Accepted Papers

Paper IDPaper TitleCategory
267Quaternion Equivariant Capsule Networks for 3D Point CloudsOral
283DeepFit: 3D Surface Fitting by Neural Network Weighted Least SquaresOral
343MoSaNAS: Multi-Objective Surrogate-Assisted Neural Architecture SearchOral
384Describing Textures using Natural LanguageOral
410Empowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity RecognitionOral
445AiR: Attention with Reasoning CapabilityOral
500Self6D: Self-Supervised Monocular 6D Object Pose EstimationOral
529Invertible Image RescalingOral
612Synthesize then Compare: Detecting Failures and Anomalies for Semantic SegmentationOral
677House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout GenerationOral
736Crowdsampling the Plenoptic FunctionOral
738End-to-End Estimation of Multi-Person 3D Poses from Multiple CamerasOral
832End-to-End Object Detection with TransformersOral
840DeepSFM: Structure From Motion Via Deep Bundle AdjustmentOral
1044Ladybird: Deep Implicit Field Based 3D Reconstruction with Sampling and SymmetryOral
1059Segment as Points for Efficient Online Multi-Object Tracking and SegmentationOral
1105Conditional Convolutions for Instance SegmentationOral
1196MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and ResolutionOral
1203Fashionpedia: Ontology, Segmentation, and an Attribute Localization DatasetOral
1273Privacy Preserving Structure-from-MotionOral
1326Rewriting a Deep Generative ModelOral
1417Compare and Reweight: Distinctive Image Captioning Using Similar Images SetsOral
1448Long-term Human Motion Prediction with Scene ContextOral
1473NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisOral
1501ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World ScenesOral
1737MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere ImagesOral
1793Learning and aggregating deep local descriptors for instance-level recognitionOral
1969A Consistently Fast and Globally Optimal Solution to the Perspective-n-Point ProblemOral
2096Learn to Recover Visible Color for Video Surveillance in a DayOral
2149Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single-view ImagesOral
2193Spatially Adaptive Inference with Stochastic Feature Sampling and InterpolationOral
2211BorderDet: Border Feature for Dense Object DetectionOral
2258Regularization with Latent Space Virtual Adversarial TrainingOral
2263Du$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-PixelsOral
2307Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learningOral
2463Targeted Attack for Deep Hashing based RetrievalOral
2471Gradient Centralization: A New Optimization Technique for Deep Neural NetworksOral
2503Content-Aware Unsupervised Deep Homography EstimationOral
2556Multi-View Optimization of Local Feature GeometryOral
2597Efficient Model Fitting by Combining Lifted Optimization with Phong Surface ModelsOral
2641Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person VideoOral
2683Learning Stereo from Single ImagesOral
2748Prototype Rectification for Few-Shot LearningOral
2784Learning Feature Descriptors using Camera Pose SupervisionOral
2785Semantic Flow for Fast and Accurate Scene ParsingOral
2788Appearance Consensus Driven Self-Supervised Human Mesh RecoveryOral
2825Diffraction Line ImagingOral
2834Aligning and Projecting Images to Class-conditional Generative NetworksOral
2852Suppress and Balance: A Simple Gated Network for Salient Object DetectionOral
2904Visual Memorability for Robotic Interestingness Prediction via Unsupervised Online LearningOral
2949Post-Training Piecewise Linear Quantization for Deep Neural NetworksOral
2974Joint Disentangling and Adaptation for Cross-Domain Person Re-IdentificationOral
2978In-Home Daily-Life Captioning Using Radio SignalsOral
3018Self-Challenging Improves Cross-Domain GeneralizationOral
3029A Competence-aware Curriculum for Visual Concepts Learning via Question AnsweringOral
3047Multi-task Learning Increases Adversarial RobustnessOral
3054S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture SearchOral
3112Improving Deep Video Compression by Resolution-adaptive Flow CodingOral
3158Motion Capture from Internet VideosOral
3183Appearance-Preserving 3D Convolution for Video-based Person Re-identificationOral
3241Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric OptimizationOral
3265Exploiting Deep Generative Prior for Versatile Image Restoration and ManipulationOral
3312Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded AperturesOral
3331Video-based Remote Physiological Measurement via Cross-verified Feature DisentanglingOral
3356Combining Implicit Function Learning and Parametric Models for 3D Human ReconstructionOral
3376Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention NetworkOral
3387Mining Cross-Image Semantics for Weakly Supervised Semantic SegmentationOral
3439Coherent full scene 3D reconstruction from a single RGB imageOral
3482Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNsOral
3526RAFT: Recurrent All-Pairs Field Transforms for Optical FlowOral
3528Domain-invariant Stereo Matching NetworksOral
3538DeepHandMesh: Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling from a Single RGB ImageOral
3544Content Adaptive and Error Propagation Aware Deep Video CompressionOral
3553Towards Streaming Image UnderstandingOral
3570Towards Automated Testing and Robustification by Semantic Adversarial Data GenerationOral
3582Adversarial Generative Grammars for Human Activity PredictionOral
3587Greedy Sampler and Dumb Learner: A Surprisingly Effective Approach for Continual LearningOral
3622Learning Lane Graph Representations for Motion ForecastingOral
3651What Matters in Unsupervised Optical FlowOral
3678Synthesis and Completion of Facades from Satellite ImageryOral
3772Mapillary Planet-Scale Depth DatasetOral
3838V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and PredictionOral
3891Training Interpretable Convolutional Neural Networks by Differentiating Class-specific FiltersOral
3948EagleEye: Fast Sub-net Evaluation for Efficient Neural Network PruningOral
3975Intrinsic Point Cloud Interpolation via Dual Latent Space NavigationOral
3976Cross-Domain Cascaded Deep TranslationOral
4043"Look Ma, no landmarks!" - Unsupervised, model-based dense face alignmentOral
4158Online Invariance Selection for Local Feature DescriptorsOral
4179Rethinking image inpainting via a mutual encoder-decoder with feature equalizationOral
4358TextCaps: a Dataset for Image Captioning with Reading ComprehensionOral
4423It is not the Journey but the Destination: Endpoint Conditioned Trajectory PredictionOral
4440Learning What to Learn for Video Object SegmentationOral
4732SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D ClothingOral
4866LIMP: Learning Latent Shape Representations with Metric Preservation PriorsOral
5277Unsupervised Sketch-to-Photo SynthesisOral
5360A simple way to make neural networks robust against diverse image corruptionsOral
5457SoftpoolNet: Shape Descriptor for Point Cloud Completion and ClassificationOral
5800Hierarchical Face Aging through Disentangled Latent CharacteristicsOral
5859Hybrid Models for Open Set RecognitionOral
5932TopoGAN: A Topology-Aware Generative Adversarial NetworkOral
6101Learning to Localize Actions from MomentsOral
6147ForkGAN: Seeing into the Rainy NightOral
6209TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality LearningOral
6502ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image RetrievalOral
22A Simple and Versatile Framework for Image-to-Image TranslationSpotlight
43ProxyBNN: Learning Binarized Neural Networks via Proxy MatricesSpotlight
87Fair Attribute Classification through Latent Space De-biasingSpotlight
148HMOR: Hierarchical Multi-person Ordinal Relations for Monocular Multi-Person 3D Pose EstimationSpotlight
193Mask2CAD: 3D Shape Prediction by Learning to Segment and RetrieveSpotlight
223A Unified Framework of Surrogate Loss by Refactorization and InterpolationSpotlight
362Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric ImagesSpotlight
366Memory-augmented Dense Predictive Coding for Video Representation LearningSpotlight
378PointMixup: Augmentation for Point CloudsSpotlight
415Identity-Guided Human Semantic Parsing Learning for Person Re-IdentificationSpotlight
462Learning Gradient Fields for Shape GenerationSpotlight
467Few-Shot Unsupervised Image Translation with a Content Conditioned Style EncoderSpotlight
492Corner Proposal Network for Anchor-free, Two-stage Object DetectionSpotlight
495PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and ClickSpotlight
513Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video ParsingSpotlight
526Learning Delicate Local Representations for Multi-Person Pose EstimationSpotlight
544Learning to plan with uncertain topological mapsSpotlight
574Neural Design Network: Graphic Layout Generation with ConstraintsSpotlight
591Learning Open Set Network with Discriminative Reciprocal PointsSpotlight
597Convolutional Occupancy NetworksSpotlight
672Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View GeometrySpotlight
849A General Toolbox for Understanding Errors in Object DetectionSpotlight
893PointContrast: Unsupervised Pretraining for 3D Point Cloud UnderstandingSpotlight
922DSA: More Efficient Budgeted Pruning via Differentiable Sparsity AllocationSpotlight
990Circumventing Outliers of AutoAugment with Knowledge DistillationSpotlight
997S2DNet: Learning accurate correspondences for sparse-to-dense feature matchingSpotlight
1054RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous DrivingSpotlight
1062Video Object Segmentation with Graph Memory NetworkSpotlight
1101Rethinking Bottleneck Structure for Efficient Mobile Network DesignSpotlight
1104Side-Tuning: A Baseline for Network Adaptation via Additive Side NetworksSpotlight
1121Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search ApproachSpotlight
1207A Tool for Measuring and Mitigating Bias in Visual DatasetsSpotlight
1327Contrastive Learning for Weakly Supervised Phrase GroundingSpotlight
1362Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature AnalysisSpotlight
1425Studying the Transferability of Adversarial Attacks on Object DetectorsSpotlight
1449TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired ImagesSpotlight
1479Semi-Siamese Training for Shallow Face LearningSpotlight
1488GAN Slimming: All-in-One Unified GAN CompressionSpotlight
1526Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence RecognitionSpotlight
1530Binarized Neural Network for Single Image Super ResolutionSpotlight
1564Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic SegmentationSpotlight
1605Adaptive Computationally Efficient Network for Monocular 3D Hand Pose EstimationSpotlight
1624Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and TrackingSpotlight
1631Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed DatasetsSpotlight
1676Hamiltonian Dynamics for Real-World Shape InterpolationSpotlight
1694Learning to Scale Multilingual Representations for Vision-Language TasksSpotlight
1710Multi-modal Transformer for Video RetrievalSpotlight
1761Matching Feature Matters: End-to-End Learning for Neural Texture TransferSpotlight
1802RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD CameraSpotlight
1886Surface Normal Estimation of Tilted Images via Spatial RectifierSpotlight
1915Multimodal Shape Completion via Conditional Generative Adversarial NetworksSpotlight
1977Generative Sparse Detection Network for 3D Single-shot Object DetectionSpotlight
1987Grounded Situation RecognitionSpotlight
2019Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in VideosSpotlight
2157Unpaired Learning of Deep Blind Image DenoisingSpotlight
2191Self-supervising Fine-grained Region Similarities for Large-scale Image LocalizationSpotlight
2215Rotationally-Temporally Consistent Novel-View Synthesis of Human Performance VideoSpotlight
2272Side-Aware Boundary Localization for More Precise Object DetectionSpotlight
2314SF-Net: Single-Frame Supervision for Temporal Action LocalizationSpotlight
2317Negative Margin Matters: Understanding Margin in Few-shot ClassificationSpotlight
2323Particularity beyond Commonality: Unpaired Identity Transfer with Multiple ReferencesSpotlight
2342Tracking objects as pointsSpotlight
2390CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image SynthesisSpotlight
2402Transporting Labels via Hierarchical Optimal Transport for Semi-Supervised LearningSpotlight
2449MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task LearningSpotlight
2473Learning to Factorize a CitySpotlight
2495Region Graph Embedding Network for Zero-Shot LearningSpotlight
2534GRAB: A Dataset of Whole-Body Human Grasping of ObjectsSpotlight
