OV-OAD

This repo takes the initial step towards leveraging text learning for online action detection without explicit human supervision.

Release Notes

• [2024/10/04] 🔥 OV-OAD Code release.

Models & Scripts

Installation

1. Clone this repository and navigate to the OV-OAD folder:

git clone https://github.com/OV-OAD
cd OV-OAD

2. Install the inference package:

conda create -n ovoad python=3.7 -y
conda activate ovoad

Project Navigation

Please checkout the following page for more inference & evaluation details.

Citation

If you find it useful for your research and applications, please cite related papers/blogs using this BibTeX:

@article{zhao2024ovoad,
  title={Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?},
  author={Qingsong Zhao, Yi Wang, Jilan Xu, Yinan He, Zifan Song, Limin Wang, Yu Qiao, Cairong Zhao},
  journal={Advances in neural information processing systems},
  year={2024}
}

Acknowledgement

• GroupViT: the codebase we built upon.
• Uniformer: the codebase we built upon.

Related Projects