Skip to content

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

License

Notifications You must be signed in to change notification settings

OpenGVLab/TimeSuite

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 

Repository files navigation

Xiangyu Zeng, Kunchang Li, Chenting Wang, Xinhao Li, Tianxiang Jiang, Ziang Yan, Songze Li, Yansong Shi, Zhengrong Yue, Yi Wang, Yali Wang, Yu Qiao, and Limin Wang

🦜 Introduction

This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for long video understanding, including a simple yet efficient framework to process long video sequence, a high-quality video dataset for grounded tuning of MLLMs, and a carefully-designed instruction tuning task to explicitly incorporate the grounding supervision in the traditional QA format.

State-of-the-art performance: VideoChat-T demonstrates high performance for both long-form video question answering and temporal grounding. alt text

Highly efficient model architecture with exceptional inference speed, encoding each video frame into just 3 tokens, leading to the flops of our VideoChat-T are 5.1% of Llava-OneVision alt text

High-quality data

  • We introduced the comprehensive dataset TimePro, which includes 9 task types with video sources from 15 different datasets.
  • We designed a novel Temporal Grounded Caption fine-tuning task to effectively mitigate hallucinations in MLLM. alt text

🔥 Updates

TODO

Inference & Demo

TODO

Evaluation Results

TODO

Grounded Training

TODO

📄 Citation

If you find this project useful in your research, please consider cite:

@article{zeng2024timesuite,
  title={Timesuite: Improving mllms for long video understanding via grounded tuning},
  author={Zeng, Xiangyu and Li, Kunchang and Wang, Chenting and Li, Xinhao and Jiang, Tianxiang and Yan, Ziang and Li, Songze and Shi, Yansong and Yue, Zhengrong and Wang, Yi and others},
  journal={arXiv preprint arXiv:2410.19702},
  year={2024}
}

💫 Acknowledgement

About

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published