ECCV2020将于2020年8月23-28日在线上举行，今年共接受了1361篇论文，本文是接收论列表的第二部分，第一部见链接
| Paper ID | Paper Title | Category |
|---|---|---|
| 2515 | Temporal Aggregate Representations for Long Term Video Understanding | Poster |
| 2527 | Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition | Poster |
| 2530 | General 3D Room Layout from a Single View by Render-and-Compare | Poster |
| 2532 | Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints | Poster |
| 2535 | Multimodal Memorability: Modeling Effects of Semantics and Decay on Video Memorability | Poster |
| 2538 | Yet Another Intermediate-Level Attack | Poster |
| 2540 | Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction | Poster |
| 2544 | Early Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images | Poster |
| 2547 | PatchNets: Patch-based Generalizable Deep Implicit 3D Shape Representations | Poster |
| 2548 | How does Lipschitz Regularization Influence GAN Training? | Poster |
| 2550 | Infrastructure-based Multi-Camera Calibration using Radial Projections | Poster |
| 2553 | MotionSqueeze: Neural Motion Feature Learning for Video Understanding | Poster |
| 2559 | Polarized optical-flow gyroscope | Poster |
| 2561 | Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation | Poster |
| 2562 | An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning | Poster |
| 2568 | On the Effectiveness of Image Rotation for Open Set Domain Adapation | Poster |
| 2569 | Combining Task Predictors via Enhancing Joint Predictability | Poster |
| 2581 | Multi-Scale Positive Sample Refinement for Few-Shot Object Detection | Poster |
| 2583 | Single-Image Depth Prediction Makes Feature Matching Easier | Poster |
| 2586 | Deep Reinforced Attention Learning for Quality-Aware Visual Recognition | Poster |
| 2588 | CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization | Poster |
| 2590 | Learning Joint Spatial-Temporal Transformations for Video Inpainting | Poster |
| 2593 | Single Path One-Shot Neural Architecture Search with Uniform Sampling | Poster |
| 2595 | Learning to Generate Novel Domains for Domain Generalization | Poster |
| 2599 | Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections | Poster |
| 2601 | Impact of base dataset design on few-shot image classification | Poster |
| 2605 | Invertible Zero-Shot Recognition Flows | Poster |
| 2606 | GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes | Poster |
| 2607 | Location Sensitive Image Retrieval and Tagging | Poster |
| 2608 | Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image | Poster |
| 2612 | Guessing State Tracking for Visual Dialogue | Poster |
| 2614 | Memory-Efficient Incremental Learning Through Feature Adaptation | Poster |
| 2619 | Neural Voice Puppetry: Audio-Driven Facial Reenactment | Poster |
| 2621 | One-Shot Unsupervised Cross-Domain Detection | Poster |
| 2629 | Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks | Poster |
| 2630 | Probabilistic Future Prediction for Video Scene Understanding | Poster |
| 2633 | Suppressing Mislabeled Data via Grouping and Self-Attention | Poster |
| 2638 | Class-wise Dynamic Graph Convolution for Semantic Segmentation | Poster |
| 2639 | Character-Preserving Coherent Story Visualization | Poster |
| 2640 | GINet: Graph Interaction Network for Scene Parsing | Poster |
| 2662 | Tensor Low-Rank Reconstruction for Semantic Segmentation | Poster |
| 2668 | Attentive Normalization | Poster |
| 2678 | Count- and Similarity-aware Pedestrian Detection | Poster |
| 2682 | TRADI: Tracking deep neural network weight distributions | Poster |
| 2686 | Spatiotemporal Attacks for Embodied Agents | Poster |
| 2697 | Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation | Poster |
| 2701 | Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild | Poster |
| 2709 | Design and Interpretation of Universal Adversarial Patches in Face Detection | Poster |
| 2712 | Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild | Poster |
| 2715 | Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints | Poster |
| 2716 | Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification | Poster |
| 2718 | Contextual Heterogeneous Graph for Human-Object Interaction Detection | Poster |
| 2721 | Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning | Poster |
| 2724 | A Closest Point Proposal for MCMC-based Probabilistic Surface Registration | Poster |
| 2729 | Interactive Video Object Segmentation Using Global and Local Transfer Modules | Poster |
| 2749 | End-to-end interpretable learning of non-blind image deblurring | Poster |
| 2756 | Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation | Poster |
| 2760 | Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection | Poster |
| 2761 | Rethinking Image Deraining via Rain Streaks and Vapors | Poster |
| 2775 | Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes | Poster |
| 2781 | Is Sharing of Egocentric Video Giving Away Your Biometric Signature? | Poster |
| 2783 | Captioning Images for a Real Use Case | Poster |
| 2800 | Improving Semantic Segmentation via Decoupled Body and Edge Supervision | Poster |
| 2805 | Conditional Entropy Coding for Efficient Video Compression | Poster |
| 2810 | Differentiable Feature Aggregation Search for Knowledge Distillation | Poster |
| 2813 | Attention Guided Anomaly Localization in Images | Poster |
| 2819 | Self-supervised Video Representation Learning by Pace Reasoning | Poster |
| 2820 | Full-Body Awareness from Partial Observations | Poster |
| 2822 | Reinforced Axial Refinement Network for Monocular 3D Object Detection | Poster |
| 2830 | Self-Supervised Procedure Learning from Instructional Videos using DNNs | Poster |
| 2838 | Multi-view multi-object 6D pose estimation via robust scene consistency optimization | Poster |
| 2839 | In-Domain GAN Inversion for Real Image Editing | Poster |
| 2841 | Key Frame Proposal Network for Efficient Pose Estimation in Videos | Poster |
| 2844 | Exchangeable Deep Neural Networks for Set-to-Set Matching and Learning | Poster |
| 2861 | Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs | Poster |
| 2864 | Cross-Modal Weighting Network for RGB-D Salient Object Detection | Poster |
| 2865 | Open-set Adversarial Defense | Poster |
| 2866 | Deep Image Compression using Decoder Side Information | Poster |
| 2874 | Bridging the Sim-to-Real Gap: Unsupervised Learning of Scene Structure for Synthetic Data Generation | Poster |
| 2883 | L2 Norm: A Generic Visualization Approach for Convolutional Neural Networks | Poster |
| 2888 | Interactive Annotation of 3D Object Geometry using 2D Scribbles | Poster |
| 2889 | Hierarchical Kinematic Human Mesh Recovery | Poster |
| 2890 | Multi-Loss Rebalancing Algorithm for Monocular Depth Estimation | Poster |