2616DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming ObjectsSpotlight
2623RANSAC-Flow: generic two-stage image alignmentSpotlight
2632Semantic Object Prediction with Binaural SoundsSpotlight
2636Neural Object Learning for 6D Pose Estimation Using a Few Cluttered ImagesSpotlight
2666Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency CheckingSpotlight
2707Pixel-Pair Occlusion Relationship Map (P2ORM): Formulation, Inference & ApplicationSpotlight
2710MovieNet: A Holistic Dataset for Movie UnderstandingSpotlight
2723Short-Term and Long-Term Context Aggregation Network for Video InpaintingSpotlight
2754Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DOF RelocalizationSpotlight
2755Face Super-Resolution Guided by 3D Facial PriorsSpotlight
2763Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain AdaptationSpotlight
2767Are Labels Necessary for Neural Architecture Search?Spotlight
2776BLSM: A Bone-Level Skinned Model of the Human MeshSpotlight
2826Associative Alignment for Few-shot Image ClassificationSpotlight
2873Cyclic Functional Mapping:Self-supervised correspondence between non-isometric deformable shapesSpotlight
2905View-Invariant Probabilistic Embedding for Human PoseSpotlight
2918Contact and Human Dynamics from Monocular VideoSpotlight
2950PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow EstimationSpotlight
2965Point2Surf: Learning Implicit Surfaces from Point Cloud PatchesSpotlight
2983Few-Shot Scene-Adaptive Anomaly DetectionSpotlight
2986Personalized Face Modeling for Improved Face Reconstruction and Motion RetargetingSpotlight
2988Entropy Minimisation Framework for Event-based Vision Model EstimationSpotlight
2992Reconstructing NBA PlayersSpotlight
3087PIoU Loss: Towards Accurate Oriented Object Detection in Complex EnvironmentsSpotlight
3089TENet: Triple Excitation Network for Video Salient Object DetectionSpotlight
3099Deep Feedback Inverse Problem SolverSpotlight
3119Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed ClassificationSpotlight
3120Hallucinating Visual Instances in Total AbsentiaSpotlight
3125Unsupervised 3D Shape Completion in the WildSpotlight
3335DTVNet: Dynamic Time-lapse Video Generation via Single Still ImageSpotlight
3365CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding LossSpotlight
3385Collaborative Video Object Segmentation by Foreground-Background IntegrationSpotlight
3456Adaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIRSpotlight
3477XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze VariationSpotlight
3499Calibration-free Structure-from-Motion with Calibrated Radial Trifocal TensorsSpotlight
3594Occupancy anticipation for efficient navigationSpotlight
3601Unified Image and Video Saliency ModelingSpotlight
3604TAO: A Large-scale Benchmark for Tracking Any ObjectSpotlight
3657A Generalization of Otsu's Method and Minimum Error ThresholdingSpotlight
3663A Cordial Sync: Moving Furniture by Moving Beyond Marginal PoliciesSpotlight
3665Big Transfer (BiT): General Visual Representation LearningSpotlight
3684Visual Commonsense Graphs: Reasoning about the Dynamic Context of a Still ImageSpotlight
3831Few-shot Action Recognition via Permutation-invariant AttentionSpotlight
3913Character Grounding and Re-Identification in Story of Videos and Text DescriptionsSpotlight
3977AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-samplingSpotlight
3984Learning Visual Context by ComparisonSpotlight
3994Large scale holistic video understandingSpotlight
3995Indirect Local Attacks for Context-aware Semantic Segmentation NetworksSpotlight
4294Inferring Visual Overlap of Images through Interpretable Non-Metric EmbeddingsSpotlight
4296Connecting Vision and Language with Localized NarrativesSpotlight
4383Adversarial T-shirt! Evading Person Detectors in A Physical WorldSpotlight
4404Bounding-box Channels for Visual Relationship DetectionSpotlight
4407Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial DistortionSpotlight
4442SRFlow: Learning the Super-Resolution Space with Normalizing FlowSpotlight
4452DeepGMR: Learning Latent Gaussian Mixture Models for RegistrationSpotlight
4458Active 3D Perception using Light CurtainsSpotlight
4521Invertible Neural BRDF for Object Inverse RenderingSpotlight
4545Semi-supervised Semantic Segmentation via Strong-weak Dual-branch NetworkSpotlight
4571Practical Deep Raw Image Denoising on Mobile DevicesSpotlight
4577Audio-Visual Embodied NavigationSpotlight
4602Two-Stream Consensus Networks for Weakly-Supervised Temporal Action LocalizationSpotlight
4677Erasing Appearance Preservation in Image SmoothingSpotlight
4727Counterfactual Vision-and-Language Navigation via Adversarial Path SamplerSpotlight
4749Guided Deep Decoder: Unsupervised Image Pair FusionSpotlight
4809Filter Style Transfer between PhotosSpotlight
4860JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth ImageSpotlight
4867Dynamic Group Convolution for Accelerating Convolutional Neural NetworksSpotlight
4880RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and RenderingSpotlight
5021Object-Contextual Representations for Semantic SegmentationSpotlight
5116Spatio-Temporal Efficient Recurrent Neural Network for Video DeblurringSpotlight
5393The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance SegmentationSpotlight
5471Photon-Efficient 3D Imaging with A Non-Local Neural NetworkSpotlight
5554Generative Latent Textured Proxies for Category-Level Object ModelingSpotlight
5672Improving Vision-and-Language Navigation with Image-Text Pairs from the WebSpotlight
5685Directional Temporal Modeling for Action RecognitionSpotlight
5714Shonan Rotation Averaging: Global Optimality by Surfing $SO(p)^n$Spotlight
5723Semantic Curiosity for Visual NavigationSpotlight
5821Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal TrainingSpotlight
5975ProgressFace: Scale-Aware Progressive Learning for Face DetectionSpotlight
6025Learning Multi-layer Latent Variable Model with Short Run Inference DynamicsSpotlight
6053CoTeRe-Net: Discovering Collaborative Ternary Relations in VideosSpotlight
6100Modeling the Effects of Windshield Refraction for Camera CalibrationSpotlight
6124Skin Segmentation from NIR Images using Unsupervised Domain Adaptation through Generative Latent SearchSpotlight
6254PROFIT: A Novel Training Method for sub-4-bit MobileNet ModelsSpotlight
6277Visual Relation Grounding in VideosSpotlight
6296Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing FlowsSpotlight
6314Controlling semantics and style in conditional image synthesisSpotlight
6360Jointly learning visual motion and confidence from local patches in event camerasSpotlight
6406SODA: Story Oriented Dense Video Captioning Evaluation FrameworkSpotlight
6490Sketch-Guided Object Localization in Natural ImagesSpotlight
6496Metric learning: cross-entropy vs. pairwise lossesSpotlight
6959Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language ModelsSpotlight
7231The Hessian Penalty: A Weak Prior for Unsupervised DisentanglementSpotlight
5STAR: Sparse Trained Articulated Human Body RegressorPoster
13Optical Flow Distillation: Towards Efficient and Stable Video Style TransferPoster
15Collaboration by Competition: Self-coordinated Knowledge Amalgamation for Multi-talent Student LearningPoster
25Do Not Disturb Me: Person Re-identification Under the Interference of Other PedestriansPoster
31Learning 3D Part Assembly from A Single ImagePoster
32PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree ConditionsPoster
50Highly Efficient Salient Object Detection with 100K ParametersPoster
69HardGAN: A Haze-Aware Representation Distillation GAN for Single Image DehazingPoster
88Lifespan Age Transformation SynthesisPoster
90Domain2Vec: Domain Embedding for Unsupervised Domain AdaptationPoster
106Synthesizing Content Consistent Vehicle Datasets with Attribute DescentPoster
116Multiview Pedestrian Detection with Feature Perspective TransformationPoster
121Learning Object Relation Graph and Tentative Policy for Visual NavigationPoster
123Adversarial Self-Supervised Learning for Semi-Supervised 3D Action RecognitionPoster
132Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal LearningPoster
138Inducing Optimal Attributes Representations for Conditional GANsPoster
152AR-Net: Adaptive Frame Resolution for Efficient Action RecognitionPoster
156Image-to-Voxel Model Translation for 3D Scene Reconstruction and SegmentationPoster
157Consistency Guided Scene Flow EstimationPoster
160Autoregressive Unsupervised Image SegmentationPoster
169Controllable Image Synthesis via SegVAEPoster
173Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture SearchPoster
177Efficient Non-Line-of-Sight Imaging by Circular and Confocal ScanningPoster
181Texture Hallucination for Large-Factor Painting Super-ResolutionPoster
183Learning Progressive Joint Propagation for Human Motion PredictionPoster
184Rolling Shutter Image Stitching and Rectification via Differential HomographyPoster
186ParSeNet: A Parametric Surface Fitting Network for 3D Point CloudsPoster
188The Group Loss for Deep Metric LearningPoster
203Learning Object Depth from Camera Motion and Video Object SegmentationPoster
206OnlineAugment: Online Data Augmentation with Less Domain KnowledgePoster
209Learning Inter-Plane Relations for Piecewise Planar ReconstructionPoster
230Intra-class Compactness Distillation for Semantic SegmentationPoster
233Temporal Distinct Representation Learning for 2D-CNN-based Action RecognitionPoster
241Representative Graph Neural NetworkPoster
264Deformation-Aware 3D Shape Embedding and RetrievalPoster
277Atlas: End-to-End 3D Scene Reconstruction from Posed ImagesPoster
278Multiple Class Novelty Detection Under the Data Distribution ShiftPoster
281Colorization of Depth Map via DisentanglementPoster
287Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor ScenesPoster
292GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-endPoster
300Localizing the Common Action Among a Few VideosPoster
306TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationPoster
312Traffic Accident Analysis by Cause and Effect Events LocalizationPoster
318Face Anti-Spoofing with Human Material PerceptionPoster
328How Can I See My Future? FvTraj: Using First-person View for Pedestrian Trajectory PredictionPoster
338Multiple Expert Brainstorming for Domain Adaptive Person Re-identificationPoster
344NASA: Neural Articulated Shape ApproximationPoster
350Towards Unique and Informative Captioning of ImagesPoster
352When Does Self-supervision Improve Few-shot Learning?Poster
355Two-branch Recurrent Network for Isolating Deepfakes in VideosPoster
360Incremental Few-Shot Meta-Learning via Indirect Feature AlignmentPoster
363BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage ModelsPoster
386Differentiable Hierarchical Graph Grouping for Multi-Person Pose EstimationPoster
392Global Distance-distributions Separation for Unsupervised Person Re-identificationPoster
397I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB ImagePoster
398Pose2Mesh: Graph Convolutional Network for 3D human Pose and Mesh Recovery from 2D Human PosePoster
402ALRe: Outlier Detection for Guided RefinementPoster
414Weakly-Supervised Crowd Counting Learns from Sorting rather than LocationsPoster
429Unsupervised Domain Attention Adaptation Network for Caricature Attribute RecognitionPoster
438Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object DetectionPoster
441Curriculum DeepSDFPoster
444Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio GuidancePoster
457Improved Adversarial Training via Learned OptimizerPoster
471Component Divide-and-Conquer for Real-World Image Super-ResolutionPoster
479Enabling Deep Residual Networks for Weakly Supervised Object DetectionPoster
494Deep near-light photometric stereo for spatially varying reflectancesPoster
498Learning Visual Representations with Caption AnnotationsPoster
509Solving Long-tailed Recognition with Deep Realistic Taxonomic ClassifierPoster
512Regression of Instance Boundary by Aggregated CNN and GCNPoster
520Social Adaptive Module for Weakly-supervised Group Activity RecognitionPoster
521RGB-D Salient Object Detection with Cross-Modality Modulation and SelectionPoster
524RetrieveGAN: Image Synthesis via Differentiable Patch RetrievalPoster
536Cheaper Pre-training Lunch: An Efficient Paradigm for Object DetectionPoster
566Faster Person Re-IdentificationPoster
570Quantization Guided JPEG Artifact CorrectionPoster
5713PointTM: Faster Measurement of High-Dimensional Transmission MatricesPoster
575Joint Bilateral Learning for Real-time Universal Photorealistic Style TransferPoster
581Beyond 3DMM Space: Towards Fine-grained 3D Face ReconstructionPoster
587World-Consistent Video-to-Video SynthesisPoster
596Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance SegmentationPoster
598GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the WildPoster
600Event-based Asynchronous Sparse Convolutional NetworksPoster
604AtlantaNet: Inferring the 3D Indoor Layout from a Single 360 Image Beyond the Manhattan World AssumptionPoster
607Spatiotemporal Attention Cell Search for Video ClassificationPoster
609REMIND Your Neural Network to Prevent Catastrophic ForgettingPoster
611Image Classification in the dark using Quanta Image SensorsPoster
615$n$-Reference Transfer Learning for Saliency PredictionPoster
618Progressively Guided Alternate Refinement Network for RGB-D Salient Object DetectionPoster
622Bottom-Up Temporal Action Localization with Mutual RegularizationPoster
623On Learning to Modulate the Gradient for Fast Adaptation of Neural NetworksPoster
634Domain-Specific Mappings for Generative Adversarial Style TransferPoster
636DiVA: Diverse Visual Feature Aggregation for Deep Metric LearningPoster
637DHP: Differentiable Meta Pruning via HyperNetworksPoster
639Deep Transferring QuantizationPoster
645Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identificationPoster
648Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?Poster
666Arbitrary-Oriented Object Detection with Circular Smooth LabelPoster
671Learning Event-Driven Video Deblurring and InterpolationPoster
678Vectorizing world buildings: planar graph reconstruction by primitive detection and relationship inferencePoster
692Learning to Combine: Knowledge Aggregation for Multi-Source Domain AdaptationPoster
696CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain AdaptationPoster
700Prototype Mixture Models for Few-shot Semantic SegmentationPoster
701Webly Supervised Image Classification with Self-Contained ConfidencePoster
704Search what you want: Barrier Panelty NAS for mixed precision quantizationPoster
709Monocular 3D Object Detection via Feature Domain AdaptationPoster
718Talking-head Generation with Rhythmic Head MotionPoster
719AUTO3D: Novel view synthesis through unsupervised-learned variational viewpoints and global 3D representationsPoster
720VPN: Learning Video-Pose Embedding for Activities of Daily LivingPoster
721Soft Anchor-Point Object DetectionPoster
735Deformable GridPoster
751Soft Expert Reward Learning for Vision-and-Language NavigationPoster
754Part-aware Prototype Network for Few-shot Semantic SegmentationPoster
759Learning from Extrinsic and Intrinsic Supervisions for Domain GeneralizationPoster
761Joint Learning of Social Groups, Individuals Action and Sub-group Activities in VideosPoster
768Whole-Body Human Pose Estimation in the WildPoster
770Relative Pose Estimation of Calibrated Cameras with Known $\mathrm{SE}(3)$ InvariantsPoster
777A Novel Compressed Sensing Approach on Convolutions and Runge-Kutta MethodsPoster
779Deep Hough Transform for Semantic Line DetectionPoster
781Cross-domain Structured Landmark Detection via Progressive Topology-Adapting Deep Graph LearningPoster
7873D Human Shape and Pose from a Single Low-Resolution ImagePoster
790Learning to Balance Specificity and Invariance for In and Out of Domain GeneralizationPoster
792Contrastive Learning for Conditional Image GenerationPoster
794DLow: Diversifying Latent Flows for Diverse Human Motion PredictionPoster
798GRNet: Gridding Residual Network for Dense Point Cloud CompletionPoster
800Learning Discriminative and Compact Representations for Gait RecognitionPoster
806Blind Face Restoration via Deep Multi-scale Component DictionariesPoster
866Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methodsPoster
867Inequality-Constrained and Robust 3D Face Model FittingPoster
869Gabor Layers Enhance Network RobustnessPoster
871Conditional Image Repainting via Semantic Bridge and Piecewise Value FunctionPoster
872Learnable Cost Volume using the Cayley RepresentationPoster
884Learning to Adapt: Towards Resource-Efficient On-Device Adaptation Beyond Gradient DescentPoster
890Structured3D: A Large Photo-realistic Dataset for Structured 3D ModelingPoster
894BroadFace: Looking at Tens of Thousands of People at Once for Face RecognitionPoster
895Interpretable Visual Reasoning via Probabilistic Formulation under Natural SupervisionPoster
896Domain Adaptive Semantic Segmentation Using Weak LabelsPoster
898Knowledge Distillation Meets Self-SupervisionPoster
909Efficient Neighbourhood Consensus Networks via Submanifold Sparse ConvolutionsPoster
910Reconstructing the Noise Manifold for Image DenoisingPoster
916Occlusion-Aware Depth Estimation with Adaptive Normal ConstraintsPoster
927VisualEchoes: Spatial Image Representation Learning through EcholocationPoster
929Smooth-AP: Smoothing the Path Towards Large-Scale Image RetrievalPoster
942Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene SegmentationPoster
946Spatially Aware Multimodal Transformers for TextVQAPoster
948Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object DetectorPoster
960URIE: Universal Image Enhancement for Visual Recognition in the WildPoster
961Pyramid Multi-view Stereo Net with Self-adaptive View AggregationPoster
977SPL-MLL: Selecting Predictable Landmarks for Multi-Label LearningPoster
978Unpaired Image-to-Image Translation using Adversarial Consistency LossPoster
981Discriminability Distillation in Group Representation LearningPoster
983Monocular Expressive Body Regression through Body-Driven AttentionPoster
984Dual Adversarial Network: Toward Real Noise Removal and Noise GenerationPoster
986Linguistic Structure Guided Context Modeling for Referring Image SegmentationPoster
988Meta-Learning across Meta-Tasks for Few-Shot LearningPoster
994Federated Visual Classification with Real-World Data DistributionPoster
996Robust Re-Identification by Multiple Views Knowledge DistillationPoster
1003Defocus Deblurring Using Dual-Pixel DataPoster
1008RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex VideosPoster
1012Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective MappingPoster
1022Weighting Counts: Sequential Crowd Counting by Reinforcement LearningPoster
1024Reflection Backdoor: A Natural Backdoor Attack on Deep Neural NetworksPoster
1035Learning to Learn with Variational Information Bottleneck for Domain GeneralizationPoster
1045Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud AnalysisPoster
1046Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural NetworksPoster
1051Layered Neighborhood Expansion for Incremental Multiple Graph MatchingPoster
1057Learning To Classify Images Without LabelsPoster
1060Graph convolutional networks for learning with few clean and many noisy labelsPoster
1078Object-and-Action Aware Model for Visual Language NavigationPoster
1079A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose EstimationPoster
1086MuCAN: Multi-Correspondence Aggregation Network for Video Super-ResolutionPoster
1094Efficient Semantic Video Segmentation with Per-frame InferencePoster
1097Increasing the Robustness of Semantic Segmentation Models with Painting-by-NumbersPoster
1103Deep Spiking Neural Network: Energy Efficiency Through Time based CodingPoster
1137InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information ModelingPoster
1139Utilizing Patch-level Category Activation Patterns for Multiple Class Novelty DetectionPoster
1143People as Scene ProbesPoster
1147Mapping in a Cycle: Sinkhorn Regularized Unsupervised Learning for Point Cloud ShapesPoster
1148Label-Efficient Learning on Point Clouds using Approximate Convex DecompositionsPoster
1152TexMesh: Reconstructing Human Texture and Geometry from Monocular VideoPoster
1153Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling CostPoster
1162Point-Set Anchors for Object Detection, Instance Segmentation and Pose EstimationPoster
1163Modeling 3D shapes by Reinforcement LearningPoster
1164LST-Net: Learning a Convolutional Neural Networkwith a Learnable Sparse TransformPoster
1165Learning What Makes a Difference from Counterfactual Examples and Gradient SupervisionPoster
1171CN: Channel Normalization in Point CloudPoster
1182Rethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD ModelPoster
1184AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter LearningPoster
1186Scene Text Image Super-Resolution in the WildPoster
1220Coupling Explicit and Implicit Surface Representations for Generative 3D ModelingPoster
1227Learning Disentangled Representations with Latent Variation PredictabilityPoster
1232Deep Space-Time Video Upsampling NetworksPoster
1242Large-Scale Few-Shot Learning via Multi-Modal Knowledge DiscoveryPoster
1248Fast Video Object Segmentation using Global Context ModulePoster
1263Uncertainty-aware Weakly Supervised Action Detection from Long VideosPoster
1267Selecting Relevant Features from a Universal Representation for Few-shot LearningPoster
1276MessyTable: Instance Association in Multiple Camera ViewsPoster
1277A Unified Framework for Shot Type Classification Based on Subject Centric LensPoster
1279BSL-1K: Scaling up co-articulated sign recognition using mouthing cuesPoster
1280Parametric Hand Texture Model for 3D Hand Reconstruction and PersonalizationPoster
1290CycAs: Self-supervised Cycle Association for Learning Re-identifiable Person DescriptionsPoster
1291Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary InstructionsPoster
1292Towards Real-time MOT: A Joint Solution for Detection and Appearance EmbeddingPoster
1294A Balanced and Uncertainty-aware Approach for Partial Domain AdaptationPoster
1295Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering LossPoster
1299STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in VideosPoster
1302Hierarchical Style-based Networks for Motion SynthesisPoster
1303Who left the dogs out? 3D Animal Reconstruction with Expectation Maximization in the LoopPoster
1308Learning to Count in the Crowd from Limited Labeled DataPoster
1314SPOD: Selective Point Cloud Densification for Better Localization in Point Cloud Object DetectionPoster
1319Explainable Face RecognitionPoster
1321From Shadow Segmentation to Shadow RemovalPoster
1322Diverse and Admissible Trajectory Prediction through Multimodal Context UnderstandingPoster
1332CONFIG: Controllable Neural Face Image GenerationPoster
1337Scene Scale Estimation from Single Image in the WildPoster
1340Procedure Planning in Instructional VideosPoster
1342Funnel Activation for Visual RecognitionPoster
1354GIQA: Generated Image Quality AssessmentPoster
1355Adversarial Continual LearningPoster
1358Adapting Object Detectors with Conditional Domain NormalizationPoster
1360HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity PredictionPoster
1363Pseudo RGB-D for Self-Improving Monocular SLAM and Depth PredictionPoster
1369Interpretable and Generalizable Person Re-identification with Query-adaptive Convolution and Temporal LiftingPoster
1372Unsupervised Bayesian Deep Learning for Image Reconstruction in Compressive SensingPoster
1380Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose RefinementPoster
1381Semi-supervised Learning with a Teacher-student Network for Generalized Attribute PredictionPoster
1391Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identificationPoster
1395DPDist : Comparing Point Clouds Using Deep Point Cloud DistancePoster
1399Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic SegmentationPoster
1408FaceMix: Privacy-Preserving Facial Attribute Classification on the CloudPoster
1415Neural Re-Rendering of Humans from a Single ImagePoster
1420Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationPoster
1421PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image RestorationPoster
1422Why do These Match? Explaining the Behavior of Image Similarity ModelsPoster
1426CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute EditingPoster
1430Progressive Transformers for End-to-End Sign Language ProductionPoster
1436 Mask TextSpotter V3: Segmentation Proposal Network for Robust Scene Text SpottingPoster
1440Making Affine Correspondences Work in Camera Geometry ComputationPoster
1445Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web FacesPoster
1450Foley Music: Learning to Generate Music from VideosPoster
1453Contrastive Multiview CodingPoster
1456Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against DefensesPoster
1469Generative Low-bitwidth Data Free QuantizationPoster
1470Local Correlation Consistency for Knowledge DistillationPoster
1474Perceiving 3D Human-Object SpatialArrangements from a Single Image in the WildPoster
1483Sep-Stereo: Visual-Guided Stereophonic Audio Generation by Associating Source SeparationPoster
1485CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich AnnotationsPoster
1486Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware CluesPoster
