28 August 202000:00:00Poster
3018DongHuangSelf-Challenging Improves Cross-Domain Generalization4340Thursday 27 August 202014:00:00Oral
3018DongHuangSelf-Challenging Improves Cross-Domain Generalization4340Friday 28 August 202000:00:00Oral
3023AmanpreetSinghSeeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation2337Tuesday 25 August 202014:00:00Poster
3023AmanpreetSinghSeeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation2337Wednesday 26 August 202000:00:00Poster
3024ChenhongyiYangLearning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes2119Tuesday 25 August 202000:00:00Poster
3024ChenhongyiYangLearning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes2119Tuesday 25 August 202006:00:00Poster
3029QingLiA Competence-aware Curriculum for Visual Concepts Learning via Question Answering4341Thursday 27 August 202014:00:00Oral
3029QingLiA Competence-aware Curriculum for Visual Concepts Learning via Question Answering4341Friday 28 August 202000:00:00Oral
3037GuhaBalakrishnanTowards causal benchmarking of bias in face analysis algorithms4342Thursday 27 August 202014:00:00Poster
3037GuhaBalakrishnanTowards causal benchmarking of bias in face analysis algorithms4342Friday 28 August 202000:00:00Poster
3039DongGongLearning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation2120Tuesday 25 August 202000:00:00Poster
3039DongGongLearning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation2120Tuesday 25 August 202006:00:00Poster
3047ChengzhiMaoMultitask Learning Strengthens Adversarial Robustness3274Wednesday 26 August 202014:00:00Oral
3047ChengzhiMaoMultitask Learning Strengthens Adversarial Robustness3274Thursday 27 August 202000:00:00Oral
3054ZhihangYuanS2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search3090Wednesday 26 August 202000:00:00Oral
3054ZhihangYuanS2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search3090Wednesday 26 August 202006:00:00Oral
3056NoaGarciaKnowledge-Based Video Question Answering with Unsupervised Scene Descriptions4119Thursday 27 August 202000:00:00Poster
3056NoaGarciaKnowledge-Based Video Question Answering with Unsupervised Scene Descriptions4119Thursday 27 August 202006:00:00Poster
3066AamirMustafaTransformation Consistency Regularization -- A Semi-Supervised Paradigm for Image-to-Image Translation3275Wednesday 26 August 202014:00:00Poster
3066AamirMustafaTransformation Consistency Regularization -- A Semi-Supervised Paradigm for Image-to-Image Translation3275Thursday 27 August 202000:00:00Poster
3072JianzhaoLiuLIRA: Lifelong Image Restoration from Unknown Blended Distortions4120Thursday 27 August 202000:00:00Poster
3072JianzhaoLiuLIRA: Lifelong Image Restoration from Unknown Blended Distortions4120Thursday 27 August 202006:00:00Poster
3074JiahaoLinHDNet: Human Depth Estimation for Multi-Person Camera-Space Localization3091Wednesday 26 August 202000:00:00Poster
3074JiahaoLinHDNet: Human Depth Estimation for Multi-Person Camera-Space Localization3091Wednesday 26 August 202006:00:00Poster
3082XinlongWangSegmenting Objects by Locations4121Thursday 27 August 202000:00:00Poster
3082XinlongWangSegmenting Objects by Locations4121Thursday 27 August 202006:00:00Poster
3087ZhimingChenPIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments3092Wednesday 26 August 202000:00:00Spotlight
3087ZhimingChenPIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments3092Wednesday 26 August 202006:00:00Spotlight
3089SuchengRenTENet: Triple Excitation Network for Video Salient Object Detection2121Tuesday 25 August 202000:00:00Spotlight
3089SuchengRenTENet: Triple Excitation Network for Video Salient Object Detection2121Tuesday 25 August 202006:00:00Spotlight
3093SongZhangLearning to See in the Dark with Events2122Tuesday 25 August 202000:00:00Poster
3093SongZhangLearning to See in the Dark with Events2122Tuesday 25 August 202006:00:00Poster
3094BorisIvanovicDynamically-Feasible Trajectory Forecasting With Heterogeneous Data2338Tuesday 25 August 202014:00:00Poster
3094BorisIvanovicDynamically-Feasible Trajectory Forecasting With Heterogeneous Data2338Wednesday 26 August 202000:00:00Poster
3098WeiLiuContext-Gated Convolution2123Tuesday 25 August 202000:00:00Poster
3098WeiLiuContext-Gated Convolution2123Tuesday 25 August 202006:00:00Poster
3099Wei-ChiuMaDeep Feedback Inverse Problem Solver4343Thursday 27 August 202014:00:00Spotlight
3099Wei-ChiuMaDeep Feedback Inverse Problem Solver4343Friday 28 August 202000:00:00Spotlight
3100BingkeWangPolynomial Regression Network for Variable-Number Lane Detection4122Thursday 27 August 202000:00:00Poster
3100BingkeWangPolynomial Regression Network for Variable-Number Lane Detection4122Thursday 27 August 202006:00:00Poster
3108WenzhaoZhengStructural Deep Metric Learning for Room Layout Estimation3093Wednesday 26 August 202000:00:00Poster
3108WenzhaoZhengStructural Deep Metric Learning for Room Layout Estimation3093Wednesday 26 August 202006:00:00Poster
3112ZhihaoHuImproving Deep Video Compression by Resolution-adaptive Flow Coding2124Tuesday 25 August 202000:00:00Oral
3112ZhihaoHuImproving Deep Video Compression by Resolution-adaptive Flow Coding2124Tuesday 25 August 202006:00:00Oral
3119LiuyuXiangLearning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification4123Thursday 27 August 202000:00:00Spotlight
3119LiuyuXiangLearning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification4123Thursday 27 August 202006:00:00Spotlight
3120JiayanQiuHallucinating Visual Instances in Total Absentia4344Thursday 27 August 202014:00:00Spotlight
3120JiayanQiuHallucinating Visual Instances in Total Absentia4344Friday 28 August 202000:00:00Spotlight
3122YuanFangAdaptive Task Sampling for Meta-Learning2125Tuesday 25 August 202000:00:00Poster
3122YuanFangAdaptive Task Sampling for Meta-Learning2125Tuesday 25 August 202006:00:00Poster
3124YutingHeDeep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images3094Wednesday 26 August 202000:00:00Poster
3124YutingHeDeep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images3094Wednesday 26 August 202006:00:00Poster
3125JiayuanGuWeakly-supervised 3D Shape Completion in the Wild4345Thursday 27 August 202014:00:00Spotlight
3125JiayuanGuWeakly-supervised 3D Shape Completion in the Wild4345Friday 28 August 202000:00:00Spotlight
3128KailaiZhouImproving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems4124Thursday 27 August 202000:00:00Poster
3128KailaiZhouImproving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems4124Thursday 27 August 202006:00:00Poster
3135YuZengHigh-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling4125Thursday 27 August 202000:00:00Poster
3135YuZengHigh-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling4125Thursday 27 August 202006:00:00Poster
3136DeveshWalawalkarOnline Ensemble Model Compression using Knowledge Distillation3276Wednesday 26 August 202014:00:00Poster
3136DeveshWalawalkarOnline Ensemble Model Compression using Knowledge Distillation3276Thursday 27 August 202000:00:00Poster
3137Byung CheolSongDeep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking System4126Thursday 27 August 202000:00:00Poster
3137Byung CheolSongDeep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking System4126Thursday 27 August 202006:00:00Poster
3149Zhi-GangLiuEfficient Residue Number System Based Winograd Convolution4346Thursday 27 August 202014:00:00Poster
3149Zhi-GangLiuEfficient Residue Number System Based Winograd Convolution4346Friday 28 August 202000:00:00Poster
3150ShuaiJiaRobust Tracking against Adversarial Attacks3095Wednesday 26 August 202000:00:00Poster
3150ShuaiJiaRobust Tracking against Adversarial Attacks3095Wednesday 26 August 202006:00:00Poster
3151ShenSangSingle-Shot Neural Relighting and SVBRDF Estimation3277Wednesday 26 August 202014:00:00Poster
3151ShenSangSingle-Shot Neural Relighting and SVBRDF Estimation3277Thursday 27 August 202000:00:00Poster
3152QiangNieUnsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement2126Tuesday 25 August 202000:00:00Poster
3152QiangNieUnsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement2126Tuesday 25 August 202006:00:00Poster
3155YimingHuAngle-based Search Space Shrinking for Neural Architecture Search3096Wednesday 26 August 202000:00:00Poster
3155YimingHuAngle-based Search Space Shrinking for Neural Architecture Search3096Wednesday 26 August 202006:00:00Poster
3158JuntingDongMotion Capture from Internet Videos4127Thursday 27 August 202000:00:00Oral
3158JuntingDongMotion Capture from Internet Videos4127Thursday 27 August 202006:00:00Oral
3160XiaoyuYueRobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition2127Tuesday 25 August 202000:00:00Poster
3160XiaoyuYueRobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition2127Tuesday 25 August 202006:00:00Poster
3162JianzhuGuoTowards Fast, Accurate and Stable 3D Dense Face Alignment3097Wednesday 26 August 202000:00:00Poster
3162JianzhuGuoTowards Fast, Accurate and Stable 3D Dense Face Alignment3097Wednesday 26 August 202006:00:00Poster
3170Tai-YinChiuIterative Feature Transformation for Fast and Versatile Universal Style Transfer3278Wednesday 26 August 202014:00:00Poster
3170Tai-YinChiuIterative Feature Transformation for Fast and Versatile Universal Style Transfer3278Thursday 27 August 202000:00:00Poster
3177YawenDuanCATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search3098Wednesday 26 August 202000:00:00Poster
3177YawenDuanCATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search3098Wednesday 26 August 202006:00:00Poster
3182TanYuToward Faster and Simpler Matrix Normalization via Rank-1 Update4128Thursday 27 August 202000:00:00Poster
3182TanYuToward Faster and Simpler Matrix Normalization via Rank-1 Update4128Thursday 27 August 202006:00:00Poster
3183XinqianGuAppearance-Preserving 3D Convolution for Video-based Person Re-identification4129Thursday 27 August 202000:00:00Oral
3183XinqianGuAppearance-Preserving 3D Convolution for Video-based Person Re-identification4129Thursday 27 August 202006:00:00Oral
3186YuhiKondoAccurate Polarimetric BRDF for Real Polarization Scene Rendering4130Thursday 27 August 202000:00:00Poster
3186YuhiKondoAccurate Polarimetric BRDF for Real Polarization Scene Rendering4130Thursday 27 August 202006:00:00Poster
3188IlyaReshetouskiLensless Imaging with Focusing Sparse URA Masks in Long-Wave Infrared and its Application for Human Detection2128Tuesday 25 August 202000:00:00Poster
3188IlyaReshetouskiLensless Imaging with Focusing Sparse URA Masks in Long-Wave Infrared and its Application for Human Detection2128Tuesday 25 August 202006:00:00Poster
3190XiaopengHongTopology-Preserving Class-Incremental Learning4131Thursday 27 August 202000:00:00Poster
3190XiaopengHongTopology-Preserving Class-Incremental Learning4131Thursday 27 August 202006:00:00Poster
3199XiaolinZhangInter-Image Communication for Weakly Supervised Localization2129Tuesday 25 August 202000:00:00Poster
3199XiaolinZhangInter-Image Communication for Weakly Supervised Localization2129Tuesday 25 August 202006:00:00Poster
3205ZhidingYuUFO$^2$: A Unified Framework towards Omni-supervised Object Detection1177Monday 24 August 202014:00:00Poster
3205ZhidingYuUFO$^2$: A Unified Framework towards Omni-supervised Object Detection1177Tuesday 25 August 202000:00:00Poster
3215DahuinJungiCaps: An Interpretable Classifier via Disentangled Capsule Networks2130Tuesday 25 August 202006:00:00Poster
3215DahuinJungiCaps: An Interpretable Classifier via Disentangled Capsule Networks2130Tuesday 25 August 202006:00:00Poster
3220EthanWeberDetecting Natural Disasters, Damage, and Incidents in the Wild2339Tuesday 25 August 202014:00:00Poster
3220EthanWeberDetecting Natural Disasters, Damage, and Incidents in the Wild2339Wednesday 26 August 202000:00:00Poster
3223YinpengChenDynamic ReLU4347Thursday 27 August 202014:00:00Poster
3223YinpengChenDynamic ReLU4347Friday 28 August 202000:00:00Poster
3224KoheiSakaiAcquiring Dynamic Light Fields through Coded Aperture Camera4132Thursday 27 August 202000:00:00Poster
3224KoheiSakaiAcquiring Dynamic Light Fields through Coded Aperture Camera4132Thursday 27 August 202006:00:00Poster
3238ChiXuGait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network2131Tuesday 25 August 202000:00:00Poster
3238ChiXuGait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network2131Tuesday 25 August 202006:00:00Poster
3240JieCaoInformative Sample Mining Network for Multi-Domain Image-to-Image Translation2132Tuesday 25 August 202000:00:00Poster
3240JieCaoInformative Sample Mining Network for Multi-Domain Image-to-Image Translation2132Tuesday 25 August 202006:00:00Poster
3241DylanCampbellSolving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization3099Wednesday 26 August 202000:00:00Oral
3241DylanCampbellSolving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization3099Wednesday 26 August 202006:00:00Oral
3242YukeZhuSpherical Feature Transform for Deep Metric Learning4133Thursday 27 August 202000:00:00Poster
3242YukeZhuSpherical Feature Transform for Deep Metric Learning4133Thursday 27 August 202006:00:00Poster
3245RuixueTangSemantic Equivalent Adversarial Data Augmentation for Visual Question Answering2133Tuesday 25 August 202000:00:00Poster
3245RuixueTangSemantic Equivalent Adversarial Data Augmentation for Visual Question Answering2133Tuesday 25 August 202006:00:00Poster
3254RanSongUnsupervised Multi-View CNN for Salient View Selection of 3D Objects and Scenes3100Wednesday 26 August 202000:00:00Poster
3254RanSongUnsupervised Multi-View CNN for Salient View Selection of 3D Objects and Scenes3100Wednesday 26 August 202006:00:00Poster
3265XingangPanExploiting Deep Generative Prior for Versatile Image Restoration and Manipulation2134Tuesday 25 August 202000:00:00Oral
3265XingangPanExploiting Deep Generative Prior for Versatile Image Restoration and Manipulation2134Tuesday 25 August 202006:00:00Oral
3266YujieZhongRepresentation Sharing for Fast Object Detector Search and Beyond4134Thursday 27 August 202000:00:00Poster
3266YujieZhongRepresentation Sharing for Fast Object Detector Search and Beyond4134Thursday 27 August 202006:00:00Poster
3268XuanyeZhangPeeking into occluded joints: A novel framework for crowd pose estimation3101Wednesday 26 August 202000:00:00Poster
3268XuanyeZhangPeeking into occluded joints: A novel framework for crowd pose estimation3101Wednesday 26 August 202006:00:00Poster
3271LinxiFanRubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition2340Tuesday 25 August 202014:00:00Poster
3271LinxiFanRubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition2340Wednesday 26 August 202000:00:00Poster
3281ZiweiWangDeep Hashing with Active Pairwise Supervision2135Tuesday 25 August 202000:00:00Poster
3281ZiweiWangDeep Hashing with Active Pairwise Supervision2135Tuesday 25 August 202006:00:00Poster
3293LichangChenGraph Edit Distance Reward: Learning to Edit Scene Graph2136Tuesday 25 August 202000:00:00Poster
3293LichangChenGraph Edit Distance Reward: Learning to Edit Scene Graph2136Tuesday 25 August 202006:00:00Poster
3295YajieXingMalleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing3102Wednesday 26 August 202000:00:00Poster
3295YajieXingMalleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing3102Wednesday 26 August 202006:00:00Poster
3301ChangShuFeature-metric Loss for Self-supervised Learning of Depth and Egomotion2137Tuesday 25 August 202000:00:00Poster
3301ChangShuFeature-metric Loss for Self-supervised Learning of Depth and Egomotion2137Tuesday 25 August 202006:00:00Poster
3304SibeiYangPropagating Over Phrase Relations for One-Stage Visual Grounding4135Thursday 27 August 202000:00:00Poster