| 2897 | 3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View | Poster |
| 2903 | We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos | Poster |
| 2908 | Joint Optimization for Multi-Person Shape Models from Markerless 3D-Scans | Poster |
| 2916 | Accurate RGB-D Salient Object Detection via Collaborative Learning | Poster |
| 2919 | Finding Your (3D) Center: 3D Object Detection Using a Learned Loss | Poster |
| 2920 | Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection | Poster |
| 2924 | Two-Stream Active Query Suggestion for Large-Scale Object Detection in Connectomics | Poster |
| 2941 | Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images | Poster |
| 2942 | Continuous Multimodal 6D Camera Relocalization | Poster |
| 2943 | Modeling Artistic Workflows for Image Generation and Editing | Poster |
| 2945 | A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks | Poster |
| 2946 | Hidden Footprints: Learning Contextual Walkability from 3D Human Trails | Poster |
| 2957 | Self-supervised learning of audio-visual objects from video | Poster |
| 2959 | GAN-based Garment Generation Using Sewing Pattern Images | Poster |
| 2962 | Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach | Poster |
| 2966 | An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds | Poster |
| 2970 | Montonicity Prior for Cloud Tomography | Poster |
| 2971 | Learning Trailer Moments in Full-Length Movies with Co-Contrastive Attention | Poster |
| 2976 | Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval | Poster |
| 2979 | Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline | Poster |
| 2981 | Learning to Generate Grounded Visual Captions without Localization Supervision | Poster |
| 2985 | Neural Hair Rendering | Poster |
| 2989 | JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling | Poster |
| 3004 | On Disentangling Spoof Traces for Generic Face Anti-Spoofing | Poster |
| 3005 | Streaming Object Detection for 3-D Point Clouds | Poster |
| 3006 | NAS-DIP: Learning Deep Image Prior with Neural Architecture Search | Poster |
| 3007 | Learning to Learn in a Semi-Supervised Fashion | Poster |
| 3009 | FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning | Poster |
| 3017 | Exploiting Radar for Robust Perception of Dynamic Objects | Poster |
| 3023 | Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation | Poster |
| 3024 | Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes | Poster |
| 3037 | Towards Causal Benchmarking of Algorithm Bias with Counterfactual Synthesis | Poster |
| 3039 | Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation | Poster |
| 3056 | Knowledge-Based Video Question Answering with Unsupervised Scene Descriptions | Poster |
| 3066 | Transformation Consistency Regularization - A Semi-Supervised Paradigm for Image-to-Image Translation | Poster |
| 3072 | LIRA: Lifelong Image Restoration from Unknown Blended Distortions | Poster |
| 3074 | HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization | Poster |
| 3082 | SOLO: Segmenting Objects by Locations | Poster |
| 3093 | Learning to See in the Dark with Events | Poster |
| 3094 | Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data | Poster |
| 3098 | Context-Gated Convolution | Poster |
| 3100 | Polynomial Regression Network for Variable-Number Lane Detection | Poster |
| 3108 | Structural Deep Metric Learning for Room Layout Estimation | Poster |
| 3122 | Adaptive Task Sampling for Meta-Learning | Poster |
| 3124 | Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images | Poster |
| 3128 | Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems | Poster |
| 3135 | High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling | Poster |
| 3136 | Online Ensemble Model Compression using Knowledge Distillation | Poster |
| 3137 | Deep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking System | Poster |
| 3149 | Efficient Residue Number System Based Winograd Convolution | Poster |
| 3150 | Robust Tracking against Adversarial Attacks | Poster |
| 3151 | Single-Shot Neural Relighting and SVBRDF Estimation | Poster |
| 3152 | Unsupervised Human 3D Pose Representation with Viewpoint and Pose Disentanglement | Poster |
| 3155 | Angle-based Search Space Shrinking for Neural Architecture Search | Poster |
| 3160 | RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition | Poster |
| 3162 | Towards Fast, Accurate and Stable 3D Dense Face Alignment | Poster |
| 3170 | Iterative Feature Transformation for Fast and Versatile Universal Style Transfer | Poster |
| 3177 | CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search | Poster |
| 3182 | Toward Faster and Simpler Matrix Normalization via Rank-1 Update | Poster |
| 3186 | Accurate polarimetric BRDF for real polarization scene rendering | Poster |
| 3188 | Lensless Imaging with Focusing Sparse URA Masks in Long-Wave Infrared and its Application for Human Detection | Poster |
| 3190 | Topology-Preserving Class-Incremental Learning | Poster |
| 3199 | Inter-Image Communication for Weakly Supervised Localization | Poster |
| 3205 | UFO$^2$: A Unified Framework Towards Omni-supervised Object Detection | Poster |
| 3215 | iCaps: An Interpretable Classifier via Disentangled Capsule Networks | Poster |
| 3220 | Detecting natural disasters, damage, and incidents in the wild | Poster |
| 3223 | Dynamic ReLU | Poster |
| 3224 | Acquiring Dynamic Light Fields through Coded Aperture Camera | Poster |
| 3238 | Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network | Poster |
| 3240 | Informative Sample Mining Network for Multi-Domain Image-to-Image Translation | Poster |
| 3242 | Spherical Feature Transform for Deep Metric Learning | Poster |
| 3245 | Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering | Poster |
| 3254 | Unsupervised Multi-View CNN for Salient View Selection of 3D Objects and Scenes | Poster |
| 3266 | FDTS: Fast Diverse-Transformation Search for Object Detection and Beyond | Poster |
| 3268 | Peeking into occluded joints: A novel framework for crowd pose estimation | Poster |
| 3271 | RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition | Poster |
| 3281 | Deep Hashing with Active Pairwise Supervision | Poster |
| 3293 | Graph Edit Distance Reward: Learning to Edit Scene Graph | Poster |
| 3295 | Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing | Poster |
| 3301 | Feature-metric Loss for Self-supervised Learning of Depth and Egomotion | Poster |
| 3304 | Propagating Over Phrase Relations for One-Stage Visual Grounding | Poster |
| 3307 | Adversarial Semantic Data Augmentation for Human Pose Estimation | Poster |
| 3314 | Deep Novel View Synthesis from Unstructured Input | Poster |
| 3315 | Face Anti-Spoofing via disentangled representation learning | Poster |