1489Weakly-Supervised Cell Tracking via Backward-and-Forward PropagationPoster
1491SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape EstimationPoster
1493Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch NormalizationPoster
1509AMLN: Adversarial-based Mutual Learning Network for Online Knowledge DistillationPoster
1514Online Multi-modal Person Search in VideosPoster
1520Single Image Super-Resolution via a Holistic Attention NetworkPoster
1535Can You Read Me Now? Content Aware Rectification using Angle SupervisionPoster
1538Momentum Batch Normalization for Deep Learning with Small Batch SizePoster
1541AdvPC: Transferable Adversarial Perturbations on 3D Point CloudsPoster
1543Edge-aware Graph Representation Learning and Reasoning for Face ParsingPoster
1547BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy NetworkPoster
1557G-LBM: Generative Low-dimensional Background Model Estimation from Video SequencesPoster
1561H3DNet: 3D Object Detection Using Hybrid Geometric PrimitivesPoster
1567Expressive Telepresence via Modular Codec AvatarPoster
1571Cascade Graph Neural Networks for RGB-D Salient Object DetectionPoster
1585FairALM: Augmented Lagrangian Method for Training Fair Models with Little RegretPoster
1586Generating Videos of Zero-Shot Compositions of Actions and ObjectsPoster
1593ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural LanguagePoster
1600Renovating Parsing R-CNN for Accurate Multiple Human ParsingPoster
1612Multi-Task Curriculum Framework for Open-Set Semi-Supervised LearningPoster
1615Gradient-Induced Co-Saliency DetectionPoster
1616Nighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color NetworksPoster
1633SegFix: Model-Agnostic Boundary Refinement for SegmentationPoster
1636Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory PredictionPoster
1637Fast Bi-layer Neural Synthesis of One-Shot Realistic Head AvatarsPoster
1644Neural Geometric Parser for Single Image Camera CalibrationPoster
1647Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent SupervisionPoster
1652Learning Architectures for Binary NetworksPoster
1653Semantic View SynthesisPoster
1659An Analysis of Sketched IRLS for Accelerated Sparse Residual RegressionPoster
1677Relative pose from deep learned depth and affine correspondencesPoster
1698Video Super-Resolution with Recurrent Structure-Detail NetworkPoster
1702Shape Adaptor: A Learnable Resizing ModulePoster
1712Shuffle and Attend: Video Domain AdaptationPoster
1714DRG: Dual Relation Graph for Human-Object Interaction DetectionPoster
1715Flow-edge Guided Video CompletionPoster
1721Deep End-to-End Trainable Active Contours for Building Footprint DelineationPoster
1728Towards End-to-end Video-based Eye-TrackingPoster
1732Generating Handwriting via Decoupled Style DescriptorsPoster
1742LEED: Label-Free Expression Editing via DisentanglementPoster
1763Fashion Captioning: Towards Generating Accurate Descriptions with Semantic RewardsPoster
1765Reducing Language Biases in Visual Question Answering with Visually-Grounded Question EncoderPoster
1766Unsupervised Cross-Modal Alignment For Multi-Person 3D Pose EstimationPoster
1769Class-Incremental Domain AdaptationPoster
1789Anti-Bandit Neural Architecture Search for Model DefensePoster
1792Wavelet-Based Dual-Branch Neural Network for Image DemoireingPoster
1809Low light video Enhancement using Synthetic Data Produced with an Intermediate Domain MappingPoster
1810Non-Local Spatial Propagation Network for Depth CompletionPoster
1816DanbooRegion: Illustration and Cartoon Region Dataset Annotated by Real-life ArtistsPoster
1819Event Enhanced High-Quality Image RecoveryPoster
1821PackDet: Packed Long-Head Object DetectorPoster
1825A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NASPoster
1829Learning Semantic Neural Tree for Human ParsingPoster
1834Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph GenerationPoster
1848Burst Denoising via Temporally Shifted Wavelet TransformsPoster
1849JSSR: Joint Synthesis Segmentation and Registration System for 3D Multi-Model Image AnalysisPoster
1850SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen CamerasPoster
1851ScribbleBox: Interactive Annotation Framework for Video Object SegmentationPoster
1862Rethinking Pseudo-LiDAR RepresentationPoster
1868Deep Multi Depth Panoramas for View SynthesisPoster
1880MINI-Net: Multiple Instance Ranking Network for Video Highlight DetectionPoster
1889ContactPose: A Dataset of Grasps with Object Contact and Hand PosePoster
1895API-Net: Robust Generative Classifier via a Single DiscriminatorPoster
1905Bias-based Universal Adversarial Patch Attack for Automatic Check-outPoster
1912Imbalanced Continual Learning with Partitioning Reservoir SamplingPoster
1932Guided Collaborative Training for Pixel-wise Semi-Supervised LearningPoster
1938Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play FrameworkPoster
1942Efficient Transfer Learning via Joint Adaptation of Network Architecture and WeightPoster
1951Spatial Attention Pyramid Network for Unsupervised Domain AdaptationPoster
1955GSIR: Generalizable 3D Shape Interpretation and ReconstructionPoster
1956Weakly Supervised 3D Object Detection from Lidar Point CloudPoster
1960Two-phase Pseudo Label Densification for Self-training based Domain AdaptationPoster
1972Adaptive Offline Quintuplet Loss for Image-text MatchingPoster
1973Learning Object Placement by Inpainting for Compositional Data AugmentationPoster
1978Deep Vectorization of Technical DrawingsPoster
1979Shape Fitting with Deformable CAD ModelsPoster
1991An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile DevicesPoster
2006AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic PointsPoster
2013Multi-Agent Embodied Question Answering in Interactive Environments via 3D ReconstructionPoster
2014Conditional Sequential Modulation for Efficient Image RetouchingPoster
2016Segmenting Transparent Objects in the WildPoster
2035Length Controllable Image CaptioningPoster
2042Few-Shot Semantic Segmentation with Democratic Attention NetworksPoster
2044Defocus Blur Detection via Depth DistillationPoster
2054Motion Guided 3D Pose Estimation from VideoPoster
2055Reflection Separation via Multi-bounce Polarization State TracingPoster
2057SIP: Spatial Information Preservation for Fast Instance SegmentationPoster
2059SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image EditingPoster
2062Learning with Noisy Class Labels for Instance SegmentationPoster
2085Deep Image Clustering with Category-Style RepresentationPoster
2090Self-supervised Learning of Motion Representation via Scattering Local Motion CuesPoster
2094Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary DatasetsPoster
2095BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video InterpolationPoster
2100Hard negatives examples are hard, but usefulPoster
2106ReActNet: Towards Precise Binary Neural Network with Generalized Activation FunctionsPoster
2107Video Object Detection via Object-level Temporal AggregationPoster
2113Object Detection with a Unified Label Space from Multiple DatasetsPoster
2114Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3DPoster
2115Comprehensive Image Captioning via Scene Graph DecompositionPoster
2116Symbiotic Adversarial Learning for Attribute-Based Person SearchPoster
2117Amplifying Key Cues for Human-Object-Interaction DetectionPoster
2118Rethinking few-shot image classification: a good embedding is all you need?Poster
2121Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity LocalizationPoster
2129Action Localization through Continual Predictive LearningPoster
2130Generative View-Correlation Adaptation for Semi-Supervised Multi-View LearningPoster
2135ReAD: Reciprocal Attention Discriminator for Image-to-Video Re-IdentificationPoster
2136Detailed Human Shape and Pose Estimation from a Single Polarization ImagePoster
2142The Devil is in the Details: Self-Supervised Attention for Vehicle Re-IdentificationPoster
2152Improving One-stage Visual Grounding by Recursive Sub-query ConstructionPoster
2160Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed VideoPoster
2168Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-SupervisionPoster
2178Content-Consistent Matching for Domain Adaptive Semantic SegmentationPoster
2183AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text SpottingPoster
2186History Repeats Itself: Human Motion Prediction via Motion AttentionPoster
2189 Unsupervised Video Object Segmentation with Joint Hotspot TrackingPoster
2201SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine ApproachPoster
2202CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention FeaturePoster
2209MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object DetectionPoster
2212Topic-aware Multi-Label ClassificationPoster
2216Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change CaptioningPoster
2235Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain AdaptationPoster
2238Curriculum Manager for Source Selection in Multi-Source Domain AdaptationPoster
2244Powering One-shot Topological NAS with Stabilized Share-parameter ProxyPoster
2246Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic SegmentationPoster
2252Boundary-preserving Mask R-CNNPoster
2253Self-supervised Single-view 3D Reconstruction via Semantic ConsistencyPoster
2255MetaDistiller: Network Self-boosting via Meta-learned Top-down DistillationPoster
2256Learning Monocular Visual Odometry via Self-Supervised Long-Term ModelingPoster
2257The Devil is in Classification: A Simple Framework for Long-tail Instance SegmentationPoster
2266What is Learned in Deep Uncalibrated Photometric Stereo?Poster
2270Prior-based Domain Adaptive Object Detection for Hazy and Rainy ConditionsPoster
2274Adversarial Ranking Attack and DefensePoster
2279ReDro: Efficiently Learning Large-sized SPD Visual RepresentationPoster
2287Graph-Based Social Relation ReasoningPoster
2290EPNet: Enhancing Point Features with Image Semantics for 3D Object DetectionPoster
2293Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry ConsistencyPoster
2295Asynchronous Interaction Aggregation for Action DetectionPoster
2305Shape and Viewpoint without KeypointsPoster
2306Learning Attentive and Hierarchical Representations for 3D Shape RecognitionPoster
2308TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture SearchPoster
2313Associative3D: Volumetric Reconstruction from Sparse ViewsPoster
2318PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution UnitPoster
2319Memory Selection Network for Video PropagationPoster
2325Disentangled Non-local Neural NetworksPoster
2327URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale BenchmarkPoster
2329Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain MixupPoster
2330Semi-supervised Crowd Counting via Self-training on Surrogate TasksPoster
2335Dynamic R-CNN: Towards High Quality Object Detection via Dynamic TrainingPoster
2336Boosting Decision-based Black-box Adversarial Attacks with Random Sign FlipPoster
2338Knowledge Transfer via Dense Cross-layer Mutual-distillationPoster
2339Matching Guided DistillationPoster
2341Clustering-driven Deep Autoencoder for Video Anomaly DetectionPoster
2343Learning to Compose Hypercolumns for Visual CorrespondencePoster
2348Stochastic Bundle Adjustment for Efficient and Scalable Structure from MotionPoster
2353Object-based Illumination Estimation with Rendering-aware Neural NetworksPoster
2354Progressive Point Cloud Deconvolution Generation NetworkPoster
2356SSCGAN: Facial Attribute Editing via Style Skip ConnectionsPoster
2374Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in PathologyPoster
2376Learn to Propagate Reliably on Noisy Affinity GraphsPoster
2382Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture SearchPoster
2383TANet: Towards Fully Automatic Tooth ArrangementPoster
2391UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction DetectionPoster
2393GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionPoster
2394Resolution Switchable Networks for Runtime Efficient Image ClassificationPoster
2395SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationPoster
2396Learning to Detect Open Classes for Universal Domain AdaptationPoster
2400Visual Compositional Learning for Human Object Interaction DetectionPoster
2422Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn SketchesPoster
2423Rethinking Class Activation Mapping for Weakly Supervised Object LocalizationPoster
2424OS2D: One-Stage One-Shot Object Detection by Matching Anchor FeaturesPoster
2426Interpretable Neural Networks DecouplingPoster
2433Omni-sourced Webly-supervised Video RecognitionPoster
2437CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point BlendingPoster