3304SibeiYangPropagating Over Phrase Relations for One-Stage Visual Grounding4135Thursday 27 August 202006:00:00Poster
3307ChangxinGaoAdversarial Semantic Data Augmentation for Human Pose Estimation1075Monday 24 August 202006:00:00Poster
3307ChangxinGaoAdversarial Semantic Data Augmentation for Human Pose Estimation1075Monday 24 August 202014:00:00Poster
3312MontangGuoDeep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures2138Tuesday 25 August 202000:00:00Oral
3312MontangGuoDeep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures2138Tuesday 25 August 202006:00:00Oral
3314GernotRieglerFree View Synthesis1076Monday 24 August 202006:00:00Poster
3314GernotRieglerFree View Synthesis1076Monday 24 August 202014:00:00Poster
3315Ke-YueZhangFace Anti-Spoofing via Disentangled Representation Learning3103Wednesday 26 August 202000:00:00Poster
3315Ke-YueZhangFace Anti-Spoofing via Disentangled Representation Learning3103Wednesday 26 August 202006:00:00Poster
3317YuchenDaiPrime-Aware Adaptive Distillation3104Wednesday 26 August 202000:00:00Poster
3317YuchenDaiPrime-Aware Adaptive Distillation3104Wednesday 26 August 202006:00:00Poster
3318XiaotongYuanMeta-Learning with Network Pruning4136Thursday 27 August 202000:00:00Poster
3318XiaotongYuanMeta-Learning with Network Pruning4136Thursday 27 August 202006:00:00Poster
3323DongshengGuoSpiral Generative Network for Image Extrapolation3105Wednesday 26 August 202000:00:00Poster
3323DongshengGuoSpiral Generative Network for Image Extrapolation3105Wednesday 26 August 202006:00:00Poster
3324FangLiuSceneSketcher: Fine-Grained Image Retrieval with Scene Sketches2139Tuesday 25 August 202000:00:00Poster
3324FangLiuSceneSketcher: Fine-Grained Image Retrieval with Scene Sketches2139Tuesday 25 August 202006:00:00Poster
3331XuesongNiuVideo-based Remote Physiological Measurement via Cross-verified Feature Disentangling3106Wednesday 26 August 202000:00:00Oral
3331XuesongNiuVideo-based Remote Physiological Measurement via Cross-verified Feature Disentangling3106Wednesday 26 August 202006:00:00Oral
3335JiangningZhangDTVNet: Dynamic Time-lapse Video Generation via Single Still Image2140Tuesday 25 August 202000:00:00Spotlight
3335JiangningZhangDTVNet: Dynamic Time-lapse Video Generation via Single Still Image2140Tuesday 25 August 202006:00:00Spotlight
3337JunbumChaFew-shot Compositional Font Generation with Dual Memory4137Thursday 27 August 202000:00:00Poster
3337JunbumChaFew-shot Compositional Font Generation with Dual Memory4137Thursday 27 August 202006:00:00Poster
3338YueQianPUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling4138Thursday 27 August 202000:00:00Poster
3338YueQianPUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling4138Thursday 27 August 202006:00:00Poster
3348LucaCavalliHandcrafted Outlier Detection Revisited1077Monday 24 August 202006:00:00Poster
3348LucaCavalliHandcrafted Outlier Detection Revisited1077Monday 24 August 202014:00:00Poster
3356Bharat LalBhatnagarCombining Implicit Function Learning and Parametric Models for 3D Human Reconstruction1078Monday 24 August 202006:00:00Oral
3356Bharat LalBhatnagarCombining Implicit Function Learning and Parametric Models for 3D Human Reconstruction1078Monday 24 August 202014:00:00Oral
3359LucaCosmoThe Average Mixing Kernel Signature1079Monday 24 August 202006:00:00Poster
3359LucaCosmoThe Average Mixing Kernel Signature1079Monday 24 August 202014:00:00Poster
3361BoyiJiangBCNet: Learning Body and Cloth Shape from A Single Image3107Wednesday 26 August 202000:00:00Poster
3361BoyiJiangBCNet: Learning Body and Cloth Shape from A Single Image3107Wednesday 26 August 202006:00:00Poster
3365LijunWangCLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss2141Tuesday 25 August 202000:00:00Spotlight
3365LijunWangCLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss2141Tuesday 25 August 202006:00:00Spotlight
3372AndreasDöringSelf-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos3190Wednesday 26 August 202006:00:00Poster
3372AndreasDöringSelf-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos3190Wednesday 26 August 202014:00:00Poster
3375JingwenHeInteractive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration3108Wednesday 26 August 202000:00:00Poster
3375JingwenHeInteractive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration3108Wednesday 26 August 202006:00:00Poster
3376Tsai-shienChenOrientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network2142Tuesday 25 August 202000:00:00Oral
3376Tsai-shienChenOrientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network2142Tuesday 25 August 202006:00:00Oral
3382ChangxingDingPolysemy Deciphering Network for Human-Object Interaction Detection4139Thursday 27 August 202000:00:00Poster
3382ChangxingDingPolysemy Deciphering Network for Human-Object Interaction Detection4139Thursday 27 August 202006:00:00Poster
3384ArthurDouillardPODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning1080Monday 24 August 202006:00:00Poster
3384ArthurDouillardPODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning1080Monday 24 August 202014:00:00Poster
3385ZongxinYangCollaborative Video Object Segmentation by Foreground-Background Integration4140Thursday 27 August 202000:00:00Spotlight
3385ZongxinYangCollaborative Video Object Segmentation by Foreground-Background Integration4140Thursday 27 August 202006:00:00Spotlight
3386FrancescaPistilliLearning Graph-Convolutional Representations for Point Cloud Denoising3191Wednesday 26 August 202006:00:00Poster
3386FrancescaPistilliLearning Graph-Convolutional Representations for Point Cloud Denoising3191Wednesday 26 August 202014:00:00Poster
3387GuoleiSunMining Cross-Image Semantics for Weakly Supervised Semantic Segmentation1081Monday 24 August 202006:00:00Oral
3387GuoleiSunMining Cross-Image Semantics for Weakly Supervised Semantic Segmentation1081Monday 24 August 202014:00:00Oral
3397DongkwonJinSemantic Line Detection Using Mirror Attention and Comparative Ranking and Matching4141Thursday 27 August 202000:00:00Poster
3397DongkwonJinSemantic Line Detection Using Mirror Attention and Comparative Ranking and Matching4141Thursday 27 August 202006:00:00Poster
3398MarcoCanniciA Differentiable Recurrent Surface for Asynchronous Event-Based Data2341Tuesday 25 August 202014:00:00Poster
3398MarcoCanniciA Differentiable Recurrent Surface for Asynchronous Event-Based Data2341Wednesday 26 August 202000:00:00Poster
3399RuoyiDuFine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches3109Wednesday 26 August 202000:00:00Poster
3399RuoyiDuFine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches3109Wednesday 26 August 202006:00:00Poster
3400Tak-WaiHuiLiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation3110Wednesday 26 August 202000:00:00Poster
3400Tak-WaiHuiLiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation3110Wednesday 26 August 202006:00:00Poster
3405ValeriyaProninaMicroscopy Image Restoration with Deep Wiener-Kolmogorov Filters3192Wednesday 26 August 202006:00:00Poster
3405ValeriyaProninaMicroscopy Image Restoration with Deep Wiener-Kolmogorov Filters3192Wednesday 26 August 202014:00:00Poster
3408Dave ZhenyuChenScanRefer: 3D Object Localization in RGB-D Scans using Natural Language1082Monday 24 August 202006:00:00Poster
3408Dave ZhenyuChenScanRefer: 3D Object Localization in RGB-D Scans using Natural Language1082Monday 24 August 202014:00:00Poster
3411ZeyuHuJoint Semantic Segmentation and Edge Detection Network for 3D Point Clouds3111Wednesday 26 August 202000:00:00Poster
3411ZeyuHuJoint Semantic Segmentation and Edge Detection Network for 3D Point Clouds3111Wednesday 26 August 202006:00:00Poster
3412HuZhangMotion-Excited Sampler: Video Adversarial Attack with Sparked Prior4142Thursday 27 August 202000:00:00Poster
3412HuZhangMotion-Excited Sampler: Video Adversarial Attack with Sparked Prior4142Thursday 27 August 202006:00:00Poster
3414IshantShanuAn Inference Algorithm for Multi-Label MRF-MAP Problems with Clique Size 1001083Monday 24 August 202006:00:00Poster
3414IshantShanuAn Inference Algorithm for Multi-Label MRF-MAP Problems with Clique Size 1001083Monday 24 August 202014:00:00Poster
3425BaojiefanDual Refinement Underwater Object Detection Network4143Thursday 27 August 202000:00:00Poster
3425BaojiefanDual Refinement Underwater Object Detection Network4143Thursday 27 August 202006:00:00Poster
3429RuiQianMultiple Sound Sources Localization from Coarse to Fine2143Tuesday 25 August 202000:00:00Poster
3429RuiQianMultiple Sound Sources Localization from Coarse to Fine2143Tuesday 25 August 202006:00:00Poster
3439StefanPopovCoReNet: Coherent 3D Scene Reconstruction from a Single RGB Image1084Monday 24 August 202006:00:00Oral
3439StefanPopovCoReNet: Coherent 3D Scene Reconstruction from a Single RGB Image1084Monday 24 August 202014:00:00Oral
3456TitirDuttaAdaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIR1085Monday 24 August 202006:00:00Spotlight
3456TitirDuttaAdaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIR1085Monday 24 August 202014:00:00Spotlight
3457JinyoungChoiTask-Aware Quantization Network for JPEG Image Compression2144Tuesday 25 August 202000:00:00Poster
3457JinyoungChoiTask-Aware Quantization Network for JPEG Image Compression2144Tuesday 25 August 202006:00:00Poster
3472FredrikGustafssonEnergy-Based Models for Deep Probabilistic Regression2256Tuesday 25 August 202006:00:00Poster
3472FredrikGustafssonEnergy-Based Models for Deep Probabilistic Regression2256Tuesday 25 August 202014:00:00Poster
3477XucongZhangETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation1086Monday 24 August 202006:00:00Spotlight
3477XucongZhangETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation1086Monday 24 August 202014:00:00Spotlight
3478HugoBerticheCLOTH3D: Clothed 3D Humans1087Monday 24 August 202006:00:00Poster
3478HugoBerticheCLOTH3D: Clothed 3D Humans1087Monday 24 August 202014:00:00Poster
3482LeiHuangLayer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs2342Tuesday 25 August 202014:00:00Oral
3482LeiHuangLayer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs2342Wednesday 26 August 202000:00:00Oral
3484KangZhouEncoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images3112Wednesday 26 August 202000:00:00Poster
3484KangZhouEncoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images3112Wednesday 26 August 202006:00:00Poster
3485XingpingDongCLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers2343Tuesday 25 August 202014:00:00Poster
3485XingpingDongCLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers2343Wednesday 26 August 202000:00:00Poster
3488LuZhouOcclusion-Aware Siamese Network for Human Pose Estimation4144Thursday 27 August 202000:00:00Poster
3488LuZhouOcclusion-Aware Siamese Network for Human Pose Estimation4144Thursday 27 August 202006:00:00Poster
3492YufanLiuLearning to Predict Salient Faces: A Novel Visual-Audio Saliency Model2145Tuesday 25 August 202000:00:00Poster
3492YufanLiuLearning to Predict Salient Faces: A Novel Visual-Audio Saliency Model2145Tuesday 25 August 202006:00:00Poster
3495LizhenWangNormalGAN: Learning Detailed 3D Human from a Single RGB-D Image3113Wednesday 26 August 202000:00:00Poster
3495LizhenWangNormalGAN: Learning Detailed 3D Human from a Single RGB-D Image3113Wednesday 26 August 202006:00:00Poster
3498FabioPizzatiModel-based occlusion disentanglement for image-to-image translation3193Wednesday 26 August 202006:00:00Poster
3498FabioPizzatiModel-based occlusion disentanglement for image-to-image translation3193Wednesday 26 August 202014:00:00Poster
3499ViktorLarssonCalibration-free Structure-from-Motion with Calibrated Radial Trifocal Tensors1088Monday 24 August 202006:00:00Spotlight
3499ViktorLarssonCalibration-free Structure-from-Motion with Calibrated Radial Trifocal Tensors1088Monday 24 August 202014:00:00Spotlight
3506YuZhengRotation-robust Intersection over Union for 3D Object Detection2146Tuesday 25 August 202000:00:00Poster
3506YuZhengRotation-robust Intersection over Union for 3D Object Detection2146Tuesday 25 August 202006:00:00Poster
3508YiHuangNew Threats against Object Detector with Non-local Block3114Wednesday 26 August 202000:00:00Poster
3508YiHuangNew Threats against Object Detector with Non-local Block3114Wednesday 26 August 202006:00:00Poster
3516LinlinShenSelf-Supervised CycleGAN for Object-Preserving Image-to-Image Domain Adaptation2147Tuesday 25 August 202000:00:00Poster
3516LinlinShenSelf-Supervised CycleGAN for Object-Preserving Image-to-Image Domain Adaptation2147Tuesday 25 August 202006:00:00Poster
3526ZacharyTeedRAFT: Recurrent All-Pairs Field Transforms for Optical Flow4348Thursday 27 August 202014:00:00Oral
3526ZacharyTeedRAFT: Recurrent All-Pairs Field Transforms for Optical Flow4348Friday 28 August 202000:00:00Oral
3528FeihuZhangDomain-invariant Stereo Matching Networks2344Tuesday 25 August 202014:00:00Oral
3528FeihuZhangDomain-invariant Stereo Matching Networks2344Wednesday 26 August 202000:00:00Oral
3533FedericaArrigoniOn the Usage of the Trifocal Tensor in Motion Segmentation3194Wednesday 26 August 202006:00:00Poster
3533FedericaArrigoniOn the Usage of the Trifocal Tensor in Motion Segmentation3194Wednesday 26 August 202014:00:00Poster
3538GyeongsikMoonDeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling4145Thursday 27 August 202000:00:00Oral
3538GyeongsikMoonDeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling4145Thursday 27 August 202006:00:00Oral
3539WenShen3D-Rotation-Equivariant Quaternion Neural Networks2148Tuesday 25 August 202000:00:00Poster
3539WenShen3D-Rotation-Equivariant Quaternion Neural Networks2148Tuesday 25 August 202006:00:00Poster
3540HeWenInterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image2149Tuesday 25 August 202000:00:00Poster
3540HeWenInterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image2149Tuesday 25 August 202006:00:00Poster
3544ChunleiCaiContent Adaptive and Error Propagation Aware Deep Video Compression2150Tuesday 25 August 202000:00:00Oral
3544ChunleiCaiContent Adaptive and Error Propagation Aware Deep Video Compression2150Tuesday 25 August 202006:00:00Oral
3548MiaojingShiActive Crowd Counting with Limited Supervision3279Wednesday 26 August 202014:00:00Poster
3548MiaojingShiActive Crowd Counting with Limited Supervision3279Thursday 27 August 202000:00:00Poster
3551MarvinKlingnerSelf-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance1089Monday 24 August 202006:00:00Poster
3551MarvinKlingnerSelf-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance1089Monday 24 August 202014:00:00Poster
3553Mengtian (Martin)LiTowards Streaming Perception4349Thursday 27 August 202014:00:00Oral
3553Mengtian (Martin)LiTowards Streaming Perception4349Friday 28 August 202000:00:00Oral
3563ShaoxiangChenHierarchical Visual-Textual Graph for Temporal Activity Localization via Language4146Thursday 27 August 202000:00:00Poster
3563ShaoxiangChenHierarchical Visual-Textual Graph for Temporal Activity Localization via Language4146Thursday 27 August 202006:00:00Poster
3568ThibautIssenhuthDo Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On1090Monday 24 August 202006:00:00Poster
3568ThibautIssenhuthDo Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On1090Monday 24 August 202014:00:00Poster
3570RakshithShettyTowards Automated Testing and Robustification by Semantic Adversarial Data Generation1091Monday 24 August 202006:00:00Oral
3570RakshithShettyTowards Automated Testing and Robustification by Semantic Adversarial Data Generation1091Monday 24 August 202014:00:00Oral
3577YurenCongNODIS: Neural Ordinary Differential Scene Understanding1092Monday 24 August 202006:00:00Poster
3577YurenCongNODIS: Neural Ordinary Differential Scene Understanding1092Monday 24 August 202014:00:00Poster