| 3317 | Prime-Aware Adaptive Distillation | Poster |
| 3318 | Meta-Learning with Network Pruning | Poster |
| 3323 | Spiral Generative Network for Image Extrapolation | Poster |
| 3324 | Scene Sketcher: Fine-grained Image Retrieval with Scene Sketch | Poster |
| 3337 | Few-shot Compositional Font Generation with Dual Memory | Poster |
| 3338 | PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling | Poster |
| 3339 | Content-aware Video Summarization | Poster |
| 3348 | Handcrafted Outlier Detection Revisited | Poster |
| 3359 | The Average Mixing Kernel Signature | Poster |
| 3361 | BCNet: Learning Body and Cloth Shape from A Single Image | Poster |
| 3372 | Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos | Poster |
| 3375 | Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration | Poster |
| 3382 | Polysemy Deciphering Network for Human-Object Interaction Detection | Poster |
| 3384 | Small-Task Incremental Learning | Poster |
| 3386 | Learning Graph-Convolutional Representations for Point Cloud Denoising | Poster |
| 3397 | Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching | Poster |
| 3398 | A Differentiable Recurrent Surface for Asynchronous Event-Based Data | Poster |
| 3399 | Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches | Poster |
| 3400 | LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation | Poster |
| 3405 | Microscopy Image Restoration with Deep Wiener-Kolmogorov filters | Poster |
| 3408 | ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language | Poster |
| 3411 | JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds | Poster |
| 3412 | Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior | Poster |
| 3414 | An Inference Algorithm for Multi-Label MRF-MAP Problems with Clique Size 100 | Poster |
| 3425 | Dual refinement underwater object detection network | Poster |
| 3429 | Learning to Visually Localize Multiple Sound Sources via A Two-stage Manner | Poster |
| 3457 | Task-Aware Quantization Network for JPEG Image Compression | Poster |
| 3472 | Learning Deep Conditional Target Densities for Accurate Regression | Poster |
| 3478 | CLOTH3D: Clothed 3D Humans | Poster |
| 3484 | Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images | Poster |
| 3485 | CLNet: A Compact Latent Network for Fast Adjusting Siamese Tracker | Poster |
| 3488 | Occlusion-Aware Siamese Network for Human Pose Estimation | Poster |
| 3492 | Learning to Predict Salient Faces: A Novel Audio-Visual Saliency Model | Poster |
| 3495 | NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image | Poster |
| 3498 | Model-based disentanglement of lens occlusions | Poster |
| 3506 | Rotation-robust Intersection over Union for 3D Object Detection | Poster |
| 3508 | New Threats against Object Detector with Non-Local Block | Poster |
| 3516 | Self-Supervised CycleGAN for Object-Preserving Image-to-Image Domain Adaptation | Poster |
| 3533 | On the Usage of the Trifocal Tensor in Motion Segmentation | Poster |
| 3539 | 3D-Rotation-Equivariant Quaternion Neural Networks | Poster |
| 3540 | InterHand2.6M: A New Large-scale Dataset and Baseline for 3D Single and Interacting Hand Pose Estimation from a Single RGB Image | Poster |
| 3548 | Active Crowd Counting with Limited Supervision | Poster |
| 3551 | Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance | Poster |
| 3563 | Hierarchical Visual-Textual Graph for Temporal Activity Localization via Language | Poster |
| 3568 | Do Not Mask What You Do Not Need to Mask: a Parser Free Virtual Try-On | Poster |
| 3577 | NODIS: Neural Ordinary Differential Scene Understanding | Poster |
| 3586 | Assembling Modality Representations via Attention Connections | Poster |
| 3588 | Learning Propagation Rules for Attribution Map Generation | Poster |
| 3590 | Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task Interference | Poster |
| 3606 | Learning Predictive Models from Observation and Interaction | Poster |
| 3607 | Unifying Deep Local and Global Features for Image Search | Poster |
| 3610 | Human Body Model Fitting by Learned Gradient Descent | Poster |
| 3611 | DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition | Poster |
| 3615 | Learning latent representions across multiple data domains using Lifelong VAEGAN | Poster |
| 3620 | DVI: Depth Guided Video Inpainting for Autonomous Driving | Poster |
| 3627 | Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation | Poster |
| 3632 | APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection | Poster |
| 3640 | Visual Question Answering on Image Sets | Poster |
| 3643 | Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots | Poster |
| 3644 | Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations | Poster |
| 3649 | Depth Estimation by Learning Triangulation and Densification of Sparse Points for Multi-view Stereo | Poster |
| 3654 | Dynamic Low-light Imaging with Quanta Image Sensors | Poster |
| 3668 | Disambiguating Monocular Depth Estimation with a Single Transient | Poster |
| 3672 | DSDNet: Deep Structured self-Driving Network | Poster |
| 3679 | QUEST: Quantized embedding space for transferring knowledge | Poster |
| 3685 | EGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma Diagnosis | Poster |
| 3689 | Backpropagated Gradient Representations for Anomaly Detection | Poster |
| 3694 | Dense RepPoints: Representing Visual Objects with Dense Point Sets | Poster |
| 3696 | On Dropping Clusters to Regularize Graph Convolutional Neural Networks | Poster |
| 3702 | Adaptive Video Highlight Detection by Learning from User History | Poster |
| 3705 | Automated Data Augmentation Significantly Improves 3D Object Detection | Poster |
| 3719 | DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction | Poster |
| 3720 | SPAN: Spatial Pyramid Attention Network for Image Manipulation Detection | Poster |
| 3721 | Transferring Domain Shift Across Tasks for Zero-shot Domain adaptation | Poster |
| 3723 | YOLO in the Dark - Domain Adaptation Method for Merging Multiple Models - | Poster |
| 3739 | Identity-Aware Multi-Sentence Video Description | Poster |
| 3742 | VQA-LOL: Visual Question Answering under the Lens of Logic | Poster |
| 3751 | Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation | Poster |
| 3752 | TRRNet: Tree Relation Reasoning for Compositional Visual Question Answering | Poster |
| 3764 | Mining Inter-Video Proposal Relations for Video Object Detection | Poster |
| 3768 | TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval | Poster |
| 3769 | Minimum Class Confusion for Versatile Domain Adaptation | Poster |
| 3790 | Large Batch Optimization for Object Detection: Training COCO in 12 Minutes | Poster |
| 3792 | Towards Practical and Efficient High-Resolution HDR Deghosting with CNN | Poster |