2442Contextual-Relation Consistent Domain Adaptation for Semantic SegmentationPoster
2455Estimating People Flows to Better Count Them in Crowded ScenesPoster
2456RAN: Resolution Adaption Network for Low-resolution Face RecognitionPoster
2460Learning Feature Embeddings for Discriminant Model based TrackingPoster
2461WeightNet: Revisiting the Design Space of Weight NetworksPoster
2472Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target ShiftPoster
2475Learning Where to Focus for Efficient Video Object DetectionPoster
2481Learning Object Permanence from VideoPoster
2492Adaptive Text Recognition through Visual MatchingPoster
2497Actions as Moving PointsPoster
2499Learning to Exploit Multiple Vision Modalities by Using Grafted NetworksPoster
2501Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the WildPoster
25053D Fluid Flow Reconstruction Using Compact Light Field PIVPoster
2510Contextual Diversity for Active LearningPoster
2515Temporal Aggregate Representations for Long Term Video UnderstandingPoster
2527Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language RecognitionPoster
2530General 3D Room Layout from a Single View by Render-and-ComparePoster
2532Neural Dense Non-Rigid Structure from Motion with Latent Space ConstraintsPoster
2535Multimodal Memorability: Modeling Effects of Semantics and Decay on Video MemorabilityPoster
2538Yet Another Intermediate-Level AttackPoster
2540Topology-Change-Aware Volumetric Fusion for Dynamic Scene ReconstructionPoster
2544Early Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed ImagesPoster
2547PatchNets: Patch-based Generalizable Deep Implicit 3D Shape RepresentationsPoster
2548How does Lipschitz Regularization Influence GAN Training?Poster
2550Infrastructure-based Multi-Camera Calibration using Radial ProjectionsPoster
2553MotionSqueeze: Neural Motion Feature Learning for Video UnderstandingPoster
2559Polarized optical-flow gyroscopePoster
2561Online Meta-Learning for Multi-Source and Semi-Supervised Domain AdaptationPoster
2562An Ensemble of Epoch-wise Empirical Bayes for Few-shot LearningPoster
2568On the Effectiveness of Image Rotation for Open Set Domain AdapationPoster
2569Combining Task Predictors via Enhancing Joint PredictabilityPoster
2581Multi-Scale Positive Sample Refinement for Few-Shot Object DetectionPoster
2583Single-Image Depth Prediction Makes Feature Matching EasierPoster
2586Deep Reinforced Attention Learning for Quality-Aware Visual RecognitionPoster
2588CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action LocalizationPoster
2590Learning Joint Spatial-Temporal Transformations for Video InpaintingPoster
2593Single Path One-Shot Neural Architecture Search with Uniform SamplingPoster
2595Learning to Generate Novel Domains for Domain GeneralizationPoster
2599Continuous Adaptation for Interactive Object Segmentation by Learning from CorrectionsPoster
2601Impact of base dataset design on few-shot image classificationPoster
2605Invertible Zero-Shot Recognition FlowsPoster
2606GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of PlanesPoster
2607Location Sensitive Image Retrieval and TaggingPoster
2608Joint 3D Layout and Depth Prediction from a Single Indoor Panorama ImagePoster
2612Guessing State Tracking for Visual DialoguePoster
2614Memory-Efficient Incremental Learning Through Feature AdaptationPoster
2619Neural Voice Puppetry: Audio-Driven Facial ReenactmentPoster
2621One-Shot Unsupervised Cross-Domain DetectionPoster
2629Stochastic Frequency Masking to Improve Super-Resolution and Denoising NetworksPoster
2630Probabilistic Future Prediction for Video Scene UnderstandingPoster
2633Suppressing Mislabeled Data via Grouping and Self-AttentionPoster
2638Class-wise Dynamic Graph Convolution for Semantic SegmentationPoster
2639Character-Preserving Coherent Story VisualizationPoster
2640GINet: Graph Interaction Network for Scene ParsingPoster
2662Tensor Low-Rank Reconstruction for Semantic SegmentationPoster
2668Attentive NormalizationPoster
2678Count- and Similarity-aware Pedestrian DetectionPoster
2682TRADI: Tracking deep neural network weight distributionsPoster
2686Spatiotemporal Attacks for Embodied AgentsPoster
2697Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual AnnotationPoster
2701Unselfie: Translating Selfies to Neutral-pose Portraits in the WildPoster
2709Design and Interpretation of Universal Adversarial Patches in Face DetectionPoster
2712Few-Shot Object Detection and Viewpoint Estimation for Objects in the WildPoster
2715Weakly Supervised 3D Hand Pose Estimation via Biomechanical ConstraintsPoster
2716Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-IdentificationPoster
2718Contextual Heterogeneous Graph for Human-Object Interaction DetectionPoster
2721Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation LearningPoster
2724A Closest Point Proposal for MCMC-based Probabilistic Surface RegistrationPoster
2729Interactive Video Object Segmentation Using Global and Local Transfer ModulesPoster
2749End-to-end interpretable learning of non-blind image deblurringPoster
2756Employing Multi-Estimations for Weakly-Supervised Semantic SegmentationPoster
2760Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency DetectionPoster
2761Rethinking Image Deraining via Rain Streaks and VaporsPoster
2775Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian ProcessesPoster
2781Is Sharing of Egocentric Video Giving Away Your Biometric Signature?Poster
2783Captioning Images for a Real Use CasePoster
2800Improving Semantic Segmentation via Decoupled Body and Edge SupervisionPoster
2805Conditional Entropy Coding for Efficient Video CompressionPoster
2810Differentiable Feature Aggregation Search for Knowledge DistillationPoster
2813Attention Guided Anomaly Localization in ImagesPoster
2819Self-supervised Video Representation Learning by Pace ReasoningPoster
2820Full-Body Awareness from Partial ObservationsPoster
2822Reinforced Axial Refinement Network for Monocular 3D Object DetectionPoster
2830Self-Supervised Procedure Learning from Instructional Videos using DNNsPoster
2838Multi-view multi-object 6D pose estimation via robust scene consistency optimizationPoster
2839In-Domain GAN Inversion for Real Image EditingPoster
2841Key Frame Proposal Network for Efficient Pose Estimation in VideosPoster
2844Exchangeable Deep Neural Networks for Set-to-Set Matching and LearningPoster
2861Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNsPoster
2864Cross-Modal Weighting Network for RGB-D Salient Object DetectionPoster
2865Open-set Adversarial DefensePoster
2866Deep Image Compression using Decoder Side InformationPoster
2874Bridging the Sim-to-Real Gap: Unsupervised Learning of Scene Structure for Synthetic Data GenerationPoster
2883L2 Norm: A Generic Visualization Approach for Convolutional Neural NetworksPoster
2888Interactive Annotation of 3D Object Geometry using 2D ScribblesPoster
2889Hierarchical Kinematic Human Mesh RecoveryPoster
2890Multi-Loss Rebalancing Algorithm for Monocular Depth EstimationPoster
28973D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single ViewPoster
2903We Have So Much In Common: Modeling Semantic Relational Set Abstractions in VideosPoster
2908Joint Optimization for Multi-Person Shape Models from Markerless 3D-ScansPoster
2916Accurate RGB-D Salient Object Detection via Collaborative LearningPoster
2919Finding Your (3D) Center: 3D Object Detection Using a Learned LossPoster
2920Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object DetectionPoster
2924Two-Stream Active Query Suggestion for Large-Scale Object Detection in ConnectomicsPoster
2941Pix2Surf: Learning Parametric 3D Surface Models of Objects from ImagesPoster
2942Continuous Multimodal 6D Camera RelocalizationPoster
2943Modeling Artistic Workflows for Image Generation and EditingPoster
2945A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural NetworksPoster
2946Hidden Footprints: Learning Contextual Walkability from 3D Human TrailsPoster
2957Self-supervised learning of audio-visual objects from videoPoster
2959GAN-based Garment Generation Using Sewing Pattern ImagesPoster
2962Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture ApproachPoster
2966An LSTM Approach to Temporal 3D Object Detection in LiDAR Point CloudsPoster
2970Montonicity Prior for Cloud TomographyPoster
2971Learning Trailer Moments in Full-Length Movies with Co-Contrastive AttentionPoster
2976Preserving Semantic Neighborhoods for Robust Cross-modal RetrievalPoster
2979Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art BaselinePoster
2981Learning to Generate Grounded Visual Captions without Localization SupervisionPoster
2985Neural Hair RenderingPoster
2989JNR: Joint-based Neural Rig Representation for Compact 3D Face ModelingPoster
3004On Disentangling Spoof Traces for Generic Face Anti-SpoofingPoster
3005Streaming Object Detection for 3-D Point CloudsPoster
3006NAS-DIP: Learning Deep Image Prior with Neural Architecture SearchPoster
3007Learning to Learn in a Semi-Supervised FashionPoster
3009FeatMatch: Feature-Based Augmentation for Semi-Supervised LearningPoster
3017Exploiting Radar for Robust Perception of Dynamic ObjectsPoster
3023Seeing the Un-Scene: Learning Amodal Semantic Maps for Room NavigationPoster
3024Learning to Separate: Detecting Heavily-Occluded Objects in Urban ScenesPoster
3037Towards Causal Benchmarking of Algorithm Bias with Counterfactual SynthesisPoster
3039Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance SegmentationPoster
3056Knowledge-Based Video Question Answering with Unsupervised Scene DescriptionsPoster
3066Transformation Consistency Regularization - A Semi-Supervised Paradigm for Image-to-Image TranslationPoster
3072LIRA: Lifelong Image Restoration from Unknown Blended DistortionsPoster
3074HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationPoster
3082SOLO: Segmenting Objects by LocationsPoster
3093Learning to See in the Dark with EventsPoster
3094Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous DataPoster
3098Context-Gated ConvolutionPoster
3100Polynomial Regression Network for Variable-Number Lane DetectionPoster
3108Structural Deep Metric Learning for Room Layout EstimationPoster
3122Adaptive Task Sampling for Meta-LearningPoster
3124Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical ImagesPoster
3128Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance ProblemsPoster
3135High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided UpsamplingPoster
3136Online Ensemble Model Compression using Knowledge DistillationPoster
3137Deep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking SystemPoster
3149Efficient Residue Number System Based Winograd ConvolutionPoster
3150Robust Tracking against Adversarial AttacksPoster
3151Single-Shot Neural Relighting and SVBRDF EstimationPoster
3152Unsupervised Human 3D Pose Representation with Viewpoint and Pose DisentanglementPoster
3155Angle-based Search Space Shrinking for Neural Architecture SearchPoster
3160RobustScanner: Dynamically Enhancing Positional Clues for Robust Text RecognitionPoster
3162Towards Fast, Accurate and Stable 3D Dense Face AlignmentPoster
3170Iterative Feature Transformation for Fast and Versatile Universal Style TransferPoster
3177CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearchPoster
3182Toward Faster and Simpler Matrix Normalization via Rank-1 UpdatePoster
3186Accurate polarimetric BRDF for real polarization scene renderingPoster
3188Lensless Imaging with Focusing Sparse URA Masks in Long-Wave Infrared and its Application for Human DetectionPoster
3190Topology-Preserving Class-Incremental LearningPoster
3199Inter-Image Communication for Weakly Supervised LocalizationPoster
3205UFO$^2$: A Unified Framework Towards Omni-supervised Object DetectionPoster
3215iCaps: An Interpretable Classifier via Disentangled Capsule NetworksPoster
3220Detecting natural disasters, damage, and incidents in the wildPoster
3223Dynamic ReLUPoster
3224Acquiring Dynamic Light Fields through Coded Aperture CameraPoster
3238Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction NetworkPoster
3240Informative Sample Mining Network for Multi-Domain Image-to-Image TranslationPoster
3242Spherical Feature Transform for Deep Metric LearningPoster
3245Semantic Equivalent Adversarial Data Augmentation for Visual Question AnsweringPoster
3254Unsupervised Multi-View CNN for Salient View Selection of 3D Objects and ScenesPoster
3266FDTS: Fast Diverse-Transformation Search for Object Detection and BeyondPoster
3268Peeking into occluded joints: A novel framework for crowd pose estimationPoster
3271RubiksNet: Learnable 3D-Shift for Efficient Video Action RecognitionPoster