3582AjPiergiovanniAdversarial Generative Grammars for Human Activity Prediction1178Monday 24 August 202014:00:00Oral
3582AjPiergiovanniAdversarial Generative Grammars for Human Activity Prediction1178Tuesday 25 August 202000:00:00Oral
3586MichaelRyooAssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -4350Thursday 27 August 202014:00:00Poster
3586MichaelRyooAssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -4350Friday 28 August 202000:00:00Poster
3587AmeyaPrabhuGDumb: A Simple Approach that Questions Our Progress in Continual Learning1093Monday 24 August 202006:00:00Oral
3587AmeyaPrabhuGDumb: A Simple Approach that Questions Our Progress in Continual Learning1093Monday 24 August 202014:00:00Oral
3588YidingYangLearning Propagation Rules for Attribution Map Generation3280Wednesday 26 August 202014:00:00Poster
3588YidingYangLearning Propagation Rules for Attribution Map Generation3280Thursday 27 August 202000:00:00Poster
3590MenelaosKanakisReparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference3195Wednesday 26 August 202006:00:00Poster
3590MenelaosKanakisReparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference3195Wednesday 26 August 202014:00:00Poster
3594Santhosh KumarRamakrishnanOccupancy Anticipation for Efficient Exploration and Navigation3281Wednesday 26 August 202014:00:00Spotlight
3594Santhosh KumarRamakrishnanOccupancy Anticipation for Efficient Exploration and Navigation3281Thursday 27 August 202000:00:00Spotlight
3601RichardDrosteUnified Image and Video Saliency Modeling2345Tuesday 25 August 202014:00:00Spotlight
3601RichardDrosteUnified Image and Video Saliency Modeling2345Wednesday 26 August 202000:00:00Spotlight
3604AchalDaveTAO: A Large-Scale Benchmark for Tracking Any Object2346Tuesday 25 August 202014:00:00Spotlight
3604AchalDaveTAO: A Large-Scale Benchmark for Tracking Any Object2346Wednesday 26 August 202000:00:00Spotlight
3606KarlSchmeckpeperLearning Predictive Models from Observation and Interaction2347Tuesday 25 August 202014:00:00Poster
3606KarlSchmeckpeperLearning Predictive Models from Observation and Interaction2347Wednesday 26 August 202000:00:00Poster
3607AndreAraujoUnifying Deep Local and Global Features for Image Search4351Thursday 27 August 202014:00:00Poster
3607AndreAraujoUnifying Deep Local and Global Features for Image Search4351Friday 28 August 202000:00:00Poster
3610JieSongHuman Body Model Fitting by Learned Gradient Descent1094Monday 24 August 202006:00:00Poster
3610JieSongHuman Body Model Fitting by Learned Gradient Descent1094Monday 24 August 202014:00:00Poster
3611XinLiDDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition4352Thursday 27 August 202014:00:00Poster
3611XinLiDDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition4352Friday 28 August 202000:00:00Poster
3615FeiYeLearning latent representations across multiple data domains using Lifelong VAEGAN2348Tuesday 25 August 202014:00:00Poster
3615FeiYeLearning latent representations across multiple data domains using Lifelong VAEGAN2348Wednesday 26 August 202000:00:00Poster
3620FeixiangLuDVI: Depth Guided Video Inpainting for Autonomous Driving4147Thursday 27 August 202000:00:00Poster
3620FeixiangLuDVI: Depth Guided Video Inpainting for Autonomous Driving4147Thursday 27 August 202006:00:00Poster
3622MingLiangLearning Lane Graph Representations for Motion Forecasting4353Thursday 27 August 202014:00:00Oral
3622MingLiangLearning Lane Graph Representations for Motion Forecasting4353Friday 28 August 202000:00:00Oral
3627NingXuIncorporating Reinforced Adversarial Learning in Autoregressive Image Generation2151Tuesday 25 August 202000:00:00Poster
3627NingXuIncorporating Reinforced Adversarial Learning in Autoregressive Image Generation2151Tuesday 25 August 202006:00:00Poster
3632MatthewWalmerAPRICOT: A Dataset of Physical Adversarial Attacks on Object Detection3282Wednesday 26 August 202014:00:00Poster
3632MatthewWalmerAPRICOT: A Dataset of Physical Adversarial Attacks on Object Detection3282Thursday 27 August 202000:00:00Poster
3640YutingZhangVisual Question Answering on Image Sets1179Monday 24 August 202014:00:00Poster
3640YutingZhangVisual Question Answering on Image Sets1179Tuesday 25 August 202000:00:00Poster
3643QiChenObject as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots3283Wednesday 26 August 202014:00:00Poster
3643QiChenObject as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots3283Thursday 27 August 202000:00:00Poster
3644HuaiyiHuangPlacepedia: Comprehensive Place Understanding with Multi-Faceted Annotations2152Tuesday 25 August 202000:00:00Poster
3644HuaiyiHuangPlacepedia: Comprehensive Place Understanding with Multi-Faceted Annotations2152Tuesday 25 August 202006:00:00Poster
3649AyanSinhaDELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points2349Tuesday 25 August 202014:00:00Poster
3649AyanSinhaDELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points2349Wednesday 26 August 202000:00:00Poster
3651RicoJonschkowskiWhat Matters in Unsupervised Optical Flow3196Wednesday 26 August 202006:00:00Oral
3651RicoJonschkowskiWhat Matters in Unsupervised Optical Flow3196Wednesday 26 August 202014:00:00Oral
3654StanleyChanDynamic Low-light Imaging with Quanta Image Sensors2350Tuesday 25 August 202014:00:00Poster
3654StanleyChanDynamic Low-light Imaging with Quanta Image Sensors2350Wednesday 26 August 202000:00:00Poster
3657JonathanBarronA Generalization of Otsu's Method and Minimum Error Thresholding2351Tuesday 25 August 202014:00:00Spotlight
3657JonathanBarronA Generalization of Otsu's Method and Minimum Error Thresholding2351Wednesday 26 August 202000:00:00Spotlight
3663UnnatJainA Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks4354Thursday 27 August 202014:00:00Spotlight
3663UnnatJainA Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks4354Friday 28 August 202000:00:00Spotlight
3665LucasBeyerBig Transfer (BiT): General Visual Representation Learning2257Tuesday 25 August 202006:00:00Spotlight
3665LucasBeyerBig Transfer (BiT): General Visual Representation Learning2257Tuesday 25 August 202014:00:00Spotlight
3668MarkNishimuraDisambiguating Monocular Depth Estimation with a Single Transient4355Thursday 27 August 202014:00:00Poster
3668MarkNishimuraDisambiguating Monocular Depth Estimation with a Single Transient4355Friday 28 August 202000:00:00Poster
3672WenyuanZengDSDNet: Deep Structured self-Driving Network4356Thursday 27 August 202014:00:00Poster
3672WenyuanZengDSDNet: Deep Structured self-Driving Network4356Friday 28 August 202000:00:00Poster
3678XiaoweiZhangSynthesis and Completion of Facades from Satellite Imagery4357Thursday 27 August 202014:00:00Oral
3678XiaoweiZhangSynthesis and Completion of Facades from Satellite Imagery4357Friday 28 August 202000:00:00Oral
3679HimalayaJainQuEST: Quantized Embedding Space for Transferring Knowledge1095Monday 24 August 202006:00:00Poster
3679HimalayaJainQuEST: Quantized Embedding Space for Transferring Knowledge1095Monday 24 August 202014:00:00Poster
3684Jae SungParkVisualCOMET: Reasoning about the Dynamic Context of a Still Image2153Tuesday 25 August 202000:00:00Spotlight
3684Jae SungParkVisualCOMET: Reasoning about the Dynamic Context of a Still Image2153Tuesday 25 August 202006:00:00Spotlight
3685RongchangZhaoEGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma Diagnosis3284Wednesday 26 August 202014:00:00Poster
3685RongchangZhaoEGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma Diagnosis3284Thursday 27 August 202000:00:00Poster
3689GukyeongKwonBackpropagated Gradient Representations for Anomaly Detection2352Tuesday 25 August 202014:00:00Poster
3689GukyeongKwonBackpropagated Gradient Representations for Anomaly Detection2352Wednesday 26 August 202000:00:00Poster
3694YinghaoXuDense RepPoints: Representing Visual Objects with Dense Point Sets4148Thursday 27 August 202000:00:00Poster
3694YinghaoXuDense RepPoints: Representing Visual Objects with Dense Point Sets4148Thursday 27 August 202006:00:00Poster
3696XikunZhangOn Dropping Clusters to Regularize Graph Convolutional Neural Networks2154Tuesday 25 August 202000:00:00Poster
3696XikunZhangOn Dropping Clusters to Regularize Graph Convolutional Neural Networks2154Tuesday 25 August 202006:00:00Poster
3702MrigankRochanAdaptive Video Highlight Detection by Learning from User History2353Tuesday 25 August 202014:00:00Poster
3702MrigankRochanAdaptive Video Highlight Detection by Learning from User History2353Wednesday 26 August 202000:00:00Poster
3705ShuyangChengImproving 3D Object Detection through Progressive Population Based Augmentation2354Tuesday 25 August 202014:00:00Poster
3705ShuyangChengImproving 3D Object Detection through Progressive Population Based Augmentation2354Wednesday 26 August 202000:00:00Poster
3719JiongchaoJinDR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction1180Monday 24 August 202014:00:00Poster
3719JiongchaoJinDR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction1180Tuesday 25 August 202000:00:00Poster
3720RamNevatiaSPAN: Spatial Pyramid Attention Network for Image Manipulation Localization4358Thursday 27 August 202014:00:00Poster
3720RamNevatiaSPAN: Spatial Pyramid Attention Network for Image Manipulation Localization4358Friday 28 August 202000:00:00Poster
3721JinghuaWangAdversarial Learning for Zero-shot Domain Adaptation3115Wednesday 26 August 202000:00:00Poster
3721JinghuaWangAdversarial Learning for Zero-shot Domain Adaptation3115Wednesday 26 August 202006:00:00Poster
3723YukihiroSasagawaYOLO in the Dark - Domain Adaptation Method for Merging Multiple Models -3116Wednesday 26 August 202000:00:00Poster
3723YukihiroSasagawaYOLO in the Dark - Domain Adaptation Method for Merging Multiple Models -3116Wednesday 26 August 202006:00:00Poster
3739Jae SungParkIdentity-Aware Multi-Sentence Video Description4149Thursday 27 August 202000:00:00Poster
3739Jae SungParkIdentity-Aware Multi-Sentence Video Description4149Thursday 27 August 202006:00:00Poster
3742TejasGokhaleVQA-LOL: Visual Question Answering under the Lens of Logic3285Wednesday 26 August 202014:00:00Poster
3742TejasGokhaleVQA-LOL: Visual Question Answering under the Lens of Logic3285Thursday 27 August 202000:00:00Poster
3751MengyaoZhaiPiggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation4150Thursday 27 August 202000:00:00Poster
3751MengyaoZhaiPiggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation4150Thursday 27 August 202006:00:00Poster
3752XiaofengYangTRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering2155Tuesday 25 August 202000:00:00Poster
3752XiaofengYangTRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering2155Tuesday 25 August 202006:00:00Poster
3764MingfeiHanMining Inter-Video Proposal Relations for Video Object Detection4151Thursday 27 August 202000:00:00Poster
3764MingfeiHanMining Inter-Video Proposal Relations for Video Object Detection4151Thursday 27 August 202006:00:00Poster
3768JieLeiTVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval4359Thursday 27 August 202014:00:00Poster
3768JieLeiTVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval4359Friday 28 August 202000:00:00Poster
3769YingJinMinimum Class Confusion for Versatile Domain Adaptation3117Wednesday 26 August 202000:00:00Poster
3769YingJinMinimum Class Confusion for Versatile Domain Adaptation3117Wednesday 26 August 202006:00:00Poster
3772ManuelLopez AntequeraMapillary Planet-Scale Depth Dataset3197Wednesday 26 August 202006:00:00Oral
3772ManuelLopez AntequeraMapillary Planet-Scale Depth Dataset3197Wednesday 26 August 202014:00:00Oral
3790TongWangLarge Batch Optimization for Object Detection: Training COCO in 12 Minutes2156Tuesday 25 August 202000:00:00Poster
3790TongWangLarge Batch Optimization for Object Detection: Training COCO in 12 Minutes2156Tuesday 25 August 202006:00:00Poster
3792Ram PrabhakarKTowards Practical and Efficient High-Resolution HDR Deghosting with CNN1096Monday 24 August 202006:00:00Poster
3792Ram PrabhakarKTowards Practical and Efficient High-Resolution HDR Deghosting with CNN1096Monday 24 August 202014:00:00Poster
3794DenizBekerMonocular Differentiable Rendering for Self-Supervised 3D Object Detection2157Tuesday 25 August 202000:00:00Poster
3794DenizBekerMonocular Differentiable Rendering for Self-Supervised 3D Object Detection2157Tuesday 25 August 202006:00:00Poster
3796MengTianShape Prior Deformation for Categorical 6D Object Pose and Size Estimation2158Tuesday 25 August 202000:00:00Poster
3796MengTianShape Prior Deformation for Categorical 6D Object Pose and Size Estimation2158Tuesday 25 August 202006:00:00Poster
3801PingLuoDynamic and Static Context-aware LSTM for Multi-agent Motion Prediction2159Tuesday 25 August 202000:00:00Poster
3801PingLuoDynamic and Static Context-aware LSTM for Multi-agent Motion Prediction2159Tuesday 25 August 202006:00:00Poster
3802PeterZhongImage-based table recognition: data, model, and evaluation2160Tuesday 25 August 202000:00:00Poster
3802PeterZhongImage-based table recognition: data, model, and evaluation2160Tuesday 25 August 202006:00:00Poster
3803YuKongGroup Activity Prediction with Sequential Relational Anticipation Model2355Tuesday 25 August 202014:00:00Poster
3803YuKongGroup Activity Prediction with Sequential Relational Anticipation Model2355Wednesday 26 August 202000:00:00Poster
3805HaoranSongPiP: Planning-informed Trajectory Prediction for Autonomous Driving3118Wednesday 26 August 202000:00:00Poster
3805HaoranSongPiP: Planning-informed Trajectory Prediction for Autonomous Driving3118Wednesday 26 August 202006:00:00Poster
3807DuoLiPSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer3119Wednesday 26 August 202000:00:00Poster
3807DuoLiPSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer3119Wednesday 26 August 202006:00:00Poster
3819ZhaominChenHierarchical Context Embedding for Region-based Object Detection2161Tuesday 25 August 202000:00:00Poster
3819ZhaominChenHierarchical Context Embedding for Region-based Object Detection2161Tuesday 25 August 202006:00:00Poster
3822JinYeAttention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition2162Tuesday 25 August 202000:00:00Poster
3822JinYeAttention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition2162Tuesday 25 August 202006:00:00Poster
3830YuliangGuoGen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection4360Thursday 27 August 202014:00:00Poster
3830YuliangGuoGen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection4360Friday 28 August 202000:00:00Poster
3831HongguangZhangFew-shot Action Recognition with Permutation-invariant Attention2163Tuesday 25 August 202000:00:00Spotlight
3831HongguangZhangFew-shot Action Recognition with Permutation-invariant Attention2163Tuesday 25 August 202006:00:00Spotlight
3833XinXiongSparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction3286Wednesday 26 August 202014:00:00Poster
3833XinXiongSparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction3286Thursday 27 August 202000:00:00Poster
3837LinsenSongMEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation2164Tuesday 25 August 202000:00:00Poster
3837LinsenSongMEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation2164Tuesday 25 August 202006:00:00Poster
3838Tsun-HsuanWangV2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction3287Wednesday 26 August 202014:00:00Oral
3838Tsun-HsuanWangV2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction3287Thursday 27 August 202000:00:00Oral
3850Dong-jinKimDetecting Human-Object Interactions with Action Co-occurrence Priors2165Tuesday 25 August 202000:00:00Poster
3850Dong-jinKimDetecting Human-Object Interactions with Action Co-occurrence Priors2165Tuesday 25 August 202006:00:00Poster