| 3794 | Self-Supervised Differentiable Rendering for Monocular 3D Object Detection | Poster |
| 3796 | Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation | Poster |
| 3801 | Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction | Poster |
| 3802 | Image-based table recognition: data, model, and evaluation | Poster |
| 3803 | Group Activity Prediction with Sequential Relational Anticipation Model | Poster |
| 3805 | PiP: Planning-informed Trajectory Prediction for Autonomous Driving | Poster |
| 3807 | PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer | Poster |
| 3819 | Hierarchical Context Embedding for Region-based Object Detection | Poster |
| 3822 | Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition | Poster |
| 3830 | Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection | Poster |
| 3833 | Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction | Poster |
| 3837 | MEAD: A Large-scale Audio-visual Dataset for Emotional Talking Face Generation | Poster |
| 3850 | Detecting Human-Object Interactions with Action Co-occurrence Priors | Poster |
| 3853 | Learning Connectivity of Neural Networks from a Topological Perspective | Poster |
| 3867 | JSTASR: Joint Size and Transparency-Aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect Removal | Poster |
| 3872 | Learning Object-aware Anchor-free Networks for Real-time Object Tracking | Poster |
| 3884 | Object Tracking using Spatio-Temporal Networks for Future Prediction Location | Poster |
| 3892 | Pillar-based Object Detection for Autonomous Driving | Poster |
| 3902 | Sparse Adversarial Attack via Perturbation Factorization | Poster |
| 3925 | 3D Scene Reconstruction from a Single Viewport | Poster |
| 3935 | Learning to Optimize Domain Specific Normalization for Domain Generalization | Poster |
| 3937 | Self-supervised Outdoor Scene Relighting | Poster |
| 3947 | LC-VSLAM: Real-time Tracking and Bundle Adjustment in Line-Cloud | Poster |
| 3951 | Leveraging Acoustic Images for Effective Self-Supervised Audio Representation Learning | Poster |
| 3960 | Learning Joint Visual Semantic Matching Embeddings for Language-guided Retrieval | Poster |
| 3990 | Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World | Poster |
| 3992 | StyleGAN2 Distillation for Feed-forward Image Manipulation | Poster |
| 3997 | Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds | Poster |
| 3999 | Learning Disentangled Representations via Mutual Information Estimation | Poster |
| 4010 | Challenge-Aware RGBT Tracking | Poster |
| 4019 | Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration | Poster |
| 4034 | AutoSimulate: (Quickly) Learning Synthetic Data Generation | Poster |
| 4035 | LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block | Poster |
| 4042 | Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation | Poster |
| 4046 | Active Visual Information Gathering for Vision-Language Navigation | Poster |
| 4061 | Deep Hough-Transform Line Priors | Poster |
| 4065 | Unsupervised Shape and Pose Disentanglement for 3D Meshes | Poster |
| 4066 | CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection | Poster |
| 4072 | Inclusive GAN: Improving Data and Minority Coverage in Generative Models | Poster |
| 4076 | SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects | Poster |
| 4095 | Dive Deeper Into Box for Object Detection | Poster |
| 4097 | PG-Net: Pixel to Global Matching Network for Visual Tracking | Poster |
| 4098 | Why Are Deep Representations Good Perceptual Quality Features? | Poster |
| 4101 | Geometric Estimation via Robust Subspace Recovery | Poster |
| 4102 | Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification | Poster |
| 4107 | Human Correspondence Consensus for 3D Object Semantic Understanding | Poster |
| 4111 | Learning Memory Augmented Cascading Network for Compressed Sensing of Images | Poster |
| 4112 | Least squares surface reconstruction on arbitrary domains | Poster |
| 4116 | Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery | Poster |
| 4118 | Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting | Poster |
| 4120 | DADA: Differentiable Automatic Data Augmentation | Poster |
| 4123 | SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans | Poster |
| 4125 | Kinship Identification through Joint Learning Using Kinship Verification Ensemble | Poster |
| 4152 | Kernelized Memory Network for Video Object Segmentation | Poster |
| 4160 | A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection | Poster |
| 4165 | Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation | Poster |
| 4167 | Temporal Keypoint Matching and Refinement Network for Pose Estimation and Tracking | Poster |
| 4168 | Neural Point-Based Graphics | Poster |
| 4171 | FHDe$^2$Net: Full High Definition Demoireing Network | Poster |
| 4172 | Learning Structural Similarity of User Interface Layouts using Graph Networks | Poster |
| 4174 | NAS-Count: Counting-by-Density with Neural Architecture Search | Poster |
| 4185 | Towards Generalization Across Depth for Monocular 3D Object Detection | Poster |
| 4197 | Margin-Mix: Semi--Supervised Learning for Face Expression Recognition | Poster |
| 4198 | Principal Feature Visualisation in Convolutional Neural Networks | Poster |
| 4211 | Progressive Refinement Network for Occluded Pedestrian Detection | Poster |
| 4214 | MonoPort: Monocular Real-Time Volumetric Teleportation | Poster |
| 4217 | The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale | Poster |
| 4220 | Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction | Poster |
| 4234 | Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders | Poster |
| 4238 | SEN: A Novel Dissimilarity Measure for Prototypical Few-Shot Learning Networks | Poster |
| 4241 | Kinematic 3D Object Detection in Monocular Video | Poster |
| 4257 | Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents | Poster |
| 4270 | SACA Net: Cybersickness Assessment of Individual Viewers for VR Content via Graph-based Symptom Relation Embedding | Poster |
| 4272 | End-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention | Poster |
| 4297 | Know Your Surroundings: Exploiting Scene Information for Object Tracking | Poster |
| 4298 | Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases | Poster |
| 4300 | Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection | Poster |
| 4302 | DeepLandscape: Adversarial Modeling of Landscape Videos | Poster |
| 4304 | GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images | Poster |
| 4306 | Spatial-Angular Interaction for Light Field Image Super-Resolution | Poster |
| 4314 | BATS: Binary ArchitecTure Search | Poster |
| 4319 | A Closer Look at Local Aggregation Operators in Point Cloud Analysis | Poster |
