Computer Vision

Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation AAAI 2021 VidTr: Video Transformer Without Convolutions ICCV 2021 View Generalization for Single Image Textured 3D Models CVPR 2021 View-Guided Point Cloud Completion CVPR 2021 Viewing Graph Solvability via Cycle Consistency ICCV 2021 ViewNet: Unsupervised Viewpoint Estimation From Conditional Generation ICCV 2021 Viewpoint-Agnostic Change Captioning With Cycle Consistency ICCV 2021 Viewpoint-Agnostic Image Rendering WACV 2021 Viewpoint Invariant Dense Matching for Visual Geolocalization ICCV 2021 VIGOR: Cross-View Image Geo-Localization Beyond One-to-One Retrieval CVPR 2021 VIL-100: A New Dataset and a Baseline Model for Video Instance Lane Detection ICCV 2021 VinVL: Revisiting Visual Representations in Vision-Language Models CVPR 2021 VIP-DeepLab: Learning Visual Perception With Depth-Aware Video Panoptic Segmentation CVPR 2021 ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search CVPR 2021 VirFace: Enhancing Face Recognition via Unlabeled Shallow Data CVPR 2021 VirTex: Learning Visual Representations From Textual Annotations CVPR 2021 Virtual Fully-Connected Layer: Training a Large-Scale Face Recognition Dataset With Limited Computational Resources CVPR 2021 Virtual Light Transport Matrices for Non-Line-of-Sight Imaging ICCV 2021 Vis2Mesh: Efficient Mesh Reconstruction From Unstructured Point Clouds of Large Scenes With Learned Virtual View Visibility ICCV 2021 ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction NeurIPS 2021 Visformer: The Vision-Friendly Transformer ICCV 2021 Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models EMNLP 2021 Vision Transformers for Dense Prediction ICCV 2021 Vision Transformer With Progressive Sampling ICCV 2021 Visual Alignment Constraint for Continuous Sign Language Recognition ICCV 2021