3853KunYuanLearning Connectivity of Neural Networks from a Topological Perspective4152Thursday 27 August 202000:00:00Poster
3853KunYuanLearning Connectivity of Neural Networks from a Topological Perspective4152Thursday 27 August 202006:00:00Poster
3867Wei-TingChenJSTASR: Joint Size and Transparency-Aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect Removal2166Tuesday 25 August 202000:00:00Poster
3867Wei-TingChenJSTASR: Joint Size and Transparency-Aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect Removal2166Tuesday 25 August 202006:00:00Poster
3872ZhipengZhangOcean: Object-aware Anchor-free Tracking4153Thursday 27 August 202000:00:00Poster
3872ZhipengZhangOcean: Object-aware Anchor-free Tracking4153Thursday 27 August 202006:00:00Poster
3884YuanLiuObject Tracking using Spatio-Temporal Networks for Future Prediction Location3120Wednesday 26 August 202000:00:00Poster
3884YuanLiuObject Tracking using Spatio-Temporal Networks for Future Prediction Location3120Wednesday 26 August 202006:00:00Poster
3891HaoyuLiangTraining Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters2167Tuesday 25 August 202000:00:00Oral
3891HaoyuLiangTraining Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters2167Tuesday 25 August 202006:00:00Oral
3892JustinSolomonPillar-based Object Detection for Autonomous Driving4361Thursday 27 August 202014:00:00Poster
3892JustinSolomonPillar-based Object Detection for Autonomous Driving4361Friday 28 August 202000:00:00Poster
3902YongZhangSparse Adversarial Attack via Perturbation Factorization2168Tuesday 25 August 202000:00:00Poster
3902YongZhangSparse Adversarial Attack via Perturbation Factorization2168Tuesday 25 August 202006:00:00Poster
3913YoungjaeYuCharacter Grounding and Re-Identification in Story of Videos and Text Descriptions4154Thursday 27 August 202000:00:00Spotlight
3913YoungjaeYuCharacter Grounding and Re-Identification in Story of Videos and Text Descriptions4154Thursday 27 August 202006:00:00Spotlight
3925MaximilianDenninger3D Scene Reconstruction from a Single Viewport3198Wednesday 26 August 202006:00:00Poster
3925MaximilianDenninger3D Scene Reconstruction from a Single Viewport3198Wednesday 26 August 202014:00:00Poster
3935SeongukSeoLearning to Optimize Domain Specific Normalization for Domain Generalization2169Tuesday 25 August 202000:00:00Poster
3935SeongukSeoLearning to Optimize Domain Specific Normalization for Domain Generalization2169Tuesday 25 August 202006:00:00Poster
3937YeYuSelf-supervised Outdoor Scene Relighting4362Thursday 27 August 202014:00:00Poster
3937YeYuSelf-supervised Outdoor Scene Relighting4362Friday 28 August 202000:00:00Poster
3947MikiyaShibuyaPrivacy Preserving Visual SLAM4155Thursday 27 August 202000:00:00Poster
3947MikiyaShibuyaPrivacy Preserving Visual SLAM4155Thursday 27 August 202006:00:00Poster
3948BailinLiEagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning2170Tuesday 25 August 202000:00:00Oral
3948BailinLiEagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning2170Tuesday 25 August 202006:00:00Oral
3951ValentinaSanguinetiLeveraging Acoustic Images for Effective Self-Supervised Audio Representation Learning1097Monday 24 August 202006:00:00Poster
3951ValentinaSanguinetiLeveraging Acoustic Images for Effective Self-Supervised Audio Representation Learning1097Monday 24 August 202014:00:00Poster
3960LorisBazzaniLearning Joint Visual Semantic Matching Embeddings for Language-guided Retrieval1098Monday 24 August 202006:00:00Poster
3960LorisBazzaniLearning Joint Visual Semantic Matching Embeddings for Language-guided Retrieval1098Monday 24 August 202014:00:00Poster
3975Marie-julieRakotosaonaIntrinsic Point Cloud Interpolation via Dual Latent Space Navigation3199Wednesday 26 August 202006:00:00Oral
3975Marie-julieRakotosaonaIntrinsic Point Cloud Interpolation via Dual Latent Space Navigation3199Wednesday 26 August 202014:00:00Oral
3976OrenKatzirCross-Domain Cascaded Deep Translation1099Monday 24 August 202006:00:00Oral
3976OrenKatzirCross-Domain Cascaded Deep Translation1099Monday 24 August 202014:00:00Oral
3977WenshuoMaAABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling3121Wednesday 26 August 202000:00:00Spotlight
3977WenshuoMaAABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling3121Wednesday 26 August 202006:00:00Spotlight
3984MinchulKimLearning Visual Context by Comparison2171Tuesday 25 August 202000:00:00Spotlight
3984MinchulKimLearning Visual Context by Comparison2171Tuesday 25 August 202006:00:00Spotlight
3990HaoangLiGlobally Optimal and Efficient Vanishing Point Estimation in Atlanta World3122Wednesday 26 August 202000:00:00Poster
3990HaoangLiGlobally Optimal and Efficient Vanishing Point Estimation in Atlanta World3122Wednesday 26 August 202006:00:00Poster
3992YuriViazovetskyiStyleGAN2 Distillation for Feed-forward Image~Manipulation1100Monday 24 August 202006:00:00Poster
3992YuriViazovetskyiStyleGAN2 Distillation for Feed-forward Image~Manipulation1100Monday 24 August 202014:00:00Poster
3994AliDibaLarge Scale Holistic Video Understanding4220Thursday 27 August 202006:00:00Spotlight
3994AliDibaLarge Scale Holistic Video Understanding4220Thursday 27 August 202014:00:00Spotlight
3995Krishna KanthNakkaIndirect Local Attacks for Context-aware Semantic Segmentation Networks1101Monday 24 August 202006:00:00Spotlight
3995Krishna KanthNakkaIndirect Local Attacks for Context-aware Semantic Segmentation Networks1101Monday 24 August 202014:00:00Spotlight
3997JinxianLiuSelf-Prediction for Joint Instance and Semantic Segmentation of Point Clouds3288Wednesday 26 August 202014:00:00Poster
3997JinxianLiuSelf-Prediction for Joint Instance and Semantic Segmentation of Point Clouds3288Thursday 27 August 202000:00:00Poster
3999Eduardo HugoSanchezLearning Disentangled Representations via Mutual Information Estimation3200Wednesday 26 August 202006:00:00Poster
3999Eduardo HugoSanchezLearning Disentangled Representations via Mutual Information Estimation3200Wednesday 26 August 202014:00:00Poster
4010LeiLiuChallenge-Aware RGBT Tracking3123Wednesday 26 August 202000:00:00Poster
4010LeiLiuChallenge-Aware RGBT Tracking3123Wednesday 26 August 202006:00:00Poster
4019BrunoLecouatFully Trainable and Interpretable Non-Local Sparse Models for Image Restoration1102Monday 24 August 202006:00:00Poster
4019BrunoLecouatFully Trainable and Interpretable Non-Local Sparse Models for Image Restoration1102Monday 24 August 202014:00:00Poster
4034Harkirat SinghBehlAutoSimulate: (Quickly) Learning Synthetic Data Generation4363Thursday 27 August 202014:00:00Poster
4034Harkirat SinghBehlAutoSimulate: (Quickly) Learning Synthetic Data Generation4363Friday 28 August 202000:00:00Poster
4035XiaotongLuoLatticeNet: Towards Lightweight Image Super-resolution with Lattice Block2172Tuesday 25 August 202000:00:00Poster
4035XiaotongLuoLatticeNet: Towards Lightweight Image Super-resolution with Lattice Block2172Tuesday 25 August 202006:00:00Poster
4042MohsenAliLearning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation3201Wednesday 26 August 202006:00:00Poster
4042MohsenAliLearning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation3201Wednesday 26 August 202014:00:00Poster
4043TatsuroKoizumi"Look Ma, no landmarks!'' -- Unsupervised, Model-based Dense Face Alignment2173Tuesday 25 August 202000:00:00Oral
4043TatsuroKoizumi"Look Ma, no landmarks!'' -- Unsupervised, Model-based Dense Face Alignment2173Tuesday 25 August 202006:00:00Oral
4046HanqingWangActive Visual Information Gathering for Vision-Language Navigation4156Thursday 27 August 202000:00:00Poster
4046HanqingWangActive Visual Information Gathering for Vision-Language Navigation4156Thursday 27 August 202006:00:00Poster
4061YancongLinDeep Hough-Transform Line Priors1103Monday 24 August 202006:00:00Poster
4061YancongLinDeep Hough-Transform Line Priors1103Monday 24 August 202014:00:00Poster
4065KeyangZhouUnsupervised Shape and Pose Disentanglement for 3D Meshes1104Monday 24 August 202006:00:00Poster
4065KeyangZhouUnsupervised Shape and Pose Disentanglement for 3D Meshes1104Monday 24 August 202014:00:00Poster
4066Muhammad ZaighamZaheerCLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection2174Tuesday 25 August 202000:00:00Poster
4066Muhammad ZaighamZaheerCLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection2174Tuesday 25 August 202006:00:00Poster
4072NingYuInclusive GAN: Improving Data and Minority Coverage in Generative Models1105Monday 24 August 202006:00:00Poster
4072NingYuInclusive GAN: Improving Data and Minority Coverage in Generative Models1105Monday 24 August 202014:00:00Poster
4076EvangelosNtavelisSESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects3202Wednesday 26 August 202006:00:00Poster
4076EvangelosNtavelisSESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects3202Wednesday 26 August 202014:00:00Poster
4095RanChenDive Deeper Into Box for Object Detection2175Tuesday 25 August 202000:00:00Poster
4095RanChenDive Deeper Into Box for Object Detection2175Tuesday 25 August 202006:00:00Poster
4097BingyanLiaoPG-Net: Pixel to Global Matching Network for Visual Tracking2176Tuesday 25 August 202000:00:00Poster
4097BingyanLiaoPG-Net: Pixel to Global Matching Network for Visual Tracking2176Tuesday 25 August 202006:00:00Poster
4098TaimoorTariqWhy Are Deep Representations Good Perceptual Quality Features?1106Monday 24 August 202006:00:00Poster
4098TaimoorTariqWhy Are Deep Representations Good Perceptual Quality Features?1106Monday 24 August 202014:00:00Poster
4101AoxiangFanGeometric Estimation via Robust Subspace Recovery3124Wednesday 26 August 202000:00:00Poster
4101AoxiangFanGeometric Estimation via Robust Subspace Recovery3124Wednesday 26 August 202006:00:00Poster
4102SanathNarayanLatent Embedding Feedback and Discriminative Features for Zero-Shot Classification2356Tuesday 25 August 202014:00:00Poster
4102SanathNarayanLatent Embedding Feedback and Discriminative Features for Zero-Shot Classification2356Wednesday 26 August 202000:00:00Poster
4107YangYouHuman Correspondence Consensus for 3D Object Semantic Understanding2177Tuesday 25 August 202000:00:00Poster
4107YangYouHuman Correspondence Consensus for 3D Object Semantic Understanding2177Tuesday 25 August 202006:00:00Poster
4111YubaoSunLearning Memory Augmented Cascading Network for Compressed Sensing of Images4157Thursday 27 August 202000:00:00Poster
4111YubaoSunLearning Memory Augmented Cascading Network for Compressed Sensing of Images4157Thursday 27 August 202006:00:00Poster
4112DizhongZhuLeast squares surface reconstruction on arbitrary domains4364Thursday 27 August 202014:00:00Poster
4112DizhongZhuLeast squares surface reconstruction on arbitrary domains4364Friday 28 August 202000:00:00Poster
4116KieuMyTask-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery1107Monday 24 August 202006:00:00Poster
4116KieuMyTask-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery1107Monday 24 August 202014:00:00Poster
4118JunhuaZouImproving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting4158Thursday 27 August 202000:00:00Poster
4118JunhuaZouImproving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting4158Thursday 27 August 202006:00:00Poster
4120YonggangLiDADA: Differentiable Automatic Data Augmentation2178Tuesday 25 August 202000:00:00Poster
4120YonggangLiDADA: Differentiable Automatic Data Augmentation2178Tuesday 25 August 202006:00:00Poster
4123ArmenAvetisyanSceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans3203Wednesday 26 August 202006:00:00Poster
4123ArmenAvetisyanSceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans3203Wednesday 26 August 202014:00:00Poster
4125WeiWangKinship Identification through Joint Learning using Kinship Verification Ensembles1108Monday 24 August 202006:00:00Poster
4125WeiWangKinship Identification through Joint Learning using Kinship Verification Ensembles1108Monday 24 August 202014:00:00Poster
4152HongjeSeongKernelized Memory Network for Video Object Segmentation3125Wednesday 26 August 202000:00:00Poster
4152HongjeSeongKernelized Memory Network for Video Object Segmentation3125Wednesday 26 August 202006:00:00Poster
4158RémiPautratOnline Invariance Selection for Local Feature Descriptors1109Monday 24 August 202006:00:00Oral
4158RémiPautratOnline Invariance Selection for Local Feature Descriptors1109Monday 24 August 202014:00:00Oral
4160XiaoqiZhaoA Single Stream Network for Robust and Real-time RGB-D Salient Object Detection2179Tuesday 25 August 202000:00:00Poster
4160XiaoqiZhaoA Single Stream Network for Robust and Real-time RGB-D Salient Object Detection2179Tuesday 25 August 202006:00:00Poster
4165JianfeiCaiSplitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation2180Tuesday 25 August 202000:00:00Poster
4165JianfeiCaiSplitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation2180Tuesday 25 August 202006:00:00Poster
4167ZhouRenTemporal Keypoint Matching and Refinement Network for Pose Estimation and Tracking2357Tuesday 25 August 202014:00:00Poster
4167ZhouRenTemporal Keypoint Matching and Refinement Network for Pose Estimation and Tracking2357Wednesday 26 August 202000:00:00Poster
4168ArtemSevastopolskyNeural Point-Based Graphics1110Monday 24 August 202006:00:00Poster
4168ArtemSevastopolskyNeural Point-Based Graphics1110Monday 24 August 202014:00:00Poster
4171BinHeFHDe\textsuperscript{2Net: Full High Definition Demoireing Network3126Wednesday 26 August 202000:00:00Poster
4171BinHeFHDe\textsuperscript{2Net: Full High Definition Demoireing Network3126Wednesday 26 August 202006:00:00Poster
4172DipuManandharLearning Structural Similarity of User Interface Layouts using Graph Networks2358Tuesday 25 August 202014:00:00Poster
4172DipuManandharLearning Structural Similarity of User Interface Layouts using Graph Networks2358Wednesday 26 August 202000:00:00Poster
4174YutaoHuNAS-Count: Counting-by-Density with Neural Architecture Search2181Tuesday 25 August 202000:00:00Poster
4174YutaoHuNAS-Count: Counting-by-Density with Neural Architecture Search2181Tuesday 25 August 202006:00:00Poster
4179HongyuLiuRethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations2182Tuesday 25 August 202000:00:00Oral
4179HongyuLiuRethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations2182Tuesday 25 August 202006:00:00Oral
4185SamuelRota BulòTowards Generalization Across Depth for Monocular 3D Object Detection1111Monday 24 August 202006:00:00Poster
4185SamuelRota BulòTowards Generalization Across Depth for Monocular 3D Object Detection1111Monday 24 August 202014:00:00Poster
4197CorneliuFloreaMargin-Mix: Semi--Supervised Learning for Face Expression Recognition1112Monday 24 August 202006:00:00Poster
4197CorneliuFloreaMargin-Mix: Semi--Supervised Learning for Face Expression Recognition1112Monday 24 August 202014:00:00Poster
4198MarianneBakkenPrincipal Feature Visualisation in Convolutional Neural Networks1113Monday 24 August 202006:00:00Poster
4198MarianneBakkenPrincipal Feature Visualisation in Convolutional Neural Networks1113Monday 24 August 202014:00:00Poster
4211KailiZhaoProgressive Refinement Network for Occluded Pedestrian Detection4159Thursday 27 August 202000:00:00Poster
4211KailiZhaoProgressive Refinement Network for Occluded Pedestrian Detection4159Thursday 27 August 202006:00:00Poster
4214RuilongLiMonocular Real-Time Volumetric Performance Capture2359Thursday 27 August 202014:00:00Poster
4214RuilongLiMonocular Real-Time Volumetric Performance Capture2359Friday 28 August 202000:00:00Poster
4217ChristianErtlerThe Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale1114Monday 24 August 202006:00:00Poster
4217ChristianErtlerThe Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale1114Monday 24 August 202014:00:00Poster
