computer vision

Omnivore: A Single Model for Many Visual Modalities CVPR 2022 One-Inlier is First: Towards Efficient Position Encoding for Point Cloud Registration NeurIPS 2022 On the Importance of Asymmetry for Siamese Representation Learning CVPR 2022 Partially Does It: Towards Scene-Level FG-SBIR With Partial Input CVPR 2022 Perceptual Consistency in Video Segmentation WACV 2022 Rethinking Alignment in Video Super-Resolution Transformers NeurIPS 2022 Rethinking Efficient Lane Detection via Curve Modeling CVPR 2022 Rethinking Image Cropping: Exploring Diverse Compositions From Global Views CVPR 2022 Robust Feature-Level Adversaries are Interpretability Tools NeurIPS 2022 ROCA: Robust CAD Model Retrieval and Alignment From a Single Image CVPR 2022 Scenic: A JAX Library for Computer Vision Research and Beyond CVPR 2022 Searching for BurgerFormer with Micro-Meso-Macro Space Design ICML 2022 Self-Supervised Models Are Continual Learners CVPR 2022 Semantic Segmentation by Early Region Proxy CVPR 2022 Shadows Can Be Dangerous: Stealthy and Effective Physical-World Adversarial Attack by Natural Phenomenon CVPR 2022 Sharing Decoders: Network Fission for Multi-Task Pixel Prediction WACV 2022 SimVQA: Exploring Simulated Environments for Visual Question Answering CVPR 2022 SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance NeurIPS 2022 Sparse Non-Local CRF CVPR 2022 SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal AAAI 2022 TAP-Vid: A Benchmark for Tracking Any Point in a Video NeurIPS 2022 The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization CVPR 2022 Thin-Plate Spline Motion Model for Image Animation CVPR 2022 Towards Accurate Facial Motion Retargeting with Identity-Consistent and Expression-Exclusive Constraints AAAI 2022 Towards Active Vision for Action Localization With Reactive Control and Predictive Learning WACV 2022