Computer Vision

How To Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild ICCV 2021 How To Exploit the Transferability of Learned Image Compression to Conventional Codecs CVPR 2021 How to Make a BLT Sandwich? Learning VQA Towards Understanding Web Instructional Videos WACV 2021 How To Train Neural Networks for Flare Removal ICCV 2021 How Transferable Are Reasoning Patterns in VQA? CVPR 2021 How Well Do Self-Supervised Models Transfer? CVPR 2021 HPNet: Deep Primitive Segmentation Using Hybrid Representations ICCV 2021 HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation AAAI 2021 HRegNet: A Hierarchical Network for Large-Scale Outdoor LiDAR Point Cloud Registration ICCV 2021 HRFormer: High-Resolution Vision Transformer for Dense Predict NeurIPS 2021 HR-NAS: Searching Efficient High-Resolution Neural Architectures With Lightweight Transformers CVPR 2021 Human De-Occlusion: Invisible Perception and Recovery for Humans CVPR 2021 Human Detection and Segmentation via Multi-View Consensus ICCV 2021 HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences CVPR 2021 Human-Like Controllable Image Captioning With Verb-Specific Semantic Roles CVPR 2021 Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-Localization in Large Scenes From Body-Mounted Sensors CVPR 2021 Human Pose Regression With Residual Log-Likelihood Estimation ICCV 2021 Humble Teachers Teach Better Students for Semi-Supervised Object Detection CVPR 2021 HuMoR: 3D Human Motion Model for Robust Pose Estimation ICCV 2021 Humor Knowledge Enriched Transformer for Understanding Multimodal Humor AAAI 2021 HVPR: Hybrid Voxel-Point Representation for Single-Stage 3D Object Detection CVPR 2021 Hybrid Message Passing With Performance-Driven Structures for Facial Action Unit Detection CVPR 2021 Hybrid Neural Fusion for Full-Frame Video Stabilization ICCV 2021 Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach CVPR 2021 HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation CVPR 2021