4220AnilArmaganMeasuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction2360Tuesday 25 August 202014:00:00Poster
4220AnilArmaganMeasuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction2360Wednesday 26 August 202000:00:00Poster
4234NengliLimDisentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders2183Tuesday 25 August 202000:00:00Poster
4234NengliLimDisentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders2183Tuesday 25 August 202006:00:00Poster
4238Van NhanNguyenSEN: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-Shot Learning Networks3204Wednesday 26 August 202006:00:00Poster
4238Van NhanNguyenSEN: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-Shot Learning Networks3204Wednesday 26 August 202014:00:00Poster
4241GarrickBrazilKinematic 3D Object Detection in Monocular Video4365Thursday 27 August 202014:00:00Poster
4241GarrickBrazilKinematic 3D Object Detection in Monocular Video4365Friday 28 August 202000:00:00Poster
4257YeZhuDescribing Unseen Videos via Multi-Modal Cooperative Dialog Agents4366Thursday 27 August 202014:00:00Poster
4257YeZhuDescribing Unseen Videos via Multi-Modal Cooperative Dialog Agents4366Friday 28 August 202000:00:00Poster
4270SangminLeeSACA Net: Cybersickness Assessment of Individual Viewers for VR Content via Graph-based Symptom Relation Embedding4160Thursday 27 August 202000:00:00Poster
4270SangminLeeSACA Net: Cybersickness Assessment of Individual Viewers for VR Content via Graph-based Symptom Relation Embedding4160Thursday 27 August 202006:00:00Poster
4272XinYuanEnd-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention3289Wednesday 26 August 202014:00:00Poster
4272XinYuanEnd-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention3289Thursday 27 August 202000:00:00Poster
4294AnitaRauPredicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings4367Thursday 27 August 202014:00:00Spotlight
4294AnitaRauPredicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings4367Friday 28 August 202000:00:00Spotlight
4296JordiPont-TusetConnecting Vision and Language with Localized Narratives1115Monday 24 August 202006:00:00Spotlight
4296JordiPont-TusetConnecting Vision and Language with Localized Narratives1115Monday 24 August 202014:00:00Spotlight
4297GoutamBhatKnow Your Surroundings: Exploiting Scene Information for Object Tracking4221Thursday 27 August 202006:00:00Poster
4297GoutamBhatKnow Your Surroundings: Exploiting Scene Information for Object Tracking4221Thursday 27 August 202014:00:00Poster
4298RenWangPractical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases3290Wednesday 26 August 202014:00:00Poster
4298RenWangPractical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases3290Thursday 27 August 202000:00:00Poster
4300YiruiWangAnatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images3291Wednesday 26 August 202014:00:00Poster
4300YiruiWangAnatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images3291Thursday 27 August 202000:00:00Poster
4302RomanSuvorovDeepLandscape: Adversarial Modeling of Landscape Videos3205Wednesday 26 August 202006:00:00Poster
4302RomanSuvorovDeepLandscape: Adversarial Modeling of Landscape Videos3205Wednesday 26 August 202014:00:00Poster
4304LeiKangGANwriting: Content-Conditioned Generation of Styled Handwritten Word Images1116Monday 24 August 202006:00:00Poster
4304LeiKangGANwriting: Content-Conditioned Generation of Styled Handwritten Word Images1116Monday 24 August 202014:00:00Poster
4306YingqianWangSpatial-Angular Interaction for Light Field Image Super-Resolution3127Wednesday 26 August 202000:00:00Poster
4306YingqianWangSpatial-Angular Interaction for Light Field Image Super-Resolution3127Wednesday 26 August 202006:00:00Poster
4314AdrianBulatBATS: Binary ArchitecTure Search4368Thursday 27 August 202014:00:00Poster
4314AdrianBulatBATS: Binary ArchitecTure Search4368Friday 28 August 202000:00:00Poster
4319HanHuA Closer Look at Local Aggregation Operators in Point Cloud Analysis2184Tuesday 25 August 202000:00:00Poster
4319HanHuA Closer Look at Local Aggregation Operators in Point Cloud Analysis2184Tuesday 25 August 202006:00:00Poster
4322YoussefAlami MejjatiLook here! A parametric learning based approach to redirect visual attention2361Tuesday 25 August 202014:00:00Poster
4322YoussefAlami MejjatiLook here! A parametric learning based approach to redirect visual attention2361Wednesday 26 August 202000:00:00Poster
4324HenryLiVariational Diffusion Autoencoders with Random Walk Sampling3292Wednesday 26 August 202014:00:00Poster
4324HenryLiVariational Diffusion Autoencoders with Random Walk Sampling3292Thursday 27 August 202000:00:00Poster
4328XinWenAdaptive Variance Based Label Distribution Learning For Facial Age Estimation3128Wednesday 26 August 202000:00:00Poster
4328XinWenAdaptive Variance Based Label Distribution Learning For Facial Age Estimation3128Wednesday 26 August 202006:00:00Poster
4334ShashaLiConnecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency4369Thursday 27 August 202014:00:00Poster
4334ShashaLiConnecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency4369Friday 28 August 202000:00:00Poster
4342AbbasSadatPerceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations4370Thursday 27 August 202014:00:00Poster
4342AbbasSadatPerceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations4370Friday 28 August 202000:00:00Poster
4350SangeekHyunVarSR: Variational Super-Resolution Network for Very Low Resolution Images2185Tuesday 25 August 202000:00:00Poster
4350SangeekHyunVarSR: Variational Super-Resolution Network for Very Low Resolution Images2185Tuesday 25 August 202006:00:00Poster
4353AdamHarrisonCo-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation1181Monday 24 August 202014:00:00Poster
4353AdamHarrisonCo-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation1181Tuesday 25 August 202000:00:00Poster
4355MassimilianoManciniTowards Recognizing Unseen Categories in Unseen Domains3206Wednesday 26 August 202006:00:00Poster
4355MassimilianoManciniTowards Recognizing Unseen Categories in Unseen Domains3206Wednesday 26 August 202014:00:00Poster
4358OleksiiSidorovTextCaps: a Dataset for Image Captioning with Reading Comprehension4371Thursday 27 August 202014:00:00Oral
4358OleksiiSidorovTextCaps: a Dataset for Image Captioning with Reading Comprehension4371Friday 28 August 202000:00:00Oral
4362francescocroceSquare Attack: a query-efficient black-box adversarial attack via random search1117Monday 24 August 202006:00:00Poster
4362francescocroceSquare Attack: a query-efficient black-box adversarial attack via random search1117Monday 24 August 202014:00:00Poster
4363NoeSamanoYou Are Here: Geolocation by Embedding Maps and Images2362Tuesday 25 August 202014:00:00Poster
4363NoeSamanoYou Are Here: Geolocation by Embedding Maps and Images2362Wednesday 26 August 202000:00:00Poster
4364YangHeSegmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation1118Monday 24 August 202006:00:00Poster
4364YangHeSegmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation1118Monday 24 August 202014:00:00Poster
4366RobertCollinsFrom Image to Stability: Learning Dynamics from Human Pose4372Thursday 27 August 202014:00:00Poster
4366RobertCollinsFrom Image to Stability: Learning Dynamics from Human Pose4372Friday 28 August 202000:00:00Poster
4368NamdarHomayounfarLevelSet R-CNN: A Deep Variational Method for Instance Segmentation3293Wednesday 26 August 202014:00:00Poster
4368NamdarHomayounfarLevelSet R-CNN: A Deep Variational Method for Instance Segmentation3293Thursday 27 August 202000:00:00Poster
4374XianzhiDuEfficient Scale-Permuted Backbone with Learned Resource Distribution3294Wednesday 26 August 202014:00:00Poster
4374XianzhiDuEfficient Scale-Permuted Backbone with Learned Resource Distribution3294Thursday 27 August 202000:00:00Poster
4375YangHuaReducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature Learning3295Wednesday 26 August 202014:00:00Poster
4375YangHuaReducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature Learning3295Thursday 27 August 202000:00:00Poster
4377AlirezaZareianBridging Knowledge Graphs to Generate Scene Graphs1182Monday 24 August 202014:00:00Poster
4377AlirezaZareianBridging Knowledge Graphs to Generate Scene Graphs1182Tuesday 25 August 202000:00:00Poster
4383KaidiXuAdversarial T-shirt! Evading Person Detectors in A Physical World2363Tuesday 25 August 202014:00:00Spotlight
4383KaidiXuAdversarial T-shirt! Evading Person Detectors in A Physical World2363Wednesday 26 August 202000:00:00Spotlight
4386SimonSuoImplicit Latent Variable Model for Scene-Consistent Motion Forecasting4373Thursday 27 August 202014:00:00Poster
4386SimonSuoImplicit Latent Variable Model for Scene-Consistent Motion Forecasting4373Friday 28 August 202000:00:00Poster
4387AlirezaZareianLearning Visual Commonsense for Robust Scene Graph Generation4374Thursday 27 August 202014:00:00Poster
4387AlirezaZareianLearning Visual Commonsense for Robust Scene Graph Generation4374Friday 28 August 202000:00:00Poster
4396NicolasAstorga RochaMPCC: Matching Priors and Conditionals for Clustering2364Tuesday 25 August 202014:00:00Poster
4396NicolasAstorga RochaMPCC: Matching Priors and Conditionals for Clustering2364Wednesday 26 August 202000:00:00Poster
4404ShoInayoshiBounding-box Channels for Visual Relationship Detection4161Thursday 27 August 202000:00:00Spotlight
4404ShoInayoshiBounding-box Channels for Visual Relationship Detection4161Thursday 27 August 202006:00:00Spotlight
4405TianGuoEfficient Lighting Estimation for Mobile Augmented Reality2365Tuesday 25 August 202014:00:00Poster
4405TianGuoEfficient Lighting Estimation for Mobile Augmented Reality2365Wednesday 26 August 202000:00:00Poster
4407ZuzanaKukelovaMinimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion1119Monday 24 August 202006:00:00Spotlight
4407ZuzanaKukelovaMinimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion1119Monday 24 August 202014:00:00Spotlight
4408RomanKlokovDiscrete Point Flow Networks for Efficient Point Cloud Generation1120Monday 24 August 202006:00:00Poster
4408RomanKlokovDiscrete Point Flow Networks for Efficient Point Cloud Generation1120Monday 24 August 202014:00:00Poster
4410ZhuoningYuanAccelerating Deep Learning with Millions of Classes4375Thursday 27 August 202014:00:00Poster
4410ZhuoningYuanAccelerating Deep Learning with Millions of Classes4375Friday 28 August 202000:00:00Poster
4416XiuyeGuPassword-conditioned Anonymization and Deanonymization with Face Identity Transformers1183Monday 24 August 202014:00:00Poster
4416XiuyeGuPassword-conditioned Anonymization and Deanonymization with Face Identity Transformers1183Tuesday 25 August 202000:00:00Poster
4421SizhuoMaInertial Safety from Structured Light2366Tuesday 25 August 202014:00:00Poster
4421SizhuoMaInertial Safety from Structured Light2366Wednesday 26 August 202000:00:00Poster
4423KarttikeyaMangalamIt is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction4376Thursday 27 August 202014:00:00Oral
4423KarttikeyaMangalamIt is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction4376Friday 28 August 202000:00:00Oral
4424NicholasSharpPointTriNet: Learned Triangulation of 3D Point Sets4377Thursday 27 August 202014:00:00Poster
4424NicholasSharpPointTriNet: Learned Triangulation of 3D Point Sets4377Friday 28 August 202000:00:00Poster
4433Huy V.VoToward Unsupervised, Multi-Object Discovery in Large-Scale Image Collections1121Monday 24 August 202006:00:00Poster
4433Huy V.VoToward Unsupervised, Multi-Object Discovery in Large-Scale Image Collections1121Monday 24 August 202014:00:00Poster
4440FelixJäremo LawinLearning What to Learn for Video Object Segmentation3207Wednesday 26 August 202006:00:00Oral
4440FelixJäremo LawinLearning What to Learn for Video Object Segmentation3207Wednesday 26 August 202014:00:00Oral
4442AndreasLugmayrSRFlow: Learning the Super-Resolution Space with Normalizing Flow2258Tuesday 25 August 202006:00:00Spotlight
4442AndreasLugmayrSRFlow: Learning the Super-Resolution Space with Normalizing Flow2258Tuesday 25 August 202014:00:00Spotlight
4452WentaoYuanDeepGMR: Learning Latent Gaussian Mixture Models for Registration4378Thursday 27 August 202014:00:00Spotlight
4452WentaoYuanDeepGMR: Learning Latent Gaussian Mixture Models for Registration4378Friday 28 August 202000:00:00Spotlight
4458SiddharthAnchaActive Perception using Light Curtains for Autonomous Driving4379Thursday 27 August 202014:00:00Spotlight
4458SiddharthAnchaActive Perception using Light Curtains for Autonomous Driving4379Friday 28 August 202000:00:00Spotlight
4474ZhenboSongDeep Novel View Synthesis from Colored 3D Point Clouds2186Tuesday 25 August 202000:00:00Poster
4474ZhenboSongDeep Novel View Synthesis from Colored 3D Point Clouds2186Tuesday 25 August 202006:00:00Poster
4495HaoranWangConsensus-Aware Visual-Semantic Embedding for Image-Text Matching4162Thursday 27 August 202000:00:00Poster
4495HaoranWangConsensus-Aware Visual-Semantic Embedding for Image-Text Matching4162Thursday 27 August 202006:00:00Poster
4499YueyiZhangSpatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising4163Thursday 27 August 202000:00:00Poster
4499YueyiZhangSpatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising4163Thursday 27 August 202006:00:00Poster
4510SongtaoHeRoad Graph Extraction through Graph-Tensor Encoding4380Thursday 27 August 202014:00:00Poster
4510SongtaoHeRoad Graph Extraction through Graph-Tensor Encoding4380Friday 28 August 202000:00:00Poster
4513DiHuCross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition4164Thursday 27 August 202000:00:00Poster
4513DiHuCross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition4164Thursday 27 August 202006:00:00Poster
4521ZheChenInvertible Neural BRDF for Object Inverse Rendering4165Thursday 27 August 202000:00:00Spotlight
4521ZheChenInvertible Neural BRDF for Object Inverse Rendering4165Thursday 27 August 202006:00:00Spotlight
4522JinyuZhaoPolarimetric Multi-View Inverse Rendering3129Wednesday 26 August 202000:00:00Poster
4522JinyuZhaoPolarimetric Multi-View Inverse Rendering3129Wednesday 26 August 202006:00:00Poster
4524AlexanderBinderSideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information3130Wednesday 26 August 202000:00:00Poster
4524AlexanderBinderSideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information3130Wednesday 26 August 202006:00:00Poster
4531AruniRoyChowdhuryImproving Face Recognition by Clustering Unlabeled Faces in the Wild4381Thursday 27 August 202014:00:00Poster
4531AruniRoyChowdhuryImproving Face Recognition by Clustering Unlabeled Faces in the Wild4381Friday 28 August 202000:00:00Poster
4532PulakPurkaitNeuRoRA: Neural Robust Rotation Averaging4166Thursday 27 August 202000:00:00Poster
4532PulakPurkaitNeuRoRA: Neural Robust Rotation Averaging4166Thursday 27 August 202006:00:00Poster
4535IanReidSG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes2187Tuesday 25 August 202000:00:00Poster
4535IanReidSG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes2187Tuesday 25 August 202006:00:00Poster
4544WoobinImUnsupervised Learning of Optical Flow with Deep Feature Similarity2188Tuesday 25 August 202000:00:00Poster
4544WoobinImUnsupervised Learning of Optical Flow with Deep Feature Similarity2188Tuesday 25 August 202006:00:00Poster
4545WengfengLuoSemi-supervised Semantic Segmentation via Strong-weak Dual-branch Network2189Tuesday 25 August 202000:00:00Spotlight
4545WengfengLuoSemi-supervised Semantic Segmentation via Strong-weak Dual-branch Network2189Tuesday 25 August 202006:00:00Spotlight
4548XiaomeiZhangBlended Grammar Network for Human Parsing3131Wednesday 26 August 202000:00:00Poster
