Pinned Loading

1. VideoMAE VideoMAE Public

   [NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

   Python 1.8k 170

2. VideoChat3 VideoChat3 Public

   A generalist video MLLM built for fine-grained motion, long-form reasoning, temporal grounding, and live streaming.

   222 4

3. MixFormer MixFormer Public

   [CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention

   Python 537 75

4. MOTIP MOTIP Public

   [CVPR 2025] Multiple Object Tracking as ID Prediction

   Python 548 50

5. StreamForest StreamForest Public

   [NeurIPS 2025 Spotlight] StreamForest: Efficient Online Video Understanding with Persistent Event Memory

   Python 133 5

6. DDT DDT Public

   [CVPR 2026] DDT: Decoupled Diffusion Transformer

   Python 405 22