Computer Vision

TransforMatcher: Match-to-Match Attention for Semantic Correspondence CVPR 2022 TUSK: Task-Agnostic Unsupervised Keypoints NeurIPS 2022 Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment NeurIPS 2022 Understanding The Robustness in Vision Transformers ICML 2022 Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces ICML 2022 Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers ICML 2022 Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints AAAI 2022 Unsupervised Visual Representation Learning by Online Constrained K-Means CVPR 2022 Video Swin Transformer CVPR 2022 ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints NeurIPS 2022 ViM: Out-of-Distribution With Virtual-Logit Matching CVPR 2022 Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions ACL 2022 Vision GNN: An Image is Worth Graph of Nodes NeurIPS 2022 Vision-Language Pre-Training for Boosting Scene Text Detectors CVPR 2022 Vision Transformer With Deformable Attention CVPR 2022 Visual Abductive Reasoning CVPR 2022 Visual Attention Emerges from Recurrent Sparse Reconstruction ICML 2022 Visual Representation Learning over Latent Domains ICLR 2022 Voxel Field Fusion for 3D Object Detection CVPR 2022 What To Look at and Where: Semantic and Spatial Refined Transformer for Detecting Human-Object Interactions CVPR 2022 When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture NeurIPS 2022 When Does Contrastive Visual Representation Learning Work? CVPR 2022 When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework AAAI 2022 WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models NeurIPS 2022 Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality CVPR 2022