4548XiaomeiZhangBlended Grammar Network for Human Parsing3131Wednesday 26 August 202006:00:00Poster
4549ZehaoYuP$^{2$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation3132Wednesday 26 August 202000:00:00Poster
4549ZehaoYuP$^{2$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation3132Wednesday 26 August 202006:00:00Poster
4553MasanoriSuganumaEfficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs2190Tuesday 25 August 202000:00:00Poster
4553MasanoriSuganumaEfficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs2190Tuesday 25 August 202006:00:00Poster
4571YuzhiWangPractical Deep Raw Image Denoising on Mobile Devices4167Thursday 27 August 202000:00:00Spotlight
4571YuzhiWangPractical Deep Raw Image Denoising on Mobile Devices4167Thursday 27 August 202006:00:00Spotlight
4577ChanganChenSoundSpaces: Audio-Visual Navigation in 3D Environments3296Wednesday 26 August 202014:00:00Spotlight
4577ChanganChenSoundSpaces: Audio-Visual Navigation in 3D Environments3296Thursday 27 August 202000:00:00Spotlight
4582XiyangLiuAdaptive Mixture Regression Network with Local Counting Map for Crowd Counting2191Tuesday 25 August 202000:00:00Poster
4582XiyangLiuAdaptive Mixture Regression Network with Local Counting Map for Crowd Counting2191Tuesday 25 August 202006:00:00Poster
4583ZihengChengBIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging3297Wednesday 26 August 202014:00:00Poster
4583ZihengChengBIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging3297Thursday 27 August 202000:00:00Poster
4584ZequnQinUltra Fast Structure-aware Deep Lane Detection2192Tuesday 25 August 202000:00:00Poster
4584ZequnQinUltra Fast Structure-aware Deep Lane Detection2192Tuesday 25 August 202006:00:00Poster
4585SubinJeonCross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling4168Thursday 27 August 202000:00:00Poster
4585SubinJeonCross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling4168Thursday 27 August 202006:00:00Poster
4600ZhenweiHeDomain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN3133Wednesday 26 August 202000:00:00Poster
4600ZhenweiHeDomain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN3133Wednesday 26 August 202006:00:00Poster
4602YuanhaoZhaiTwo-Stream Consensus Network for Weakly-Supervised Temporal Action Localization2193Tuesday 25 August 202000:00:00Spotlight
4602YuanhaoZhaiTwo-Stream Consensus Network for Weakly-Supervised Temporal Action Localization2193Tuesday 25 August 202006:00:00Spotlight
4614ZhenLeiExclusivity-Consistency Regularized Knowledge Distillation for Face Recognition3134Wednesday 26 August 202000:00:00Poster
4614ZhenLeiExclusivity-Consistency Regularized Knowledge Distillation for Face Recognition3134Wednesday 26 August 202006:00:00Poster
4617Hwann-TzongChenLearning Camera-Aware Noise Models2194Tuesday 25 August 202000:00:00Poster
4617Hwann-TzongChenLearning Camera-Aware Noise Models2194Tuesday 25 August 202006:00:00Poster
4619OshriHalimiTowards Precise Completion of Deformable Shapes3208Wednesday 26 August 202006:00:00Poster
4619OshriHalimiTowards Precise Completion of Deformable Shapes3208Wednesday 26 August 202014:00:00Poster
4625JiahaoLiIterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration4382Thursday 27 August 202014:00:00Poster
4625JiahaoLiIterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration4382Friday 28 August 202000:00:00Poster
4628AmirrezaShabanPairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization3298Wednesday 26 August 202014:00:00Poster
4628AmirrezaShabanPairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization3298Thursday 27 August 202000:00:00Poster
4629XinWangEnvironment-agnostic Multitask Learning for Natural Language Grounded Navigation4383Thursday 27 August 202014:00:00Poster
4629XinWangEnvironment-agnostic Multitask Learning for Natural Language Grounded Navigation4383Friday 28 August 202000:00:00Poster
4631ChaoLiTPFN: Applying Outer Product along Time to Multimodal Sentiment Analysis Fusion on Incomplete Data3135Wednesday 26 August 202000:00:00Poster
4631ChaoLiTPFN: Applying Outer Product along Time to Multimodal Sentiment Analysis Fusion on Incomplete Data3135Wednesday 26 August 202006:00:00Poster
4637Eu WernTehProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis4384Thursday 27 August 202014:00:00Poster
4637Eu WernTehProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis4384Friday 28 August 202000:00:00Poster
4644DohyungKimLearning with Privileged Information for Efficient Image Super-Resolution4169Thursday 27 August 202000:00:00Poster
4644DohyungKimLearning with Privileged Information for Efficient Image Super-Resolution4169Thursday 27 August 202006:00:00Poster
4652ShiliangZhangJoint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification2195Tuesday 25 August 202000:00:00Poster
4652ShiliangZhangJoint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification2195Tuesday 25 August 202006:00:00Poster
4655MingeunKangAutoencoder-based Graph Construction for Semi-supervised Learning2196Tuesday 25 August 202000:00:00Poster
4655MingeunKangAutoencoder-based Graph Construction for Semi-supervised Learning2196Tuesday 25 August 202006:00:00Poster
4670AbhijitKunduVirtual Multi-view Fusion for 3D Semantic Segmentation3299Wednesday 26 August 202014:00:00Poster
4670AbhijitKunduVirtual Multi-view Fusion for 3D Semantic Segmentation3299Thursday 27 August 202000:00:00Poster
4672KeChengDecoupling GCN with DropGraph Module for Skeleton-Based Action Recognition3136Wednesday 26 August 202000:00:00Poster
4672KeChengDecoupling GCN with DropGraph Module for Skeleton-Based Action Recognition3136Wednesday 26 August 202006:00:00Poster
4676AchutaKadambiDeep Shape from Polarization4385Thursday 27 August 202014:00:00Poster
4676AchutaKadambiDeep Shape from Polarization4385Friday 28 August 202000:00:00Poster
4677LyminZhangErasing Appearance Preservation in Optimization-based Smoothing2197Tuesday 25 August 202000:00:00Spotlight
4677LyminZhangErasing Appearance Preservation in Optimization-based Smoothing2197Tuesday 25 August 202006:00:00Spotlight
4682XuguangLanA Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning3137Wednesday 26 August 202000:00:00Poster
4682XuguangLanA Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning3137Wednesday 26 August 202006:00:00Poster
4690JianfeiYangMind the Discriminability: Asymmetric Adversarial Domain Adaptation2198Tuesday 25 August 202000:00:00Poster
4690JianfeiYangMind the Discriminability: Asymmetric Adversarial Domain Adaptation2198Tuesday 25 August 202006:00:00Poster
4694YushenLiuSeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates4170Thursday 27 August 202000:00:00Poster
4694YushenLiuSeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates4170Thursday 27 August 202006:00:00Poster
4727Tsu-JuiFuCounterfactual Vision-and-Language Navigation via Adversarial Path Sampler2367Tuesday 25 August 202014:00:00Spotlight
4727Tsu-JuiFuCounterfactual Vision-and-Language Navigation via Adversarial Path Sampler2367Wednesday 26 August 202000:00:00Spotlight
4729ShiJieSunSimultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking2199Tuesday 25 August 202000:00:00Poster
4729ShiJieSunSimultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking2199Tuesday 25 August 202006:00:00Poster
4732GarvitaTiwariSIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing3209Wednesday 26 August 202006:00:00Oral
4732GarvitaTiwariSIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing3209Wednesday 26 August 202014:00:00Oral
4736FeihuZhangDeep FusionNet for Point Cloud Semantic Segmentation4386Thursday 27 August 202014:00:00Poster
4736FeihuZhangDeep FusionNet for Point Cloud Semantic Segmentation4386Friday 28 August 202000:00:00Poster
4749TatsumiUezatoGuided Deep Decoder: Unsupervised Image Pair Fusion4171Thursday 27 August 202000:00:00Spotlight
4749TatsumiUezatoGuided Deep Decoder: Unsupervised Image Pair Fusion4171Thursday 27 August 202006:00:00Spotlight
4750BichuanGuoDeep Material Recognition in Light-Fields via Disentanglement of Spatial and Angular Information2200Tuesday 25 August 202000:00:00Poster
4750BichuanGuoDeep Material Recognition in Light-Fields via Disentanglement of Spatial and Angular Information2200Tuesday 25 August 202006:00:00Poster
4757YuexiangLiDual Adversarial Network for Deep Active Learning4172Thursday 27 August 202000:00:00Poster
4757YuexiangLiDual Adversarial Network for Deep Active Learning4172Thursday 27 August 202006:00:00Poster
4763Ka LeongChengFully Convolutional Networks for Continuous Sign Language Recognition3138Wednesday 26 August 202000:00:00Poster
4763Ka LeongChengFully Convolutional Networks for Continuous Sign Language Recognition3138Wednesday 26 August 202006:00:00Poster
4771MatteoPoggiSelf-adapting confidence estimation for stereo1122Monday 24 August 202006:00:00Poster
4771MatteoPoggiSelf-adapting confidence estimation for stereo1122Monday 24 August 202014:00:00Poster
4793QueweiLiDeep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention3139Wednesday 26 August 202000:00:00Poster
4793QueweiLiDeep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention3139Wednesday 26 August 202006:00:00Poster
4796QuanmingYaoAutoSTR: Efficient Backbone Search for Scene Text Recognition3140Wednesday 26 August 202000:00:00Poster
4796QuanmingYaoAutoSTR: Efficient Backbone Search for Scene Text Recognition3140Wednesday 26 August 202006:00:00Poster
4802SungwonHanMitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification3141Wednesday 26 August 202000:00:00Poster
4802SungwonHanMitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification3141Wednesday 26 August 202006:00:00Poster
4809JonghwaYimFilter Style Transfer between Photos4173Thursday 27 August 202000:00:00Spotlight
4809JonghwaYimFilter Style Transfer between Photos4173Thursday 27 August 202006:00:00Spotlight
4810JianshengChenAdversarial Training with Bi-directional Likelihood Regularization for Visual Classification2201Tuesday 25 August 202000:00:00Poster
4810JianshengChenAdversarial Training with Bi-directional Likelihood Regularization for Visual Classification2201Tuesday 25 August 202006:00:00Poster
4830RyuichiroHatayaLearning Augmentation Strategies Using Backpropagation3142Wednesday 26 August 202000:00:00Poster
4830RyuichiroHatayaLearning Augmentation Strategies Using Backpropagation3142Wednesday 26 August 202006:00:00Poster
4836LinHuangHand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation4387Thursday 27 August 202014:00:00Poster
4836LinHuangHand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation4387Friday 28 August 202000:00:00Poster
4845ZhenzhiWangBoundary-Aware Cascade Networks for Temporal Action Segmentation4174Thursday 27 August 202000:00:00Poster
4845ZhenzhiWangBoundary-Aware Cascade Networks for Temporal Action Segmentation4174Thursday 27 August 202006:00:00Poster
4860LinpuFangJGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image1123Monday 24 August 202006:00:00Spotlight
4860LinpuFangJGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image1123Monday 24 August 202014:00:00Spotlight
4865WeibingZhaoTowards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation4175Thursday 27 August 202000:00:00Poster
4865WeibingZhaoTowards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation4175Thursday 27 August 202006:00:00Poster
4866LucaCosmoLIMP: Learning Latent Shape Representations with Metric Preservation Priors1124Tuesday 25 August 202006:00:00Oral
4866LucaCosmoLIMP: Learning Latent Shape Representations with Metric Preservation Priors1124Tuesday 25 August 202014:00:00Oral
4867ZhuoSuDynamic Group Convolution for Accelerating Convolutional Neural Networks1125Monday 24 August 202006:00:00Spotlight
4867ZhuoSuDynamic Group Convolution for Accelerating Convolutional Neural Networks1125Monday 24 August 202014:00:00Spotlight
4871YaelKonfortiInference Graphs for CNN Interpretation1126Monday 24 August 202006:00:00Poster
4871YaelKonfortiInference Graphs for CNN Interpretation1126Monday 24 August 202014:00:00Poster
4879LiangchengLiAn End-to-End OCR Text Re-organization Sequence Learning for Rich-text Detail Image Comprehension4176Thursday 27 August 202000:00:00Poster
4879LiangchengLiAn End-to-End OCR Text Re-organization Sequence Learning for Rich-text Detail Image Comprehension4176Thursday 27 August 202006:00:00Poster
4880YaoxiongHuangRD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering2202Tuesday 25 August 202000:00:00Spotlight
4880YaoxiongHuangRD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering2202Tuesday 25 August 202006:00:00Spotlight
4889YangBaiImproving Query Efficiency of Black-box Adversarial Attack4177Thursday 27 August 202000:00:00Poster
4889YangBaiImproving Query Efficiency of Black-box Adversarial Attack4177Thursday 27 August 202006:00:00Poster
4890Hsien-TzuChengSelf-similarity Student for Partial Label Histopathology Image Segmentation3143Wednesday 26 August 202000:00:00Poster
4890Hsien-TzuChengSelf-similarity Student for Partial Label Histopathology Image Segmentation3143Wednesday 26 August 202006:00:00Poster
4912ArslanAliBioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions4222Thursday 27 August 202006:00:00Poster
4912ArslanAliBioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions4222Thursday 27 August 202014:00:00Poster
4913ZhetongLiangA Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images2203Tuesday 25 August 202000:00:00Poster
4913ZhetongLiangA Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images2203Tuesday 25 August 202006:00:00Poster
4920YunjaeJungGlobal-and-Local Relative Position Embedding for Unsupervised Video Summarization3144Wednesday 26 August 202000:00:00Poster
4920YunjaeJungGlobal-and-Local Relative Position Embedding for Unsupervised Video Summarization3144Wednesday 26 August 202006:00:00Poster
4924SunghyunChoReal-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms2204Tuesday 25 August 202000:00:00Poster
4924SunghyunChoReal-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms2204Tuesday 25 August 202006:00:00Poster
4927GuoQingSPARK: Spatial-aware Online Incremental Attack Against Visual Tracking4178Thursday 27 August 202000:00:00Poster
4927GuoQingSPARK: Spatial-aware Online Incremental Attack Against Visual Tracking4178Thursday 27 August 202006:00:00Poster
4943ZhujunXuCenterNet Heatmap Propagation for Real-time Video Object Detection1127Monday 24 August 202006:00:00Poster
4943ZhujunXuCenterNet Heatmap Propagation for Real-time Video Object Detection1127Monday 24 August 202014:00:00Poster
4959YouweiPangHierarchical Dynamic Filtering Network for RGB-D Salient Object Detection3145Wednesday 26 August 202000:00:00Poster
4959YouweiPangHierarchical Dynamic Filtering Network for RGB-D Salient Object Detection3145Wednesday 26 August 202006:00:00Poster
4963VasileiosBalntasSOLAR: Second-Order Loss and Attention for Image Retrieval4388Thursday 27 August 202014:00:00Poster
4963VasileiosBalntasSOLAR: Second-Order Loss and Attention for Image Retrieval4388Friday 28 August 202000:00:00Poster
4964GuoleiSunFixing Localization Errors to Improve Image Classification3210Wednesday 26 August 202006:00:00Poster
4964GuoleiSunFixing Localization Errors to Improve Image Classification3210Wednesday 26 August 202014:00:00Poster
4968DagmarKainmuellerPatchPerPix for Instance Segmentation1128Monday 24 August 202006:00:00Poster
4968DagmarKainmuellerPatchPerPix for Instance Segmentation1128Monday 24 August 202014:00:00Poster
4997SoroushSeifiAttend and Segment: Attention Guided Active Semantic Segmentation1129Monday 24 August 202006:00:00Poster
4997SoroushSeifiAttend and Segment: Attention Guided Active Semantic Segmentation1129Monday 24 August 202014:00:00Poster