| 4322 | Look here! A parametric learning based approach to redirect visual attention | Poster |
| 4324 | Variational Diffusion Autoencoders with Random Walk Sampling | Poster |
| 4328 | Adaptive Variance Based Label Distribution Learning For Facial Age Estimation | Poster |
| 4334 | Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency | Poster |
| 4342 | Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations | Poster |
| 4350 | VarSR: Variational Super-Resolution Network for Very Low Resolution Images | Poster |
| 4353 | Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation | Poster |
| 4355 | Towards Recognizing Unseen Categories in Unseen Domains | Poster |
| 4362 | Square Attack: a query-efficient black-box adversarial attack via random search | Poster |
| 4363 | You Are Here: Geolocation by Embedding Maps and Images | Poster |
| 4364 | Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation | Poster |
| 4366 | From Video to Stability: Learning Dynamics from Kinematics of Human Motion | Poster |
| 4368 | LevelSet R-CNN: A Deep Variational Method for Instance Segmentation | Poster |
| 4374 | Efficient Scale-permuted Backbone with Learned Resource Distribution | Poster |
| 4375 | Bridging Multiple Distant Domains by Learning Transferable Shapes from Sketch | Poster |
| 4377 | Bridging Knowledge Graphs to Generate Scene Graphs | Poster |
| 4386 | Implicit Latent Variable Model for Scene-Consistent Motion Forecasting | Poster |
| 4387 | Learning Visual Commonsense for Robust Scene Graph Generation | Poster |
| 4396 | MPCC: Matching Priors and Conditionals for Clustering | Poster |
| 4405 | PointAR: Efficient Lighting Estimation for Mobile Augmented Reality | Poster |
| 4408 | Discrete Point Flow Networks for Efficient Point Cloud Generation | Poster |
| 4410 | Accelerating Deep Learning with Millions of Classes | Poster |
| 4416 | Password-conditioned Anonymization and Deanonymization with Face Identity Transformers | Poster |
| 4421 | Inertial Safety from Structured Light | Poster |
| 4424 | PointTriNet: Learned Triangulation of 3D Point Sets | Poster |
| 4433 | Toward unsupervised, multi-object discovery in large-scale image collections | Poster |
| 4474 | Deep View Synthesis From Colored 3D PointClouds | Poster |
| 4495 | Consensus-Aware Visual-Semantic Embedding for Image-Text Matching | Poster |
| 4499 | Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising | Poster |
| 4510 | Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding | Poster |
| 4513 | Cross-task Transfer for Multimodal Aerial Scene Classification | Poster |
| 4522 | Polarimetric Multi-View Inverse Rendering | Poster |
| 4524 | SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information | Poster |
| 4531 | Improving Recognition with Unlabeled Faces in the Wild | Poster |
| 4532 | NeuRoRA: Neural Robust Rotation Averaging | Poster |
| 4535 | SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes | Poster |
| 4544 | Unsupervised Learning of Optical Flow with Deep Feature Similarity | Poster |
| 4548 | Blended Grammar Network for Human Parsing | Poster |
| 4549 | A Crisis is an Opportunity: Discriminative Patch-based and Piece-wise Planar-based Unsupervised Depth Estimation in Indoor Environments | Poster |
| 4553 | Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs | Poster |
| 4582 | Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting | Poster |
| 4583 | BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging | Poster |
| 4584 | Ultra Fast Structure-aware Deep Lane Detection | Poster |
| 4585 | Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling | Poster |
| 4600 | Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN | Poster |
| 4614 | Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition | Poster |
| 4617 | Learning Camera-Aware Noise Models | Poster |
| 4619 | The Whole is greater than the sum of its Nonrigid Parts | Poster |
| 4625 | Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration | Poster |
| 4628 | In Defense of Graph Inference Algorithms for Weakly Supervised Object Localization | Poster |
| 4629 | Environment-agnostic Multitask Learning for Natural Language Grounded Navigation | Poster |
| 4631 | TPFN: Apply Outer Product along Time for Multimodal Sentiment Analysis Fusion on Imperfect Data | Poster |
| 4637 | ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis | Poster |
| 4644 | Learning with Privileged Information for Efficient Image Super-Resolution | Poster |
| 4652 | Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification | Poster |
| 4655 | Autoencoder-based Graph Construction for Semi-supervised Learning | Poster |
| 4670 | Virtual Multi-view Fusion for 3D Semantic Segmentation | Poster |
| 4672 | Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition | Poster |
| 4676 | Deep Shape from Polarization | Poster |
| 4682 | A Boundary Based Out-Of-Distribution Classifier for Generalized Zero-Shot Learning | Poster |
| 4690 | Mind the Discriminability: Asymmetric Adversarial Domain Adaptation | Poster |
| 4694 | SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates | Poster |
| 4729 | Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking | Poster |
| 4736 | Deep FusionNet for Point Cloud Semantic Segmentation | Poster |
| 4750 | Deep Material Recognition in Light-Fields via Disentanglement of Spatial and Angular Information | Poster |
| 4757 | Dual Adversarial Network for Deep Active Learning | Poster |
| 4763 | Fully Convolutional Networks for Continuous Sign Language Recognition | Poster |
| 4771 | Self-adapting confidence estimation for stereo | Poster |
| 4793 | Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention | Poster |
| 4796 | AutoSTR: Efficient Backbone Search for Scene Text Recognition | Poster |
| 4802 | Pretraining Matters: A Two-Stage Design for Unsupervised Image Classification | Poster |
| 4810 | Adversarial Training with Bi-directional Likelihood Regularization for Visual Classification | Poster |
| 4830 | Faster AutoAugment: Learning Augmentation Strategies using Backpropagation | Poster |
| 4836 | Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation | Poster |
| 4845 | Boundary-Aware Cascade Networks for Temporal Action Segmentation | Poster |
| 4865 | Towards Content-independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation | Poster |
| 4871 | Inference Graphs for CNN Interpretation | Poster |
| 4879 | An End-to-End OCR Text Re-organization Sequence Learning for Rich-text Detail Image Comprehension | Poster |
| 4889 | Improving Query Efficiency of Black-box Adversarial Attack | Poster |
| 4890 | Self-similarity Student for Partial Label Histopathology Image Segmentation | Poster |
| 4912 | BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions | Poster |
