Repositories

Official code for "Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement" (ICCV 2025).

Official codebase of "DisenQ: Disentangling Q-Former for Activity-Biometrics" (ICCV 2025).

Official code for "Punching Bag vs. Punching Person: Motion Transferability in Videos" (ICCV 2025).

Official code for "STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding" (CVPR 2025).

Official repository of "HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding" (CVPR 2025).

Official code for "LR0.FM: Low-Resolution Zero-Shot Classification Benchmark for Foundation Models" (ICLR 2025).

Official code for "Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding" (ICLR 2025).

Official code for "Stable Mean Teacher for Semi-supervised Video Action Detection" (AAAI 2025).

Official code for "End-to-End Semi-Supervised Learning for Video Action Detection" (CVPR 2022).

Official code for "T2L: Efficient Zero-Shot Action Recognition with Temporal Token Learning" (TMLR 2025).

Official code for "Asynchronous Perception Machine for Efficient Test-Time-Training" (NeurIPS 2024).

Official code for "Activity-Biometrics: Person Identification from Daily Activities" (CVPR 2024).

Official implementation and benchmark evaluation for "MolVision: Molecular Property Prediction with Vision Language Models" (NeurIPS 2025 D&B).

Project website for "StreamReady: Learning What to Answer and When in Long Streaming Videos" (CVPR 2026).

Official code for "DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID" (CVPR 2025).