AdaTAD

This repo holds of CVPR2024 paper: "AdaTAD: End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames"

• The official pytorch implementation and pretrained checkpoints are released at OpenTAD.
• We achieve an average mAP of 42.90% on ActivityNet and 77.07% on THUMOS14. Please have a check!

Citation

@InProceedings{Liu_2024_CVPR,
    author    = {Liu, Shuming and Zhang, Chen-Lin and Zhao, Chen and Ghanem, Bernard},
    title     = {End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2024},
    pages     = {18591-18601}
}