| 4913 | A Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images | Poster |
| 4920 | Global-and-Local Relative Position Embedding for Unsupervised Video Summarization | Poster |
| 4924 | Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms | Poster |
| 4927 | SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking | Poster |
| 4943 | CenterNet Heatmap Propagation for Real-time Video Object Detection | Poster |
| 4959 | Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection | Poster |
| 4963 | SOLAR: Second-Order Loss and Attention for Image Retrieval | Poster |
| 4964 | Fixing Localization Errors to Improve Image Classification | Poster |
| 4968 | PatchPerPix for Instance Segmentation | Poster |
| 4997 | Attend and Segment | Poster |
| 5004 | Accelerating CNN Training by Pruning Activation Gradients | Poster |
| 5010 | Global and Local Enhancement Networks For Paired and Unpaired Image Enhancement | Poster |
| 5041 | Probabilistic Anchor Assignment with IoU Prediction for Object Detection | Poster |
| 5056 | Eyeglasses 3D shape reconstruction from a single face image | Poster |
| 5061 | Temporal Complementary Learning for Video Person Re-Identification | Poster |
| 5063 | HoughNet: Integrating near and long-range evidence for bottom-up object detection | Poster |
| 5066 | Graph Wasserstein Correlation Analysis for Movie Retrieval | Poster |
| 5068 | Revisiting RCNN for Action Detection in Videos | Poster |
| 5090 | Full-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of Polarization | Poster |
| 5095 | A Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation | Poster |
| 5099 | Learning Enriched Features for Real Image Restoration and Enhancement | Poster |
| 5105 | Detail Preserved Point Cloud Completion via Separated Feature Aggregation | Poster |
| 5115 | LabelEnc: A New Intermediate Supervision Method for Object Detection | Poster |
| 5118 | Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets | Poster |
| 5130 | PAMS: Quantized Super-Resolution via Parameterized Max Scale | Poster |
| 5131 | SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds | Poster |
| 5134 | OID: Outlier Identifying and Discarding in Blind Image Deblurring | Poster |
| 5140 | Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors | Poster |
| 5150 | Enhanced Sparse Model for Blind Deblurring | Poster |
| 5155 | SumGraph: Video Summarization via Recursive Graph Modeling | Poster |
| 5164 | Feature Normalized Knowledge Distillation for Image Classification | Poster |
| 5170 | A Metric Learning Reality Check | Poster |
| 5190 | FTL: A universal framework for training low-bit DNNs via Feature Transfer | Poster |
| 5192 | XingGAN for Person Image Generation | Poster |
| 5203 | GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering | Poster |
| 5204 | VCNet: A Robust Approach to Blind Image Inpainting | Poster |
| 5205 | Learning to Predict Context-adaptive Convolution for Semantic Segmentation | Poster |
| 5211 | EfficientFCN: Holistically-guided Decoding for Semantic Segmentation | Poster |
| 5227 | GroSS: Group-Size Series Decomposition for Grouped Architecture Search | Poster |
| 5291 | Efficient Adversarial Attacks for Visual Object Tracking | Poster |
| 5299 | Globally-Optimal Event Camera Motion Estimation | Poster |
| 5301 | Weakly-supervised Learning of Human Dynamics | Poster |
| 5305 | Journey Towards Tiny Perceptual Super-Resolution | Poster |
| 5308 | What makes fake images detectable? Understanding properties that generalize | Poster |
| 5313 | Embedding Propagation: Smoother Manifold for Few-Shot Classification | Poster |
| 5315 | Category Level Object Pose Estimation via Neural Analysis-by-Synthesis | Poster |
| 5320 | High-Fidelity Synthesis with Disentangled Representation | Poster |
| 5323 | PL1P - Point-line Minimal Problems under Partial Visibility in Three Views | Poster |
| 5327 | Prediction, Recovery and Identification: Adaptive Low-Resolution Person Re-Identification | Poster |
| 5328 | Learning Canonical Representations for Scene Graph to Image Generation | Poster |
| 5331 | Adversarial Robustness on In- and Out-Distribution Improves Explainability | Poster |
| 5333 | Deformable Style Transfer | Poster |
| 5336 | Aligning Videos in Space and Time | Poster |
| 5346 | Neural Wireframe Renderer: Learning Wireframe to Image Translations | Poster |
| 5351 | RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax | Poster |
| 5368 | Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction | Poster |
| 5369 | Determining the Relevance of Features for Deep Neural Networks | Poster |
| 5372 | Weakly Supervised Semantic Segmentation with Boundary Exploration | Poster |
| 5381 | GANhopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation | Poster |
| 5385 | DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild | Poster |
| 5394 | Multi-view adaptive graph convolutions for graph classification | Poster |
| 5406 | Universal Self-Training for Unsupervised Domain Adaptation | Poster |
| 5409 | Weight Decay Scheduling and Knowledge Distillation for Active Learning | Poster |
| 5414 | HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs | Poster |
| 5423 | Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning | Poster |
| 5424 | Geometry Constrained Weakly Supervised Object Localization | Poster |
| 5445 | Duality Diagram Similarity: a generic framework for initialization selection in task transfer learning | Poster |
| 5448 | OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering | Poster |
| 5450 | Mining self-similarity: Label super-resolution with epitomic representations | Poster |
| 5480 | AE-OT-GAN: Training GANs from data specific latent distribution | Poster |
| 5488 | Null-sampling for Invariant and Interpretable Representations | Poster |
| 5491 | Guiding Monocular Depth Estimation Using Depth Attention-Volume | Poster |
| 5494 | Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping | Poster |
| 5495 | Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer | Poster |
| 5496 | BézierSketch: A generative model for scalable vector sketches | Poster |
| 5530 | Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation | Poster |
| 5551 | Domain Adaptation through Task Distillation | Poster |
| 5563 | PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning | Poster |
| 5564 | More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning | Poster |
| 5568 | Extending and Analyzing Self-Supervised Learning Across Domains | Poster |
| 5573 | Multi-Source Open-Set Deep Adversarial Domain Adaptation | Poster |
| 5576 | Neural Batch Sampling with Reinforcement Learning for Semi-Supervised Anomaly Detection | Poster |
| 5581 | LEMMA: A Multiview Dataset for Learning Multi-agent Multi-task Activities | Poster |
