Computer Vision

Task-Free Dynamic Sparse Vision Transformer for Continual Learning AAAI 2024 Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence CVPR 2024 Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers CVPR 2024 Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer CVPR 2024 Towards 3D Vision with Low-Cost Single-Photon Cameras CVPR 2024 Towards Global Optimal Visual In-Context Learning Prompt Selection NeurIPS 2024 Towards Improved Proxy-Based Deep Metric Learning via Data-Augmented Domain Adaptation AAAI 2024 Towards Robust Visual Understanding: from Recognition to Reasoning AAAI 2024 TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution AAAI 2024 Transferable Adversarial Attacks on SAM and Its Downstream Models NeurIPS 2024 Transfer and Alignment Network for Generalized Category Discovery AAAI 2024 Transformer Doctor: Diagnosing and Treating Vision Transformers NeurIPS 2024 T-VSL: Text-Guided Visual Sound Source Localization in Mixtures CVPR 2024 UDON: Universal Dynamic Online distillatioN for generic image representations NeurIPS 2024 UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets CVPR 2024 Understanding Bias in Large-Scale Visual Datasets NeurIPS 2024 Understanding Visual Feature Reliance through the Lens of Complexity NeurIPS 2024 Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers CVPR 2024 UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections NeurIPS 2024 Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization CVPR 2024 Unsupervised Keypoints from Pretrained Diffusion Models CVPR 2024 Unsupervised Novelty Detection in Pretrained Representation Space with Locally Adapted Likelihood Ratio AISTATS 2024 Unveiling the Invisible: Captioning Videos with Metaphors EMNLP 2024 Unveiling the mystery of visual attributes of concrete and abstract concepts: Variability, nearest neighbors, and challenging categories EMNLP 2024 Using Stratified Sampling to Improve LIME Image Explanations AAAI 2024