3281Deep Hashing with Active Pairwise SupervisionPoster
3293Graph Edit Distance Reward: Learning to Edit Scene GraphPoster
3295Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene ParsingPoster
3301Feature-metric Loss for Self-supervised Learning of Depth and EgomotionPoster
3304Propagating Over Phrase Relations for One-Stage Visual GroundingPoster
3307Adversarial Semantic Data Augmentation for Human Pose EstimationPoster
3314Deep Novel View Synthesis from Unstructured InputPoster
3315Face Anti-Spoofing via disentangled representation learningPoster
3317Prime-Aware Adaptive DistillationPoster
3318Meta-Learning with Network PruningPoster
3323Spiral Generative Network for Image ExtrapolationPoster
3324Scene Sketcher: Fine-grained Image Retrieval with Scene SketchPoster
3337Few-shot Compositional Font Generation with Dual MemoryPoster
3338PUGeo-Net: A Geometry-centric Network for 3D Point Cloud UpsamplingPoster
3339Content-aware Video SummarizationPoster
3348Handcrafted Outlier Detection RevisitedPoster
3359The Average Mixing Kernel SignaturePoster
3361BCNet: Learning Body and Cloth Shape from A Single ImagePoster
3372Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in VideosPoster
3375Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image RestorationPoster
3382Polysemy Deciphering Network for Human-Object Interaction DetectionPoster
3384Small-Task Incremental LearningPoster
3386Learning Graph-Convolutional Representations for Point Cloud DenoisingPoster
3397Semantic Line Detection Using Mirror Attention and Comparative Ranking and MatchingPoster
3398A Differentiable Recurrent Surface for Asynchronous Event-Based DataPoster
3399Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw PatchesPoster
3400LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow EstimationPoster
3405Microscopy Image Restoration with Deep Wiener-Kolmogorov filtersPoster
3408ScanRefer: 3D Object Localization in RGB-D Scans using Natural LanguagePoster
3411JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point CloudsPoster
3412Motion-Excited Sampler: Video Adversarial Attack with Sparked PriorPoster
3414An Inference Algorithm for Multi-Label MRF-MAP Problems with Clique Size 100Poster
3425Dual refinement underwater object detection networkPoster
3429Learning to Visually Localize Multiple Sound Sources via A Two-stage MannerPoster
3457Task-Aware Quantization Network for JPEG Image CompressionPoster
3472Learning Deep Conditional Target Densities for Accurate RegressionPoster
3478CLOTH3D: Clothed 3D HumansPoster
3484Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal ImagesPoster
3485CLNet: A Compact Latent Network for Fast Adjusting Siamese TrackerPoster
3488Occlusion-Aware Siamese Network for Human Pose EstimationPoster
3492Learning to Predict Salient Faces: A Novel Audio-Visual Saliency ModelPoster
3495NormalGAN: Learning Detailed 3D Human from a Single RGB-D ImagePoster
3498Model-based disentanglement of lens occlusionsPoster
3506Rotation-robust Intersection over Union for 3D Object DetectionPoster
3508New Threats against Object Detector with Non-Local BlockPoster
3516Self-Supervised CycleGAN for Object-Preserving Image-to-Image Domain AdaptationPoster
3533On the Usage of the Trifocal Tensor in Motion SegmentationPoster
35393D-Rotation-Equivariant Quaternion Neural NetworksPoster
3540InterHand2.6M: A New Large-scale Dataset and Baseline for 3D Single and Interacting Hand Pose Estimation from a Single RGB ImagePoster
3548Active Crowd Counting with Limited SupervisionPoster
3551Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic GuidancePoster
3563Hierarchical Visual-Textual Graph for Temporal Activity Localization via LanguagePoster
3568Do Not Mask What You Do Not Need to Mask: a Parser Free Virtual Try-OnPoster
3577NODIS: Neural Ordinary Differential Scene UnderstandingPoster
3586Assembling Modality Representations via Attention ConnectionsPoster
3588Learning Propagation Rules for Attribution Map GenerationPoster
3590Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task InterferencePoster
3606Learning Predictive Models from Observation and InteractionPoster
3607Unifying Deep Local and Global Features for Image SearchPoster
3610Human Body Model Fitting by Learned Gradient DescentPoster
3611DDGCN: A Dynamic Directed Graph Convolutional Network for Action RecognitionPoster
3615Learning latent representions across multiple data domains using Lifelong VAEGANPoster
3620DVI: Depth Guided Video Inpainting for Autonomous DrivingPoster
3627Incorporating Reinforced Adversarial Learning in Autoregressive Image GenerationPoster
3632APRICOT: A Dataset of Physical Adversarial Attacks on Object DetectionPoster
3640Visual Question Answering on Image SetsPoster
3643Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of HotspotsPoster
3644Placepedia: Comprehensive Place Understanding with Multi-Faceted AnnotationsPoster
3649Depth Estimation by Learning Triangulation and Densification of Sparse Points for Multi-view StereoPoster
3654Dynamic Low-light Imaging with Quanta Image SensorsPoster
3668Disambiguating Monocular Depth Estimation with a Single TransientPoster
3672DSDNet: Deep Structured self-Driving NetworkPoster
3679QUEST: Quantized embedding space for transferring knowledgePoster
3685EGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma DiagnosisPoster
3689Backpropagated Gradient Representations for Anomaly DetectionPoster
3694Dense RepPoints: Representing Visual Objects with Dense Point SetsPoster
3696On Dropping Clusters to Regularize Graph Convolutional Neural NetworksPoster
3702Adaptive Video Highlight Detection by Learning from User HistoryPoster
3705Automated Data Augmentation Significantly Improves 3D Object DetectionPoster
3719DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape ReconstructionPoster
3720SPAN: Spatial Pyramid Attention Network for Image Manipulation DetectionPoster
3721Transferring Domain Shift Across Tasks for Zero-shot Domain adaptationPoster
3723YOLO in the Dark - Domain Adaptation Method for Merging Multiple Models -Poster
3739Identity-Aware Multi-Sentence Video DescriptionPoster
3742VQA-LOL: Visual Question Answering under the Lens of LogicPoster
3751Piggyback GAN: Efficient Lifelong Learning for Image Conditioned GenerationPoster
3752TRRNet: Tree Relation Reasoning for Compositional Visual Question AnsweringPoster
3764Mining Inter-Video Proposal Relations for Video Object DetectionPoster
3768TVR: A Large-Scale Dataset for Video-Subtitle Moment RetrievalPoster
3769Minimum Class Confusion for Versatile Domain AdaptationPoster
3790Large Batch Optimization for Object Detection: Training COCO in 12 MinutesPoster
3792Towards Practical and Efficient High-Resolution HDR Deghosting with CNNPoster
3794Self-Supervised Differentiable Rendering for Monocular 3D Object DetectionPoster
3796Shape Prior Deformation for Categorical 6D Object Pose and Size EstimationPoster
3801Dynamic and Static Context-aware LSTM for Multi-agent Motion PredictionPoster
3802Image-based table recognition: data, model, and evaluationPoster
3803Group Activity Prediction with Sequential Relational Anticipation ModelPoster
3805PiP: Planning-informed Trajectory Prediction for Autonomous DrivingPoster
3807PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional LayerPoster
3819Hierarchical Context Embedding for Region-based Object DetectionPoster
3822Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image RecognitionPoster
3830Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane DetectionPoster
3833Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph ConstructionPoster
3837MEAD: A Large-scale Audio-visual Dataset for Emotional Talking Face GenerationPoster
3850Detecting Human-Object Interactions with Action Co-occurrence PriorsPoster
3853Learning Connectivity of Neural Networks from a Topological PerspectivePoster
3867JSTASR: Joint Size and Transparency-Aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect RemovalPoster
3872Learning Object-aware Anchor-free Networks for Real-time Object TrackingPoster
3884Object Tracking using Spatio-Temporal Networks for Future Prediction LocationPoster
3892Pillar-based Object Detection for Autonomous DrivingPoster
3902Sparse Adversarial Attack via Perturbation FactorizationPoster
39253D Scene Reconstruction from a Single ViewportPoster
3935Learning to Optimize Domain Specific Normalization for Domain GeneralizationPoster
3937Self-supervised Outdoor Scene RelightingPoster
3947LC-VSLAM: Real-time Tracking and Bundle Adjustment in Line-CloudPoster
3951Leveraging Acoustic Images for Effective Self-Supervised Audio Representation LearningPoster
3960Learning Joint Visual Semantic Matching Embeddings for Language-guided RetrievalPoster
3990Globally Optimal and Efficient Vanishing Point Estimation in Atlanta WorldPoster
3992StyleGAN2 Distillation for Feed-forward Image ManipulationPoster
3997Self-Prediction for Joint Instance and Semantic Segmentation of Point CloudsPoster
3999Learning Disentangled Representations via Mutual Information EstimationPoster
4010Challenge-Aware RGBT TrackingPoster
4019Fully Trainable and Interpretable Non-Local Sparse Models for Image RestorationPoster
4034AutoSimulate: (Quickly) Learning Synthetic Data GenerationPoster
4035LatticeNet: Towards Lightweight Image Super-resolution with Lattice BlockPoster
4042Learning from Scale-Invariant Examples for Domain Adaptation in Semantic SegmentationPoster
4046Active Visual Information Gathering for Vision-Language NavigationPoster
4061Deep Hough-Transform Line PriorsPoster
4065Unsupervised Shape and Pose Disentanglement for 3D MeshesPoster
4066CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event DetectionPoster
4072Inclusive GAN: Improving Data and Minority Coverage in Generative ModelsPoster
4076SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsPoster
4095Dive Deeper Into Box for Object DetectionPoster
4097PG-Net: Pixel to Global Matching Network for Visual TrackingPoster
4098Why Are Deep Representations Good Perceptual Quality Features?Poster
4101Geometric Estimation via Robust Subspace RecoveryPoster
4102Latent Embedding Feedback and Discriminative Features for Zero-Shot ClassificationPoster
4107Human Correspondence Consensus for 3D Object Semantic UnderstandingPoster
4111Learning Memory Augmented Cascading Network for Compressed Sensing of ImagesPoster
4112Least squares surface reconstruction on arbitrary domainsPoster
4116Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal ImageryPoster
4118Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region FittingPoster
4120DADA: Differentiable Automatic Data AugmentationPoster
4123SceneCAD: Predicting Object Alignments and Layouts in RGB-D ScansPoster
4125Kinship Identification through Joint Learning Using Kinship Verification EnsemblePoster
4152Kernelized Memory Network for Video Object SegmentationPoster
4160A Single Stream Network for Robust and Real-time RGB-D Salient Object DetectionPoster
4165Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic SegmentationPoster
4167Temporal Keypoint Matching and Refinement Network for Pose Estimation and TrackingPoster
4168Neural Point-Based GraphicsPoster
4171FHDe$^2$Net: Full High Definition Demoireing NetworkPoster
4172Learning Structural Similarity of User Interface Layouts using Graph NetworksPoster
4174NAS-Count: Counting-by-Density with Neural Architecture SearchPoster
4185Towards Generalization Across Depth for Monocular 3D Object DetectionPoster
4197Margin-Mix: Semi--Supervised Learning for Face Expression RecognitionPoster
4198Principal Feature Visualisation in Convolutional Neural NetworksPoster
4211Progressive Refinement Network for Occluded Pedestrian DetectionPoster
4214MonoPort: Monocular Real-Time Volumetric TeleportationPoster
4217The Mapillary Traffic Sign Dataset for Detection and Classification on a Global ScalePoster
4220Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object InteractionPoster
4234Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational AutoencodersPoster
4238SEN: A Novel Dissimilarity Measure for Prototypical Few-Shot Learning NetworksPoster
4241Kinematic 3D Object Detection in Monocular VideoPoster
4257Describing Unseen Videos via Multi-Modal Cooperative Dialog AgentsPoster
4270SACA Net: Cybersickness Assessment of Individual Viewers for VR Content via Graph-based Symptom Relation EmbeddingPoster
4272End-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-AttentionPoster
4297Know Your Surroundings: Exploiting Scene Information for Object TrackingPoster
4298Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free CasesPoster
4300Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture DetectionPoster
4302DeepLandscape: Adversarial Modeling of Landscape VideosPoster