| 5589 | Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images | Poster |
| 5592 | Accurate Optimization of Weighted Nuclear Norm for Non-Rigid Structure from Motion | Poster |
| 5605 | Proposal based Video Completion | Poster |
| 5608 | HGNet: Hybrid Generative Network for Zero-shot Domain Adaptation | Poster |
| 5622 | Beyond Monocular Deraining: Paired Rain Removal Networks via Unpaired Semantic Understanding | Poster |
| 5625 | DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks | Poster |
| 5635 | All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling | Poster |
| 5643 | A Broader Study of Cross-Domain Few-Shot Learning | Poster |
| 5645 | Practical Poisoning Attacks on Neural Networks | Poster |
| 5669 | Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification | Poster |
| 5671 | Learn distributed GAN with Temporary Discriminators | Poster |
| 5673 | SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems | Poster |
| 5686 | Improving Adversarial Robustness by Enforcing Local and Global Compactness | Poster |
| 5687 | TopoGAN: A Generative Adversarial Approach to Topology-Aware Road Segmentation | Poster |
| 5695 | Channel selection using Gumbel softmax | Poster |
| 5696 | Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification | Poster |
| 5698 | An Efficient Training Framework for Reversible Neural Architectures | Poster |
| 5717 | Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation | Poster |
| 5744 | Freeform Structured Light | Poster |
| 5750 | One-pixel Signature: Characterizing CNN Classifiers for Backdoor Detection | Poster |
| 5752 | Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning | Poster |
| 5757 | Structure-Aware Generation Network for Recipe Generation from Images | Poster |
| 5769 | A Simple and Effective Framework for Pairwise Deep Metric Learning | Poster |
| 5772 | Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner | Poster |
| 5775 | A Recurrent Transformer Network for Novel View Action Synthesis | Poster |
| 5777 | Multi-view Action Recognition using Cross-view Video Prediction | Poster |
| 5794 | Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation | Poster |
| 5809 | SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction | Poster |
| 5818 | Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation | Poster |
| 5831 | Efficient Outdoor 3D Point Cloud Semantic Segmentation for Critical Road Objects and Distributed Contexts | Poster |
| 5849 | Attributional Robustness Training using Input-Gradient Spatial Alignment | Poster |
| 5855 | How to Train Your Event Camera Neural Network | Poster |
| 5863 | Spatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement Learning | Poster |
| 5865 | On the Importance of Data Augmentation for Object Detection | Poster |
| 5875 | DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search | Poster |
| 5879 | A Closer Look at Generalisation in RAVEN | Poster |
| 5884 | Supervised Edge Attention Network for Accurate Image Instance Segmentation | Poster |
| 5888 | Discriminative Partial Domain Adversarial Network | Poster |
| 5893 | Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model | Poster |
| 5894 | Deep Cross-species Feature Learning for Animal Face Recognition via Residual Interspecies Equivariant Network | Poster |
| 5897 | Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes | Poster |
| 5906 | Sound2Sight: Generating Visual Dynamics from Sound and Context | Poster |
| 5913 | 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection | Poster |
| 5921 | NoiseRank: Unsupervised Label Noise Reduction with Dependence Models | Poster |
| 5930 | Fast Adaptation to Super-Resolution Networks via Meta-Learning | Poster |
| 5931 | TP-LSD: Tri-Points Based Line Segment Detector | Poster |
| 5940 | Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation | Poster |
| 5955 | An Attention-driven Two-stage Clustering Method for Unsupervised Person Re-Identification | Poster |
| 5989 | Toward Fine-grained Facial Expression Manipulation | Poster |
| 5992 | Adaptive Object Detection with Dual Multi-Label Prediction | Poster |
| 6007 | Table Structure Recognition using Top-Down and Bottom-Up Cues | Poster |
| 6013 | Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder | Poster |
| 6018 | Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments | Poster |
| 6021 | Boundary Content Graph Neural Network for Temporal Action Proposal Generation | Poster |
| 6037 | Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition | Poster |
| 6051 | VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval | Poster |
| 6054 | Attention-Based Query Expansion Learning | Poster |
| 6055 | Interpretable Foreground Object Search As Knowledge Distillation | Poster |
| 6056 | Improving Knowledge Distillation via Category Structure | Poster |
| 6059 | High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images | Poster |
| 6066 | Attentive Prototype Few-shot Learning with Capsule Network-based Embedding | Poster |
| 6083 | Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances | Poster |
| 6091 | DA4AD: End-to-end Deep Attention Aware Features Aided Visual Localization for Autonomous Driving | Poster |
| 6109 | Visual-Relation Conscious Image Generation from Structured-Text | Poster |
| 6114 | Patch-wise Attack for Fooling Deep Neural Network | Poster |
| 6141 | Feature Pyramid Transformer | Poster |
| 6153 | MABNet: A Lightweight Stereo Network Based on Multibranch Adjustable Bottleneck Module | Poster |
| 6159 | Guided Saliency Feature Learning for Person Re-identification in Crowded Scenes | Poster |
| 6188 | Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency Detection | Poster |
| 6192 | Lightweight Statistical Explanations for Deep Neural Networks | Poster |
| 6207 | Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers | Poster |
| 6215 | Video Representation Learning by Learning to Tell Motions Apart | Poster |
| 6231 | Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation | Poster |
| 6236 | Variational Connectionist Temporal Classification | Poster |
| 6258 | End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose Estimation | Poster |
| 6259 | Orderly Disorder in Point Cloud Domain | Poster |
| 6272 | Deep Decomposition Learning for Inverse Imaging Problems | Poster |
| 6287 | FLOT: Scene Flow Estimation by Learned Optimal Transport on Point Clouds | Poster |
| 6294 | Accurate Reconstruction of Oriented 3D Points using Affine Correspondences | Poster |
| 6316 | Volumetric Transformer Networks | Poster |
| 6332 | 360º Camera Alignment via Segmentation | Poster |
| 6334 | A Novel Line Integral Transform for 2D Affine Invariant Shape Retrieval | Poster |
| 6336 | Explainable Graph Networks for Weakly-supervised Learning of Visual Relations | Poster |