5004JianleiYangAccelerating CNN Training by Pruning Activation Gradients3146Wednesday 26 August 202000:00:00Poster
5004JianleiYangAccelerating CNN Training by Pruning Activation Gradients3146Wednesday 26 August 202006:00:00Poster
5010HanulKimGlobal and Local Enhancement Networks for Paired and Unpaired Image Enhancement4179Thursday 27 August 202000:00:00Poster
5010HanulKimGlobal and Local Enhancement Networks for Paired and Unpaired Image Enhancement4179Thursday 27 August 202006:00:00Poster
5021YuhuiYuanObject-Contextual Representations for Semantic Segmentation3147Wednesday 26 August 202000:00:00Spotlight
5021YuhuiYuanObject-Contextual Representations for Semantic Segmentation3147Wednesday 26 August 202006:00:00Spotlight
5041KangKimProbabilistic Anchor Assignment with IoU Prediction for Object Detection2205Tuesday 25 August 202000:00:00Poster
5041KangKimProbabilistic Anchor Assignment with IoU Prediction for Object Detection2205Tuesday 25 August 202006:00:00Poster
5056YatingWangEyeglasses 3D shape reconstruction from a single face image2206Tuesday 25 August 202000:00:00Poster
5056YatingWangEyeglasses 3D shape reconstruction from a single face image2206Tuesday 25 August 202006:00:00Poster
5061RuibingHouTemporal Complementary Learning for Video Person Re-Identification2207Tuesday 25 August 202000:00:00Poster
5061RuibingHouTemporal Complementary Learning for Video Person Re-Identification2207Tuesday 25 August 202006:00:00Poster
5063NerminSametHoughNet: Integrating near and long-range evidence for bottom-up object detection1130Monday 24 August 202006:00:00Poster
5063NerminSametHoughNet: Integrating near and long-range evidence for bottom-up object detection1130Monday 24 August 202014:00:00Poster
5066XueyaZhangGraph Wasserstein Correlation Analysis for Movie Retrieval2208Tuesday 25 August 202000:00:00Poster
5066XueyaZhangGraph Wasserstein Correlation Analysis for Movie Retrieval2208Tuesday 25 August 202006:00:00Poster
5068JianchaoWuContext-Aware RCNN: A Baseline for Action Detection in Videos4180Thursday 27 August 202000:00:00Poster
5068JianchaoWuContext-Aware RCNN: A Baseline for Action Detection in Videos4180Thursday 27 August 202006:00:00Poster
5090NingLiFull-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of Polarization3211Wednesday 26 August 202006:00:00Poster
5090NingLiFull-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of Polarization3211Wednesday 26 August 202014:00:00Poster
5095HaoxianZhangA Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation2209Tuesday 25 August 202000:00:00Poster
5095HaoxianZhangA Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation2209Tuesday 25 August 202006:00:00Poster
5099Syed WaqasZamirLearning Enriched Features for Real Image Restoration and Enhancement4389Thursday 27 August 202014:00:00Poster
5099Syed WaqasZamirLearning Enriched Features for Real Image Restoration and Enhancement4389Friday 28 August 202000:00:00Poster
5105WenxiaoZhangDetail Preserved Point Cloud Completion via Separated Feature Aggregation4181Thursday 27 August 202000:00:00Poster
5105WenxiaoZhangDetail Preserved Point Cloud Completion via Separated Feature Aggregation4181Thursday 27 August 202006:00:00Poster
5115MiaoHaoLabelEnc: A New Intermediate Supervision Method for Object Detection2210Tuesday 25 August 202000:00:00Poster
5115MiaoHaoLabelEnc: A New Intermediate Supervision Method for Object Detection2210Tuesday 25 August 202006:00:00Poster
5116ZhihangZhongEfficient Spatio-Temporal Recurrent Neural Network for Video Deblurring4182Thursday 27 August 202000:00:00Spotlight
5116ZhihangZhongEfficient Spatio-Temporal Recurrent Neural Network for Video Deblurring4182Thursday 27 August 202006:00:00Spotlight
5118ClaraFernandez-LabradorUnsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets1131Monday 24 August 202006:00:00Poster
5118ClaraFernandez-LabradorUnsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets1131Monday 24 August 202014:00:00Poster
5130HuixiaLiPAMS: Quantized Super-Resolution via Parameterized Max Scale2211Tuesday 25 August 202000:00:00Poster
5130HuixiaLiPAMS: Quantized Super-Resolution via Parameterized Max Scale2211Tuesday 25 August 202006:00:00Poster
5131XingeZhuSSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds4183Thursday 27 August 202000:00:00Poster
5131XingeZhuSSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds4183Thursday 27 August 202006:00:00Poster
5134FamingFangOID: Outlier Identifying and Discarding in Blind Image Deblurring4184Thursday 27 August 202000:00:00Poster
5134FamingFangOID: Outlier Identifying and Discarding in Blind Image Deblurring4184Thursday 27 August 202006:00:00Poster
5140MateuszMichalkiewiczFew-Shot Single-View 3-D Object Reconstruction with Compositional Priors4185Thursday 27 August 202000:00:00Poster
5140MateuszMichalkiewiczFew-Shot Single-View 3-D Object Reconstruction with Compositional Priors4185Thursday 27 August 202006:00:00Poster
5150FamingFangEnhanced Sparse Model for Blind Deblurring2212Tuesday 25 August 202000:00:00Poster
5150FamingFangEnhanced Sparse Model for Blind Deblurring2212Tuesday 25 August 202006:00:00Poster
5155JunginParkSumGraph: Video Summarization via Recursive Graph Modeling2213Tuesday 25 August 202000:00:00Poster
5155JunginParkSumGraph: Video Summarization via Recursive Graph Modeling2213Tuesday 25 August 202006:00:00Poster
5164KunranXuFeature Normalized Knowledge Distillation for Image Classification2214Tuesday 25 August 202000:00:00Poster
5164KunranXuFeature Normalized Knowledge Distillation for Image Classification2214Tuesday 25 August 202006:00:00Poster
5170Ser-namLimA Metric Learning Reality Check1184Monday 24 August 202014:00:00Poster
5170Ser-namLimA Metric Learning Reality Check1184Tuesday 25 August 202000:00:00Poster
5190KunyuanDuA universal framework for training low-bit DNNs via Feature Transfer4186Thursday 27 August 202000:00:00Poster
5190KunyuanDuA universal framework for training low-bit DNNs via Feature Transfer4186Thursday 27 August 202006:00:00Poster
5192NiculaeSebeXingGAN for Person Image Generation1132Monday 24 August 202006:00:00Poster
5192NiculaeSebeXingGAN for Person Image Generation1132Monday 24 August 202014:00:00Poster
5203ChuangNiuGATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering3300Wednesday 26 August 202014:00:00Poster
5203ChuangNiuGATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering3300Thursday 27 August 202000:00:00Poster
5204YiWangVCNet: A Robust Approach to Blind Image Inpainting4187Thursday 27 August 202000:00:00Poster
5204YiWangVCNet: A Robust Approach to Blind Image Inpainting4187Thursday 27 August 202006:00:00Poster
5205JianboLiuLearning to Predict Context-adaptive Convolution for Semantic Segmentation3148Wednesday 26 August 202000:00:00Poster
5205JianboLiuLearning to Predict Context-adaptive Convolution for Semantic Segmentation3148Wednesday 26 August 202006:00:00Poster
5211JianboLiuEfficientFCN: Holistically-guided Decoding for Semantic Segmentation2215Tuesday 25 August 202000:00:00Poster
5211JianboLiuEfficientFCN: Holistically-guided Decoding for Semantic Segmentation2215Tuesday 25 August 202006:00:00Poster
5227YiwenLiGroSS: Group-Size Series Decomposition for Grouped Architecture Search2368Tuesday 25 August 202014:00:00Poster
5227YiwenLiGroSS: Group-Size Series Decomposition for Grouped Architecture Search2368Wednesday 26 August 202000:00:00Poster
5277RuntaoLiuUnsupervised Sketch to Photo Synthesis2216Tuesday 25 August 202000:00:00Oral
5277RuntaoLiuUnsupervised Sketch to Photo Synthesis2216Tuesday 25 August 202006:00:00Oral
5291SiyuanLiangEfficient Adversarial Attacks for Visual Object Tracking2217Tuesday 25 August 202000:00:00Poster
5291SiyuanLiangEfficient Adversarial Attacks for Visual Object Tracking2217Tuesday 25 August 202006:00:00Poster
5299LaurentKneipGlobally-Optimal Event Camera Motion Estimation4188Thursday 27 August 202000:00:00Poster
5299LaurentKneipGlobally-Optimal Event Camera Motion Estimation4188Thursday 27 August 202006:00:00Poster
5301PetrissaZellWeakly-supervised Learning of Human Dynamics3212Wednesday 26 August 202006:00:00Poster
5301PetrissaZellWeakly-supervised Learning of Human Dynamics3212Wednesday 26 August 202014:00:00Poster
5305RoysonLeeJourney Towards Tiny Perceptual Super-Resolution4390Thursday 27 August 202014:00:00Poster
5305RoysonLeeJourney Towards Tiny Perceptual Super-Resolution4390Friday 28 August 202000:00:00Poster
5308LucyChaiWhat makes fake images detectable? Understanding properties that generalize4391Thursday 27 August 202014:00:00Poster
5308LucyChaiWhat makes fake images detectable? Understanding properties that generalize4391Friday 28 August 202000:00:00Poster
5313PauRodríguez LópezEmbedding Propagation: Smoother Manifold for Few-Shot Classification4392Thursday 27 August 202014:00:00Poster
5313PauRodríguez LópezEmbedding Propagation: Smoother Manifold for Few-Shot Classification4392Friday 28 August 202000:00:00Poster
5315XuChenCategory Level Object Pose Estimation via Neural Analysis-by-Synthesis1133Monday 24 August 202006:00:00Poster
5315XuChenCategory Level Object Pose Estimation via Neural Analysis-by-Synthesis1133Monday 24 August 202014:00:00Poster
5320WonkwangLeeHigh-Fidelity Synthesis with Disentangled Representation2369Tuesday 25 August 202014:00:00Poster
5320WonkwangLeeHigh-Fidelity Synthesis with Disentangled Representation2369Wednesday 26 August 202000:00:00Poster
5323TomasPajdlaPL$_1$P - Point-line Minimal Problems under Partial Visibility in Three Views3301Wednesday 26 August 202014:00:00Poster
5323TomasPajdlaPL$_1$P - Point-line Minimal Problems under Partial Visibility in Three Views3301Thursday 27 August 202000:00:00Poster
5327KeHanPrediction and Recovery for Adaptive Low-Resolution Person Re-Identification4189Thursday 27 August 202000:00:00Poster
5327KeHanPrediction and Recovery for Adaptive Low-Resolution Person Re-Identification4189Thursday 27 August 202006:00:00Poster
5328AmirGlobersonLearning Canonical Representations for Scene Graph to Image Generation3213Wednesday 26 August 202006:00:00Poster
5328AmirGlobersonLearning Canonical Representations for Scene Graph to Image Generation3213Wednesday 26 August 202014:00:00Poster
5331MatthiasHeinAdversarial Robustness on In- and Out-Distribution Improves Explainability1134Monday 24 August 202006:00:00Poster
5331MatthiasHeinAdversarial Robustness on In- and Out-Distribution Improves Explainability1134Monday 24 August 202014:00:00Poster
5333GregShakhnarovichDeformable Style Transfer2370Tuesday 25 August 202014:00:00Poster
5333GregShakhnarovichDeformable Style Transfer2370Wednesday 26 August 202000:00:00Poster
5336SenthilPurushwalkamAligning Videos in Space and Time2371Tuesday 25 August 202014:00:00Poster
5336SenthilPurushwalkamAligning Videos in Space and Time2371Wednesday 26 August 202000:00:00Poster
5346YuanXueNeural Wireframe Renderer: Learning Wireframe to Image Translations2372Tuesday 25 August 202014:00:00Poster
5346YuanXueNeural Wireframe Renderer: Learning Wireframe to Image Translations2372Wednesday 26 August 202000:00:00Poster
5351XiaoZhangRBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax4190Thursday 27 August 202000:00:00Poster
5351XiaoZhangRBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax4190Thursday 27 August 202006:00:00Poster
5360EvgeniaRusakA Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions1135Monday 24 August 202006:00:00Oral
5360EvgeniaRusakA Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions1135Monday 24 August 202014:00:00Oral
5368KelvinWongTesting the Safety of Self-driving Vehicles by Simulating Perception and Prediction3302Wednesday 26 August 202014:00:00Poster
5368KelvinWongTesting the Safety of Self-driving Vehicles by Simulating Perception and Prediction3302Thursday 27 August 202000:00:00Poster
5369ChristianReimersDetermining the Relevance of Features for Deep Neural Networks1136Monday 24 August 202006:00:00Poster
5369ChristianReimersDetermining the Relevance of Features for Deep Neural Networks1136Monday 24 August 202014:00:00Poster
5372LiyiChenWeakly Supervised Semantic Segmentation with Boundary Exploration2218Tuesday 25 August 202000:00:00Poster
5372LiyiChenWeakly Supervised Semantic Segmentation with Boundary Exploration2218Tuesday 25 August 202006:00:00Poster
5381WallaceLiraGANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation2373Tuesday 25 August 202014:00:00Poster
5381WallaceLiraGANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation2373Wednesday 26 August 202000:00:00Poster
5385PhilippeWeinzaepfelDOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild3214Wednesday 26 August 202006:00:00Poster
5385PhilippeWeinzaepfelDOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild3214Wednesday 26 August 202014:00:00Poster
5393SteffenWolfJoint Semantic Instance Segmentation on Graphs with the Semantic Mutex Watershed4393Thursday 27 August 202014:00:00Spotlight
5393SteffenWolfJoint Semantic Instance Segmentation on Graphs with the Semantic Mutex Watershed4393Friday 28 August 202000:00:00Spotlight
5394NikolasAdaloglouMulti-view adaptive graph convolutions for graph classification1137Monday 24 August 202006:00:00Poster
5394NikolasAdaloglouMulti-view adaptive graph convolutions for graph classification1137Monday 24 August 202014:00:00Poster
5406ChuangZhuInstance Adaptive Self-Training for Unsupervised Domain Adaptation3149Wednesday 26 August 202000:00:00Poster
5406ChuangZhuInstance Adaptive Self-Training for Unsupervised Domain Adaptation3149Wednesday 26 August 202006:00:00Poster
5409JuseungYunWeight Decay Scheduling and Knowledge Distillation for Active Learning4191Thursday 27 August 202000:00:00Poster
5409JuseungYunWeight Decay Scheduling and Knowledge Distillation for Active Learning4191Thursday 27 August 202006:00:00Poster
5414Hai VictorHabiHMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs1138Monday 24 August 202006:00:00Poster
5414Hai VictorHabiHMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs1138Monday 24 August 202014:00:00Poster
5423HuuLeTruncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning3215Wednesday 26 August 202006:00:00Poster
5423HuuLeTruncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning3215Wednesday 26 August 202014:00:00Poster
5424LinlinShenGeometry Constrained Weakly Supervised Object Localization3150Wednesday 26 August 202000:00:00Poster
5424LinlinShenGeometry Constrained Weakly Supervised Object Localization3150Wednesday 26 August 202006:00:00Poster
5445GemmaRoigDuality Diagram Similarity: a generic framework for initialization selection in task transfer learning1139Monday 24 August 202006:00:00Poster
5445GemmaRoigDuality Diagram Similarity: a generic framework for initialization selection in task transfer learning1139Monday 24 August 202014:00:00Poster
5448YanivBennyOneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering1140Monday 24 August 202006:00:00Poster
5448YanivBennyOneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering1140Monday 24 August 202014:00:00Poster
5450NikolayMalkinMining self-similarity: Label super-resolution with epitomic representations4394Thursday 27 August 202014:00:00Poster
5450NikolayMalkinMining self-similarity: Label super-resolution with epitomic representations4394Friday 28 August 202000:00:00Poster
5457YidaWangSoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification1141Monday 24 August 202006:00:00Oral
5457YidaWangSoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification1141Monday 24 August 202014:00:00Oral
5471JiayongPengPhoton-Efficient 3D Imaging with A Non-Local Neural Network4192Thursday 27 August 202000:00:00Spotlight
5471JiayongPengPhoton-Efficient 3D Imaging with A Non-Local Neural Network4192Thursday 27 August 202006:00:00Spotlight
