Skip to content
@MCG-NJU

Multimedia Computing Group, Nanjing University

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 173

  2. VideoChat3 VideoChat3 Public

    VideoChat3: a generalist video MLLM built for fine-grained motion, long-form reasoning, temporal grounding, and online proactive response.

    Python 350 11

  3. MixFormer MixFormer Public

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

    Python 542 74

  4. OneStreamer OneStreamer Public

    OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

    Python 228 4

  5. MOTIP MOTIP Public

    [CVPR 2025] Multiple Object Tracking as ID Prediction

    Python 575 56

  6. VideoJev VideoJev Public

    VideoJev: System One Model for Video Understanding and Interaction

    Python 201 10

Repositories

Showing 10 of 108 repositories
  • VideoJev Public

    VideoJev: System One Model for Video Understanding and Interaction

    MCG-NJU/VideoJev's past year of commit activity
    Python 201 Apache-2.0 10 2 0 Updated Oct 18, 2026
  • OneStreamer Public

    OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

    MCG-NJU/OneStreamer's past year of commit activity
    Python 228 Apache-2.0 4 3 0 Updated Oct 14, 2026
  • MIMFlow Public

    [ECCV 2026 oral] MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

    MCG-NJU/MIMFlow's past year of commit activity
    Python 18 0 1 0 Updated Oct 14, 2026
  • STP Public

    [IJCV] Spatiotemporal Predictive Pre-training for Robotic Motor Control

    MCG-NJU/STP's past year of commit activity
    Python 2 Apache-2.0 0 0 0 Updated Oct 8, 2026
  • VideoChat3 Public

    VideoChat3: a generalist video MLLM built for fine-grained motion, long-form reasoning, temporal grounding, and online proactive response.

    MCG-NJU/VideoChat3's past year of commit activity
    Python 350 11 2 1 Updated Oct 2, 2026
  • TimeLens2 Public

    TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

    MCG-NJU/TimeLens2's past year of commit activity
    Python 145 4 0 0 Updated Oct 2, 2026
  • UniDDT Public

    [ECCV 2026 Spotlight] UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

    MCG-NJU/UniDDT's past year of commit activity
    Python 13 1 0 0 Updated Sep 17, 2026
  • VIABench Public

    VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance

    MCG-NJU/VIABench's past year of commit activity
    Python 9 0 0 0 Updated Aug 13, 2026
  • VideoRealBench Public

    [CVPR 2026] VideoRealBench: A Chain-of-Thought Realism Evaluation Benchmark for Generated Human-Centric Videos

    MCG-NJU/VideoRealBench's past year of commit activity
    Python 1 0 0 0 Updated Aug 6, 2026
  • MOTIP Public

    [CVPR 2025] Multiple Object Tracking as ID Prediction

    MCG-NJU/MOTIP's past year of commit activity
    Python 575 Apache-2.0 56 6 1 Updated Jul 30, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.