| 6345 | Guided Semantic Flow | Poster |
| 6393 | Document Structure Extraction using Prior Based HighResolution Hierarchical Semantic Segmentation | Poster |
| 6416 | Measuring the importance of temporal features in video saliency | Poster |
| 6421 | Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution | Poster |
| 6424 | Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images | Poster |
| 6425 | Online Continual Learning under Extreme Memory Constraints | Poster |
| 6436 | Learning to Cluster under Domain Shift | Poster |
| 6438 | Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds | Poster |
| 6440 | Improving Optical Flow on a Pyramid Level | Poster |
| 6446 | Procrustean Regression Networks: Learning 3D Structure of Non-Rigid Objects from 2D Annotations | Poster |
| 6474 | Learning to Learn Parameterized Classification Networks for Scalable Input Images | Poster |
| 6476 | Stereo Event-based Particle Tracking Velocimetry for 3D Fluid Flow Reconstruction | Poster |
| 6515 | Simplicial Complex based Point Correspondence between Images warped onto Manifolds | Poster |
| 6535 | Neural Message Passing on Hybrid Spatio-Temporal Visual and Symbolic Graphs for Video Understanding | Poster |
| 6559 | Distance-Normalized Unified Representation for Monocular 3D Object Detection | Poster |
| 6576 | Sequential Deformation for Accurate Scene Text Detection | Poster |
| 6579 | Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Exploration | Poster |
| 6591 | Semi-Supervised Segmentation based on Error-Correcting Supervision | Poster |
| 6621 | Quantum-soft QUBO Suppression for Accurate Object Detection | Poster |
| 6624 | Label-similarity Curriculum Learning | Poster |
| 6627 | Recurrent Image Annotation With Explicit Inter-Label Dependencies | Poster |
| 6628 | Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution | Poster |
| 6637 | SimPose: Effectively Learning DensePose and Surface Normal of People from Simulated Data | Poster |
| 6639 | ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face Images | Poster |
| 6693 | Differentiable Joint Pruning and Quantization for Hardware Efficiency | Poster |
| 6697 | Learning to Generate Customized Dynamic 3D Facial Expressions | Poster |
| 6698 | LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors | Poster |
| 6709 | Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly Detection | Poster |
| 6717 | Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration. | Poster |
| 6719 | Jointly De-biasing Face Recognition and Demographic Attribute Estimation | Poster |
| 6721 | Regularized Loss for Weakly Supervised Single Class Segmentation | Poster |
| 6736 | Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks | Poster |
| 6746 | Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations | Poster |
| 6748 | Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations | Poster |
| 6753 | Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks | Poster |
| 6754 | Learning to Learn Words from Visual Scenes | Poster |
| 6765 | On Transferability of Histological Tissue Labels in Computational Pathology | Poster |
| 6770 | Learning actionness via long-range temporal order verification | Poster |
| 6773 | Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays | Poster |
| 6775 | Character Region Attention For Text Spotting | Poster |
| 6795 | Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network | Poster |
| 6796 | Dual Mixup Regularized Learning for Adversarial Domain Adaptation | Poster |
| 6814 | Robust and On-the-fly Dataset Denoising for Image Classification | Poster |
| 6833 | Imaging Behind Occluders Using Two-Bounce Light | Poster |
| 6837 | Improving Object Detection with Selective Self-supervised Self-training | Poster |
| 6873 | Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction | Poster |
| 6884 | Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning | Poster |
| 6895 | Adversarial Data Augmentation via Deformation Statistics | Poster |
| 6926 | Neural Predictor for Neural Architecture Search | Poster |
| 6927 | Learning Permutation Invariant Representations using Memory Networks | Poster |
| 6936 | Feature Space Augmentation for Long-Tailed Data | Poster |
| 6940 | Laying the Foundations of Deep Long-Term Crowd Flow Prediction | Poster |
| 6965 | Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning | Poster |
| 6967 | Fairness by Learning Orthogonal Disentangled Representations | Poster |
| 6977 | Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation | Poster |
| 6979 | On Diverse Asynchronous Activity Anticipation | Poster |
| 6994 | Representative-Discriminative Learning for Open-set Land Cover Classification of Satellite Imagery | Poster |
| 7020 | Structure-Aware Human-Action Generation | Poster |
| 7035 | Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition | Poster |
| 7036 | $S^3$Net: Semantic-Aware Self-Supervised Depth Estimation with Monocular Videos and Synthetic Data | Poster |
| 7037 | Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning | Poster |
| 7039 | Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks | Poster |
| 7093 | UNITER: UNiversal Image-TExt Representation Learning | Poster |
| 7133 | $Oscar$: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks | Poster |
| 7177 | Improving Face Recognition from Hard Samples via Distribution Distillation Loss | Poster |
| 7198 | Extract and Merge: Superpixel Segmentation with Regional Attributes | Poster |
| 7202 | Spatial-Adaptive Network for Single Image Denoising | Poster |
| 7263 | Physics-based Feature Dehazing Networks | Poster |
| 7352 | Master-Slave Interaction Model: An Asymmetric Modelling for Action Assessment | Poster |
| 7358 | High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential Modulation | Poster |
| 7362 | Instance-Aware Embedding for Point Cloud Instance Segmentation | Poster |
| 7424 | Self-Paced Deep Regression Forests with Consideration on Underrepresented Samples | Poster |
| 7451 | Manifold Projection for Adversarial Defense on Face Recognition | Poster |
| 7467 | Weakly-Supervised Learning with Side Information for Noisy Labeled Images | Poster |
| 7476 | Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision | Poster |
| 7513 | SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection | Poster |
| 7548 | Modeling the Space of Point Landmark Constrained Diffeomorphisms | Poster |
| 7579 | PieNet: Personalized Image Enhancement Network | Poster |
| 7614 | Statistical Outlier Identification in Pose Graphs Using Cycles | Poster |
| 7625 | Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture | Poster |
| 7627 | Solving phase retrieval with a learned reference | Poster |
| 7644 | Dual Grid Net: Hand Mesh VertexRegression from Single Depth Maps | Poster |