5480NaLeiAE-OT-GAN: Training GANs from data specific latent distribution4193Thursday 27 August 202000:00:00Poster
5480NaLeiAE-OT-GAN: Training GANs from data specific latent distribution4193Thursday 27 August 202006:00:00Poster
5488ThomasKehrenbergNull-sampling for Interpretable and Fair Representations2374Tuesday 25 August 202014:00:00Poster
5488ThomasKehrenbergNull-sampling for Interpretable and Fair Representations2374Wednesday 26 August 202000:00:00Poster
5491LamHuynhGuiding Monocular Depth Estimation Using Depth-Attention Volume1142Monday 24 August 202006:00:00Poster
5491LamHuynhGuiding Monocular Depth Estimation Using Depth-Attention Volume1142Monday 24 August 202014:00:00Poster
5494AdamHarleyTracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping1185Monday 24 August 202014:00:00Poster
5494AdamHarleyTracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping1185Tuesday 25 August 202000:00:00Poster
5495LeiZhangBoosting Weakly Supervised Object Detection with Progressive Knowledge Transfer4395Thursday 27 August 202014:00:00Poster
5495LeiZhangBoosting Weakly Supervised Object Detection with Progressive Knowledge Transfer4395Friday 28 August 202000:00:00Poster
5496AyanDasB\'ezierSketch: A generative model for scalable vector sketches4396Thursday 27 August 202014:00:00Poster
5496AyanDasB\'ezierSketch: A generative model for scalable vector sketches4396Friday 28 August 202000:00:00Poster
5530RuoweiJiangSemantic Relation Preserving Knowledge Distillation for Image-to-Image Translation2375Tuesday 25 August 202014:00:00Poster
5530RuoweiJiangSemantic Relation Preserving Knowledge Distillation for Image-to-Image Translation2375Wednesday 26 August 202000:00:00Poster
5551BradyZhouDomain Adaptation Through Task Distillation4397Thursday 27 August 202014:00:00Poster
5551BradyZhouDomain Adaptation Through Task Distillation4397Friday 28 August 202000:00:00Poster
5554RicardoMartin BruallaGeLaTO: Generative Latent Textured Objects4398Thursday 27 August 202014:00:00Spotlight
5554RicardoMartin BruallaGeLaTO: Generative Latent Textured Objects4398Friday 28 August 202000:00:00Spotlight
5563ChenglinYangPatchAttack: A Black-box Texture-based Attack with Reinforcement Learning4399Thursday 27 August 202014:00:00Poster
5563ChenglinYangPatchAttack: A Black-box Texture-based Attack with Reinforcement Learning4399Friday 28 August 202000:00:00Poster
5564YuLiuMore Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning1143Monday 24 August 202006:00:00Poster
5564YuLiuMore Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning1143Monday 24 August 202014:00:00Poster
5568BramWallaceExtending and Analyzing Self-Supervised Learning Across Domains3303Wednesday 26 August 202014:00:00Poster
5568BramWallaceExtending and Analyzing Self-Supervised Learning Across Domains3303Thursday 27 August 202000:00:00Poster
5573SayanRakshitMulti-Source Open-Set Deep Adversarial Domain Adaptation1144Monday 24 August 202006:00:00Poster
5573SayanRakshitMulti-Source Open-Set Deep Adversarial Domain Adaptation1144Monday 24 August 202014:00:00Poster
5576Wen-hsuanChuNeural Batch Sampling with Reinforcement Learning for Semi-Supervised Anomaly Detection2376Tuesday 25 August 202014:00:00Poster
5576Wen-hsuanChuNeural Batch Sampling with Reinforcement Learning for Semi-Supervised Anomaly Detection2376Wednesday 26 August 202000:00:00Poster
5581BaoxiongJiaLEMMA: A Multi-view Dataset for \underline{L\underline{Earning \underline{Multi-agent \underline{Multi-task \underline{Activities4400Thursday 27 August 202014:00:00Poster
5581BaoxiongJiaLEMMA: A Multi-view Dataset for \underline{L\underline{Earning \underline{Multi-agent \underline{Multi-task \underline{Activities4400Friday 28 August 202000:00:00Poster
5589MatthewPurriTeaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images3304Wednesday 26 August 202014:00:00Poster
5589MatthewPurriTeaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images3304Thursday 27 August 202000:00:00Poster
5592JoseIglesiasAccurate Optimization of Weighted Nuclear Norm for Non-Rigid Structure from Motion1145Monday 24 August 202006:00:00Poster
5592JoseIglesiasAccurate Optimization of Weighted Nuclear Norm for Non-Rigid Structure from Motion1145Monday 24 August 202014:00:00Poster
5605HengWangProposal-based Video Completion4401Thursday 27 August 202014:00:00Poster
5605HengWangProposal-based Video Completion4401Friday 28 August 202000:00:00Poster
5608ZhengmingDingHGNet: Hybrid Generative Network for Zero-shot Domain Adaptation2377Tuesday 25 August 202014:00:00Poster
5608ZhengmingDingHGNet: Hybrid Generative Network for Zero-shot Domain Adaptation2377Wednesday 26 August 202000:00:00Poster
5622KaihaoZhangBeyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding2219Tuesday 25 August 202000:00:00Poster
5622KaihaoZhangBeyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding2219Tuesday 25 August 202006:00:00Poster
5625HassanDboukDBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks2378Tuesday 25 August 202014:00:00Poster
5625HassanDboukDBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks2378Wednesday 26 August 202000:00:00Poster
5635ZhixiangChiAll at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling2379Tuesday 25 August 202014:00:00Poster
5635ZhixiangChiAll at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling2379Wednesday 26 August 202000:00:00Poster
5643NoelCodellaA Broader Study of Cross-Domain Few-Shot Learning3305Wednesday 26 August 202014:00:00Poster
5643NoelCodellaA Broader Study of Cross-Domain Few-Shot Learning3305Thursday 27 August 202000:00:00Poster
5645JFGoPractical Poisoning Attacks on Neural Networks4402Thursday 27 August 202014:00:00Poster
5645JFGoPractical Poisoning Attacks on Neural Networks4402Friday 28 August 202000:00:00Poster
5669DjebrilMekhazniUnsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification1186Monday 24 August 202014:00:00Poster
5669DjebrilMekhazniUnsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification1186Tuesday 25 August 202000:00:00Poster
5671HuiQuLearn distributed GAN with Temporary Discriminators4403Thursday 27 August 202014:00:00Poster
5671HuiQuLearn distributed GAN with Temporary Discriminators4403Friday 28 August 202000:00:00Poster
5672ArjunMajumdarImproving Vision-and-Language Navigation with Image-Text Pairs from the Web4404Thursday 27 August 202014:00:00Spotlight
5672ArjunMajumdarImproving Vision-and-Language Navigation with Image-Text Pairs from the Web4404Friday 28 August 202000:00:00Spotlight
5673JoãoPeralta MoreiraSemifreddoNets: Partially Frozen Neural Networks for~Efficient~Computer~Vision~Systems3306Wednesday 26 August 202014:00:00Poster
5673JoãoPeralta MoreiraSemifreddoNets: Partially Frozen Neural Networks for~Efficient~Computer~Vision~Systems3306Thursday 27 August 202000:00:00Poster
5685XinyuLiDirectional Temporal Modeling for Action Recognition4405Thursday 27 August 202014:00:00Spotlight
5685XinyuLiDirectional Temporal Modeling for Action Recognition4405Friday 28 August 202000:00:00Spotlight
5686Tuan AnhBuiImproving Adversarial Robustness by Enforcing Local and Global Compactness2220Tuesday 25 August 202000:00:00Poster
5686Tuan AnhBuiImproving Adversarial Robustness by Enforcing Local and Global Compactness2220Tuesday 25 August 202006:00:00Poster
5687SubeeshVasuTopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation3216Wednesday 26 August 202006:00:00Poster
5687SubeeshVasuTopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation3216Wednesday 26 August 202014:00:00Poster
5695CharlesHerrmannChannel selection using Gumbel Softmax4406Thursday 27 August 202014:00:00Poster
5695CharlesHerrmannChannel selection using Gumbel Softmax4406Friday 28 August 202000:00:00Poster
5696Dripta SankarRaychaudhuriExploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification4407Thursday 27 August 202014:00:00Poster
5696Dripta SankarRaychaudhuriExploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification4407Friday 28 August 202000:00:00Poster
5698ZixuanJiangAn Efficient Training Framework for Reversible Neural Architectures4408Thursday 27 August 202014:00:00Poster
5698ZixuanJiangAn Efficient Training Framework for Reversible Neural Architectures4408Friday 28 August 202000:00:00Poster
5714FrankDellaertShonan Rotation Averaging: Global Optimality by Surfing $SO(p)^n$4409Thursday 27 August 202014:00:00Spotlight
5714FrankDellaertShonan Rotation Averaging: Global Optimality by Surfing $SO(p)^n$4409Friday 28 August 202000:00:00Spotlight
5717SiddharthaChandraBox2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation4410Thursday 27 August 202014:00:00Poster
5717SiddharthaChandraBox2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation4410Friday 28 August 202000:00:00Poster
5723Devendra SinghChaplotSemantic Curiosity for Active Visual Learning2380Tuesday 25 August 202014:00:00Spotlight
5723Devendra SinghChaplotSemantic Curiosity for Active Visual Learning2380Wednesday 26 August 202000:00:00Spotlight
5744YichengWuFreeCam3D: Snapshot Structured Light 3D with Freely-Moving Cameras2381Tuesday 25 August 202014:00:00Poster
5744YichengWuFreeCam3D: Snapshot Structured Light 3D with Freely-Moving Cameras2381Wednesday 26 August 202000:00:00Poster
5750ShanjiaoyangHuangOne-Pixel Signature: Characterizing CNN Models for Backdoor Detection4411Thursday 27 August 202014:00:00Poster
5750ShanjiaoyangHuangOne-Pixel Signature: Characterizing CNN Models for Backdoor Detection4411Friday 28 August 202000:00:00Poster
5752LinchaoZhuLearning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning2221Tuesday 25 August 202000:00:00Poster
5752LinchaoZhuLearning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning2221Tuesday 25 August 202006:00:00Poster
5757HaoWangStructure-Aware Generation Network for Recipe Generation from Images4194Thursday 27 August 202000:00:00Poster
5757HaoWangStructure-Aware Generation Network for Recipe Generation from Images4194Thursday 27 August 202006:00:00Poster
5769QiQiA Simple and Effective Framework for Pairwise Deep Metric Learning4412Thursday 27 August 202014:00:00Poster
5769QiQiA Simple and Effective Framework for Pairwise Deep Metric Learning4412Friday 28 August 202000:00:00Poster
5772EugeneLeeMeta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner2222Tuesday 25 August 202000:00:00Poster
5772EugeneLeeMeta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner2222Tuesday 25 August 202006:00:00Poster
5775KaraSchatzA Recurrent Transformer Network for Novel View Action Synthesis4413Thursday 27 August 202014:00:00Poster
5775KaraSchatzA Recurrent Transformer Network for Novel View Action Synthesis4413Friday 28 August 202000:00:00Poster
5777ShrutiVyasMulti-view Action Recognition using Cross-view Video Prediction4414Thursday 27 August 202014:00:00Poster
5777ShrutiVyasMulti-view Action Recognition using Cross-view Video Prediction4414Friday 28 August 202000:00:00Poster
5794MingminZhenLearning Discriminative Feature with CRF for Unsupervised Video Object Segmentation4195Thursday 27 August 202000:00:00Poster
5794MingminZhenLearning Discriminative Feature with CRF for Unsupervised Video Object Segmentation4195Thursday 27 August 202006:00:00Poster
5800PeipeiLiHierarchical Face Aging through Disentangled Latent Characteristics2223Tuesday 25 August 202000:00:00Oral
5800PeipeiLiHierarchical Face Aging through Disentangled Latent Characteristics2223Tuesday 25 August 202006:00:00Oral
5809SriramNochur NarayananSMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction3307Wednesday 26 August 202014:00:00Poster
5809SriramNochur NarayananSMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction3307Thursday 27 August 202000:00:00Poster
5818JinyuYangLabel-Driven Reconstruction for Domain Adaptation in Semantic Segmentation4415Thursday 27 August 202014:00:00Poster
5818JinyuYangLabel-Driven Reconstruction for Domain Adaptation in Semantic Segmentation4415Friday 28 August 202000:00:00Poster
5821DongwonParkMulti-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training2224Tuesday 25 August 202000:00:00Spotlight
5821DongwonParkMulti-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training2224Tuesday 25 August 202006:00:00Spotlight
5831Chi-ChongWongEfficient Outdoor 3D Point Cloud Semantic Segmentation for Critical Road Objects and Distributed Contexts3151Wednesday 26 August 202000:00:00Poster
5831Chi-ChongWongEfficient Outdoor 3D Point Cloud Semantic Segmentation for Critical Road Objects and Distributed Contexts3151Wednesday 26 August 202006:00:00Poster
5849NupurKumariAttributional Robustness Training using Input-Gradient Spatial Alignment1146Monday 24 August 202006:00:00Poster
5849NupurKumariAttributional Robustness Training using Input-Gradient Spatial Alignment1146Monday 24 August 202014:00:00Poster
5855TimoStoffregenReducing the Sim-to-Real Gap for Event Cameras4196Thursday 27 August 202000:00:00Poster
5855TimoStoffregenReducing the Sim-to-Real Gap for Event Cameras4196Thursday 27 August 202006:00:00Poster
5859HongjieZhangHybrid Models for Open Set Recognition4197Thursday 27 August 202000:00:00Oral
5859HongjieZhangHybrid Models for Open Set Recognition4197Thursday 27 August 202006:00:00Oral
5863LiangliangRenSpatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement Learning3152Wednesday 26 August 202000:00:00Poster
5863LiangliangRenSpatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement Learning3152Wednesday 26 August 202006:00:00Poster
5865BarretZophLearning Data Augmentation Strategies for Object Detection2382Tuesday 25 August 202014:00:00Poster
5865BarretZophLearning Data Augmentation Strategies for Object Detection2382Wednesday 26 August 202000:00:00Poster
5875XiyangDaiDA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search4416Thursday 27 August 202014:00:00Poster
5875XiyangDaiDA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search4416Friday 28 August 202000:00:00Poster
5879StevenSpratleyA Closer Look at Generalisation in RAVEN2225Tuesday 25 August 202000:00:00Poster
5879StevenSpratleyA Closer Look at Generalisation in RAVEN2225Tuesday 25 August 202006:00:00Poster
5884XierChenSupervised Edge Attention Network for Accurate Image Instance Segmentation3153Wednesday 26 August 202000:00:00Poster
5884XierChenSupervised Edge Attention Network for Accurate Image Instance Segmentation3153Wednesday 26 August 202006:00:00Poster
5888JianHuDiscriminative Partial Domain Adversarial Network2226Wednesday 26 August 202000:00:00Poster
5888JianHuDiscriminative Partial Domain Adversarial Network2226Wednesday 26 August 202006:00:00Poster
5893SurenJayasuriyaDifferentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model2383Tuesday 25 August 202014:00:00Poster
5893SurenJayasuriyaDifferentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model2383Wednesday 26 August 202000:00:00Poster
5894XiaoShiDeep Cross-species Feature Learning for Animal Face Recognition via Residual Interspecies Equivariant Network2227Tuesday 25 August 202000:00:00Poster
5894XiaoShiDeep Cross-species Feature Learning for Animal Face Recognition via Residual Interspecies Equivariant Network2227Tuesday 25 August 202006:00:00Poster
5897LiangLiaoGuidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes3154Wednesday 26 August 202000:00:00Poster
5897LiangLiaoGuidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes3154Wednesday 26 August 202006:00:00Poster
5906AnoopCherianSound2Sight: Generating Visual Dynamics from Sound and Context2384Tuesday 25 August 202014:00:00Poster
5906AnoopCherianSound2Sight: Generating Visual Dynamics from Sound and Context2384Wednesday 26 August 202000:00:00Poster
5913Jun WonChoi3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection4198Thursday 27 August 202000:00:00Poster
5913Jun WonChoi3D