Computer Vision

Self-supervised learning of Split Invariant Equivariant representations ICML 2023 SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models ICML 2023 Semi-supervised Deep Large-Baseline Homography Estimation with Progressive Equivalence Constraint AAAI 2023 Siamese-Discriminant Deep Reinforcement Learning for Solving Jigsaw Puzzles with Large Eroded Gaps AAAI 2023 Siamese Image Modeling for Self-Supervised Vision Representation Learning CVPR 2023 Siamese Masked Autoencoders NeurIPS 2023 SimMatchV2: Semi-Supervised Learning with Graph Consistency ICCV 2023 SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams ACL 2023 SimpleClick: Interactive Image Segmentation with Simple Vision Transformers ICCV 2023 Simple Disentanglement of Style and Content in Visual Representations ICML 2023 Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs AAAI 2023 SMPConv: Self-Moving Point Representations for Continuous Convolution CVPR 2023 SparseVSR: Lightweight and Noise Robust Visual Speech Recognition Interspeech 2023 Spike Count Maximization for Neuromorphic Vision Recognition IJCAI 2023 Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet ICCV 2023 StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners NeurIPS 2023 SurfsUP: Learning Fluid Simulation for Novel Surfaces ICCV 2023 Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning AAAI 2023 Taxonomizing and Measuring Representational Harms: A Look at Image Tagging AAAI 2023 Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models CVPR 2023 TempSAL - Uncovering Temporal Information for Deep Saliency Prediction CVPR 2023 Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization ICML 2023 The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training CVPR 2023 Time to augment self-supervised visual representation learning ICLR 2023 Top-Down Visual Attention From Analysis by Synthesis CVPR 2023