4304GANwriting: Content-Conditioned Generation of Styled Handwritten Word ImagesPoster
4306Spatial-Angular Interaction for Light Field Image Super-ResolutionPoster
4314BATS: Binary ArchitecTure SearchPoster
4319A Closer Look at Local Aggregation Operators in Point Cloud AnalysisPoster
4322Look here! A parametric learning based approach to redirect visual attentionPoster
4324Variational Diffusion Autoencoders with Random Walk SamplingPoster
4328Adaptive Variance Based Label Distribution Learning For Facial Age EstimationPoster
4334Connecting the Dots: Detecting Adversarial Perturbations Using Context InconsistencyPoster
4342Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic RepresentationsPoster
4350VarSR: Variational Super-Resolution Network for Very Low Resolution ImagesPoster
4353Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion SegmentationPoster
4355Towards Recognizing Unseen Categories in Unseen DomainsPoster
4362Square Attack: a query-efficient black-box adversarial attack via random searchPoster
4363You Are Here: Geolocation by Embedding Maps and ImagesPoster
4364Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image SegmentationPoster
4366From Video to Stability: Learning Dynamics from Kinematics of Human MotionPoster
4368LevelSet R-CNN: A Deep Variational Method for Instance SegmentationPoster
4374Efficient Scale-permuted Backbone with Learned Resource DistributionPoster
4375Bridging Multiple Distant Domains by Learning Transferable Shapes from SketchPoster
4377Bridging Knowledge Graphs to Generate Scene GraphsPoster
4386Implicit Latent Variable Model for Scene-Consistent Motion ForecastingPoster
4387Learning Visual Commonsense for Robust Scene Graph GenerationPoster
4396MPCC: Matching Priors and Conditionals for ClusteringPoster
4405PointAR: Efficient Lighting Estimation for Mobile Augmented RealityPoster
4408Discrete Point Flow Networks for Efficient Point Cloud GenerationPoster
4410Accelerating Deep Learning with Millions of ClassesPoster
4416Password-conditioned Anonymization and Deanonymization with Face Identity TransformersPoster
4421Inertial Safety from Structured LightPoster
4424PointTriNet: Learned Triangulation of 3D Point SetsPoster
4433Toward unsupervised, multi-object discovery in large-scale image collectionsPoster
4474Deep View Synthesis From Colored 3D PointCloudsPoster
4495Consensus-Aware Visual-Semantic Embedding for Image-Text MatchingPoster
4499Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth DenoisingPoster
4510Sat2Graph: Road Graph Extraction through Graph-Tensor EncodingPoster
4513Cross-task Transfer for Multimodal Aerial Scene ClassificationPoster
4522Polarimetric Multi-View Inverse RenderingPoster
4524SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side InformationPoster
4531Improving Recognition with Unlabeled Faces in the WildPoster
4532NeuRoRA: Neural Robust Rotation AveragingPoster
4535SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenesPoster
4544Unsupervised Learning of Optical Flow with Deep Feature SimilarityPoster
4548Blended Grammar Network for Human ParsingPoster
4549A Crisis is an Opportunity: Discriminative Patch-based and Piece-wise Planar-based Unsupervised Depth Estimation in Indoor EnvironmentsPoster
4553Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsPoster
4582Adaptive Mixture Regression Network with Local Counting Map for Crowd CountingPoster
4583BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive ImagingPoster
4584Ultra Fast Structure-aware Deep Lane DetectionPoster
4585Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video ReassemblingPoster
4600Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNNPoster
4614Exclusivity-Consistency Regularized Knowledge Distillation for Face RecognitionPoster
4617Learning Camera-Aware Noise ModelsPoster
4619The Whole is greater than the sum of its Nonrigid PartsPoster
4625Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud RegistrationPoster
4628In Defense of Graph Inference Algorithms for Weakly Supervised Object LocalizationPoster
4629Environment-agnostic Multitask Learning for Natural Language Grounded NavigationPoster
4631TPFN: Apply Outer Product along Time for Multimodal Sentiment Analysis Fusion on Imperfect DataPoster
4637ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component AnalysisPoster
4644Learning with Privileged Information for Efficient Image Super-ResolutionPoster
4652Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-IdentificationPoster
4655Autoencoder-based Graph Construction for Semi-supervised LearningPoster
4670Virtual Multi-view Fusion for 3D Semantic SegmentationPoster
4672Decoupling GCN with DropGraph Module for Skeleton-Based Action RecognitionPoster
4676Deep Shape from PolarizationPoster
4682A Boundary Based Out-Of-Distribution Classifier for Generalized Zero-Shot LearningPoster
4690Mind the Discriminability: Asymmetric Adversarial Domain AdaptationPoster
4694SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D CoordinatesPoster
4729Simultaneous Detection and Tracking with Motion Modelling for Multiple Object TrackingPoster
4736Deep FusionNet for Point Cloud Semantic SegmentationPoster
4750Deep Material Recognition in Light-Fields via Disentanglement of Spatial and Angular InformationPoster
4757Dual Adversarial Network for Deep Active LearningPoster
4763Fully Convolutional Networks for Continuous Sign Language RecognitionPoster
4771Self-adapting confidence estimation for stereoPoster
4793Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic AttentionPoster
4796AutoSTR: Efficient Backbone Search for Scene Text RecognitionPoster
4802Pretraining Matters: A Two-Stage Design for Unsupervised Image ClassificationPoster
4810Adversarial Training with Bi-directional Likelihood Regularization for Visual ClassificationPoster
4830Faster AutoAugment: Learning Augmentation Strategies using BackpropagationPoster
4836Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose EstimationPoster
4845Boundary-Aware Cascade Networks for Temporal Action SegmentationPoster
4865Towards Content-independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature AggregationPoster
4871Inference Graphs for CNN InterpretationPoster
4879An End-to-End OCR Text Re-organization Sequence Learning for Rich-text Detail Image ComprehensionPoster
4889Improving Query Efficiency of Black-box Adversarial AttackPoster
4890Self-similarity Student for Partial Label Histopathology Image SegmentationPoster
4912BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributionsPoster
4913A Decoupled Learning Scheme for Real-world Burst Denoising from Raw ImagesPoster
4920Global-and-Local Relative Position Embedding for Unsupervised Video SummarizationPoster
4924Real-World Blur Dataset for Learning and Benchmarking Deblurring AlgorithmsPoster
4927SPARK: Spatial-aware Online Incremental Attack Against Visual TrackingPoster
4943CenterNet Heatmap Propagation for Real-time Video Object DetectionPoster
4959Hierarchical Dynamic Filtering Network for RGB-D Salient Object DetectionPoster
4963SOLAR: Second-Order Loss and Attention for Image RetrievalPoster
4964Fixing Localization Errors to Improve Image ClassificationPoster
4968PatchPerPix for Instance SegmentationPoster
4997Attend and SegmentPoster
5004Accelerating CNN Training by Pruning Activation GradientsPoster
5010Global and Local Enhancement Networks For Paired and Unpaired Image EnhancementPoster
5041Probabilistic Anchor Assignment with IoU Prediction for Object DetectionPoster
5056Eyeglasses 3D shape reconstruction from a single face imagePoster
5061Temporal Complementary Learning for Video Person Re-IdentificationPoster
5063HoughNet: Integrating near and long-range evidence for bottom-up object detectionPoster
5066Graph Wasserstein Correlation Analysis for Movie RetrievalPoster
5068Revisiting RCNN for Action Detection in VideosPoster
5090Full-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of PolarizationPoster
5095A Flexible Recurrent Residual Pyramid Network for Video Frame InterpolationPoster
5099Learning Enriched Features for Real Image Restoration and EnhancementPoster
5105Detail Preserved Point Cloud Completion via Separated Feature AggregationPoster
5115LabelEnc: A New Intermediate Supervision Method for Object DetectionPoster
5118Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point SetsPoster
5130PAMS: Quantized Super-Resolution via Parameterized Max ScalePoster
5131SSN: Shape Signature Networks for Multi-class Object Detection from Point CloudsPoster
5134OID: Outlier Identifying and Discarding in Blind Image DeblurringPoster
5140Few-Shot Single-View 3-D Object Reconstruction with Compositional PriorsPoster
5150Enhanced Sparse Model for Blind DeblurringPoster
5155SumGraph: Video Summarization via Recursive Graph ModelingPoster
5164Feature Normalized Knowledge Distillation for Image ClassificationPoster
5170A Metric Learning Reality CheckPoster
5190FTL: A universal framework for training low-bit DNNs via Feature TransferPoster
5192XingGAN for Person Image GenerationPoster
5203GATCluster: Self-Supervised Gaussian-Attention Network for Image ClusteringPoster
5204VCNet: A Robust Approach to Blind Image InpaintingPoster
5205Learning to Predict Context-adaptive Convolution for Semantic SegmentationPoster
5211EfficientFCN: Holistically-guided Decoding for Semantic SegmentationPoster
5227GroSS: Group-Size Series Decomposition for Grouped Architecture SearchPoster
5291Efficient Adversarial Attacks for Visual Object TrackingPoster
5299Globally-Optimal Event Camera Motion EstimationPoster
5301Weakly-supervised Learning of Human DynamicsPoster
5305Journey Towards Tiny Perceptual Super-ResolutionPoster
5308What makes fake images detectable? Understanding properties that generalizePoster
5313Embedding Propagation: Smoother Manifold for Few-Shot ClassificationPoster
5315Category Level Object Pose Estimation via Neural Analysis-by-SynthesisPoster
5320High-Fidelity Synthesis with Disentangled RepresentationPoster
5323PL1P - Point-line Minimal Problems under Partial Visibility in Three ViewsPoster
5327Prediction, Recovery and Identification: Adaptive Low-Resolution Person Re-IdentificationPoster
5328Learning Canonical Representations for Scene Graph to Image GenerationPoster
5331Adversarial Robustness on In- and Out-Distribution Improves ExplainabilityPoster
5333Deformable Style TransferPoster
5336Aligning Videos in Space and TimePoster
5346Neural Wireframe Renderer: Learning Wireframe to Image TranslationsPoster
5351RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function SoftmaxPoster
5368Testing the Safety of Self-driving Vehicles by Simulating Perception and PredictionPoster
5369Determining the Relevance of Features for Deep Neural NetworksPoster
5372Weakly Supervised Semantic Segmentation with Boundary ExplorationPoster
5381GANhopper: Multi-Hop GAN for Unsupervised Image-to-Image TranslationPoster
5385DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wildPoster
5394Multi-view adaptive graph convolutions for graph classificationPoster
5406Universal Self-Training for Unsupervised Domain AdaptationPoster
5409Weight Decay Scheduling and Knowledge Distillation for Active LearningPoster
5414HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNsPoster
5423Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and LearningPoster
5424Geometry Constrained Weakly Supervised Object LocalizationPoster
5445Duality Diagram Similarity: a generic framework for initialization selection in task transfer learningPoster
5448OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained ClusteringPoster
5450Mining self-similarity: Label super-resolution with epitomic representationsPoster
5480AE-OT-GAN: Training GANs from data specific latent distributionPoster
5488Null-sampling for Invariant and Interpretable RepresentationsPoster
5491Guiding Monocular Depth Estimation Using Depth Attention-VolumePoster
5494Tracking Emerges by Looking Around Static Scenes, with Neural 3D MappingPoster
5495Boosting Weakly Supervised Object Detection with Progressive Knowledge TransferPoster
5496BézierSketch: A generative model for scalable vector sketchesPoster
5530Semantic Relation Preserving Knowledge Distillation for Image-to-Image TranslationPoster
5551Domain Adaptation through Task DistillationPoster
5563PatchAttack: A Black-box Texture-based Attack with Reinforcement LearningPoster
5564More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental LearningPoster
5568Extending and Analyzing Self-Supervised Learning Across DomainsPoster
5573Multi-Source Open-Set Deep Adversarial Domain AdaptationPoster
5576Neural Batch Sampling with Reinforcement Learning for Semi-Supervised Anomaly DetectionPoster
5581LEMMA: A Multiview Dataset for Learning Multi-agent Multi-task ActivitiesPoster
5589Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From ImagesPoster
5592Accurate Optimization of Weighted Nuclear Norm for Non-Rigid Structure from MotionPoster
5605Proposal based Video CompletionPoster
5608HGNet: Hybrid Generative Network for Zero-shot Domain AdaptationPoster
5622Beyond Monocular Deraining: Paired Rain Removal Networks via Unpaired Semantic UnderstandingPoster
5625DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural NetworksPoster
5635All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion ModelingPoster
5643A Broader Study of Cross-Domain Few-Shot LearningPoster
5645Practical Poisoning Attacks on Neural NetworksPoster
5669Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identificationPoster
5671Learn distributed GAN with Temporary DiscriminatorsPoster
5673SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision SystemsPoster
5686Improving Adversarial Robustness by Enforcing Local and Global CompactnessPoster
5687TopoGAN: A Generative Adversarial Approach to Topology-Aware Road SegmentationPoster
5695Channel selection using Gumbel softmaxPoster
5696Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identificationPoster
5698An Efficient Training Framework for Reversible Neural ArchitecturesPoster
5717Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised SegmentationPoster
5744Freeform Structured LightPoster
5750One-pixel Signature: Characterizing CNN Classifiers for Backdoor DetectionPoster
5752Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer LearningPoster
5757Structure-Aware Generation Network for Recipe Generation from ImagesPoster
5769A Simple and Effective Framework for Pairwise Deep Metric LearningPoster
5772Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-LearnerPoster
5775A Recurrent Transformer Network for Novel View Action SynthesisPoster
5777Multi-view Action Recognition using Cross-view Video PredictionPoster
5794Learning Discriminative Feature with CRF for Unsupervised Video Object SegmentationPoster
5809SMART: Simultaneous Multi-Agent Recurrent Trajectory PredictionPoster
5818Label-Driven Reconstruction for Domain Adaptation in Semantic SegmentationPoster
5831Efficient Outdoor 3D Point Cloud Semantic Segmentation for Critical Road Objects and Distributed ContextsPoster
5849Attributional Robustness Training using Input-Gradient Spatial AlignmentPoster
5855How to Train Your Event Camera Neural NetworkPoster
5863Spatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement LearningPoster
5865On the Importance of Data Augmentation for Object DetectionPoster
5875DA-NAS: Data Adapted Pruning for Efficient Neural Architecture SearchPoster
5879A Closer Look at Generalisation in RAVENPoster
5884Supervised Edge Attention Network for Accurate Image Instance SegmentationPoster
5888Discriminative Partial Domain Adversarial NetworkPoster
5893Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion ModelPoster
5894Deep Cross-species Feature Learning for Animal Face Recognition via Residual Interspecies Equivariant NetworkPoster
5897Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed ScenesPoster
5906Sound2Sight: Generating Visual Dynamics from Sound and ContextPoster
59133D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object DetectionPoster
5921NoiseRank: Unsupervised Label Noise Reduction with Dependence ModelsPoster
5930Fast Adaptation to Super-Resolution Networks via Meta-LearningPoster
5931TP-LSD: Tri-Points Based Line Segment DetectorPoster
5940Spatially-Adaptive Convolution for Efficient Point-Cloud SegmentationPoster
5955An Attention-driven Two-stage Clustering Method for Unsupervised Person Re-IdentificationPoster
5989Toward Fine-grained Facial Expression ManipulationPoster
5992Adaptive Object Detection with Dual Multi-Label PredictionPoster
6007Table Structure Recognition using Top-Down and Bottom-Up CuesPoster
6013Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-EncoderPoster
6018Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous EnvironmentsPoster
6021Boundary Content Graph Neural Network for Temporal Action Proposal GenerationPoster
6037Pose Augmentation: Class-agnostic Object Pose Transformation for Object RecognitionPoster
6051VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment RetrievalPoster
6054Attention-Based Query Expansion LearningPoster
6055Interpretable Foreground Object Search As Knowledge DistillationPoster
6056Improving Knowledge Distillation via Category StructurePoster
6059High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face ImagesPoster
6066Attentive Prototype Few-shot Learning with Capsule Network-based EmbeddingPoster
6083Weakly Supervised Instance Segmentation by Learning Annotation Consistent InstancesPoster
6091DA4AD: End-to-end Deep Attention Aware Features Aided Visual Localization for Autonomous DrivingPoster
6109Visual-Relation Conscious Image Generation from Structured-TextPoster
6114Patch-wise Attack for Fooling Deep Neural NetworkPoster
6141Feature Pyramid TransformerPoster
6153MABNet: A Lightweight Stereo Network Based on Multibranch Adjustable Bottleneck ModulePoster
6159Guided Saliency Feature Learning for Person Re-identification in Crowded ScenesPoster
6188Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency DetectionPoster
6192Lightweight Statistical Explanations for Deep Neural NetworksPoster
6207Deep Graph Matching via Blackbox Differentiation of Combinatorial SolversPoster
6215Video Representation Learning by Learning to Tell Motions ApartPoster
6231Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature AdaptationPoster
6236Variational Connectionist Temporal ClassificationPoster
6258End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose EstimationPoster
6259Orderly Disorder in Point Cloud DomainPoster
6272Deep Decomposition Learning for Inverse Imaging ProblemsPoster
6287FLOT: Scene Flow Estimation by Learned Optimal Transport on Point CloudsPoster
6294Accurate Reconstruction of Oriented 3D Points using Affine CorrespondencesPoster
6316Volumetric Transformer NetworksPoster
6332360º Camera Alignment via SegmentationPoster
6334A Novel Line Integral Transform for 2D Affine Invariant Shape RetrievalPoster
6336Explainable Graph Networks for Weakly-supervised Learning of Visual RelationsPoster
6345Guided Semantic FlowPoster
6393Document Structure Extraction using Prior Based HighResolution Hierarchical Semantic SegmentationPoster
6416Measuring the importance of temporal features in video saliencyPoster
6421Searching Efficient 3D Architectures with Sparse Point-Voxel ConvolutionPoster
6424Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial ImagesPoster
6425Online Continual Learning under Extreme Memory ConstraintsPoster
6436Learning to Cluster under Domain ShiftPoster
6438Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded ManifoldsPoster
6440Improving Optical Flow on a Pyramid LevelPoster
6446Procrustean Regression Networks: Learning 3D Structure of Non-Rigid Objects from 2D AnnotationsPoster
6474Learning to Learn Parameterized Classification Networks for Scalable Input ImagesPoster
6476Stereo Event-based Particle Tracking Velocimetry for 3D Fluid Flow ReconstructionPoster
6515Simplicial Complex based Point Correspondence between Images warped onto ManifoldsPoster
6535Neural Message Passing on Hybrid Spatio-Temporal Visual and Symbolic Graphs for Video UnderstandingPoster
6559Distance-Normalized Unified Representation for Monocular 3D Object DetectionPoster
6576Sequential Deformation for Accurate Scene Text DetectionPoster
6579Where to Explore Next? ExHistCNN for History-aware Autonomous 3D ExplorationPoster
6591Semi-Supervised Segmentation based on Error-Correcting SupervisionPoster
6621Quantum-soft QUBO Suppression for Accurate Object DetectionPoster
6624Label-similarity Curriculum LearningPoster
6627Recurrent Image Annotation With Explicit Inter-Label DependenciesPoster
6628Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-ResolutionPoster
6637SimPose: Effectively Learning DensePose and Surface Normal of People from Simulated DataPoster
6639ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face ImagesPoster
6693Differentiable Joint Pruning and Quantization for Hardware EfficiencyPoster
6697Learning to Generate Customized Dynamic 3D Facial ExpressionsPoster
6698LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned DescriptorsPoster
6709Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly DetectionPoster
6717Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration.Poster
6719Jointly De-biasing Face Recognition and Demographic Attribute EstimationPoster
6721Regularized Loss for Weakly Supervised Single Class SegmentationPoster
6736Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural NetworksPoster
6746Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output ObservationsPoster
6748Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear ActivationsPoster
6753Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial NetworksPoster
6754Learning to Learn Words from Visual ScenesPoster
6765On Transferability of Histological Tissue Labels in Computational PathologyPoster
6770Learning actionness via long-range temporal order verificationPoster
6773Fully Embedding Fast Convolutional Networks on Pixel Processor ArraysPoster
6775Character Region Attention For Text SpottingPoster
6795Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural NetworkPoster
6796Dual Mixup Regularized Learning for Adversarial Domain AdaptationPoster
6814Robust and On-the-fly Dataset Denoising for Image ClassificationPoster
6833Imaging Behind Occluders Using Two-Bounce LightPoster
6837Improving Object Detection with Selective Self-supervised Self-trainingPoster
6873Deep Local Shapes: Learning Local SDF Priors for Detailed 3D ReconstructionPoster
6884Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive LearningPoster
6895Adversarial Data Augmentation via Deformation StatisticsPoster
6926Neural Predictor for Neural Architecture SearchPoster
6927Learning Permutation Invariant Representations using Memory NetworksPoster
6936Feature Space Augmentation for Long-Tailed DataPoster
6940Laying the Foundations of Deep Long-Term Crowd Flow PredictionPoster
6965Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance LearningPoster
6967Fairness by Learning Orthogonal Disentangled RepresentationsPoster
6977Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without AnnotationPoster
6979On Diverse Asynchronous Activity AnticipationPoster
6994Representative-Discriminative Learning for Open-set Land Cover Classification of Satellite ImageryPoster
7020Structure-Aware Human-Action GenerationPoster
7035Towards Efficient Coarse-to-Fine Networks for Action and Gesture RecognitionPoster
7036$S^3$Net: Semantic-Aware Self-Supervised Depth Estimation with Monocular Videos and Synthetic DataPoster
7037Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot LearningPoster
7039Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural NetworksPoster
7093UNITER: UNiversal Image-TExt Representation LearningPoster
7133$Oscar$: Object-Semantics Aligned Pre-training for Vision-and-Language TasksPoster
7177Improving Face Recognition from Hard Samples via Distribution Distillation LossPoster
7198Extract and Merge: Superpixel Segmentation with Regional AttributesPoster
7202Spatial-Adaptive Network for Single Image DenoisingPoster
7263Physics-based Feature Dehazing NetworksPoster
7305Learning Surrogates via Deep EmbeddingPoster
7352Master-Slave Interaction Model: An Asymmetric Modelling for Action AssessmentPoster
7358High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential ModulationPoster
7362Instance-Aware Embedding for Point Cloud Instance SegmentationPoster
7424Self-Paced Deep Regression Forests with Consideration on Underrepresented SamplesPoster
7451Manifold Projection for Adversarial Defense on Face RecognitionPoster
7467Weakly-Supervised Learning with Side Information for Noisy Labeled ImagesPoster
7476Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak SupervisionPoster
7513SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace DetectionPoster
7548Modeling the Space of Point Landmark Constrained DiffeomorphismsPoster
7579PieNet: Personalized Image Enhancement NetworkPoster
7614Statistical Outlier Identification in Pose Graphs Using CyclesPoster
7625Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and TexturePoster
7627Solving phase retrieval with a learned referencePoster
7644Dual Grid Net: Hand Mesh VertexRegression from Single Depth MapsPoster

quick links

Diamond Partners

Platinum Partners

Gold Partners

Silver Partners

Start-Up / Exhibiting Partners