OpenTAD: An Open-Source Temporal Action Detection Toolbox.
OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.
π₯³ What's New
- A technical report of this library will be provided soon.
- [2024/07/07] π₯ We support DyFADet (ECCV'24). Thanks to the authors's effort!
- [2024/06/17] π₯ We rank 1st in the Action Recognition, Action Detection, and Audio-Based Interaction Detection tasks of the EPIC-KITCHENS-100 2024 Challenge, as well as 1st place in the Moment Queries task of the Ego4D 2024 Challenge by using OpenTAD! The technical report and code will be released soon!
- [2024/06/14] We release version v0.3, which brings many new features and improvements.
- [2024/04/17] We release the AdaTAD (CVPR'24), which can achieve average mAP of 42.90% on ActivityNet and 77.07% on THUMOS14.
π Major Features
- Support SoTA TAD methods with modular design. We decompose the TAD pipeline into different components, and implement them in a modular way. This design makes it easy to implement new methods and reproduce existing methods.
- Support multiple TAD datasets. We support 9 TAD datasets, including ActivityNet-1.3, THUMOS-14, HACS, Ego4D-MQ, EPIC-Kitchens-100, FineAction, Multi-THUMOS, Charades, and EPIC-Sounds Detection datasets.
- Support feature-based training and end-to-end training. The feature-based training can easily be extended to end-to-end training with raw video input, and the video backbone can be easily replaced.
- Release various pre-extracted features. We release the feature extraction code, as well as many pre-extracted features on each dataset.
π Model Zoo
One Stage
|
Two Stage
|
DETR
|
End-to-End Training
|
|
|
|
|
The detailed configs, results, and pretrained models of each method can be found in above folders.
π οΈ Installation
Please refer to install.md for installation and data preparation.
π Usage
Please refer to usage.md for details of training and evaluation scripts.
π Updates
Please refer to changelog.md for update details.
π€ Roadmap
All the things that need to be done in the future is in roadmap.md.
ποΈ Citation
[Acknowledgement] This repo is inspired by OpenMMLab project, and we give our thanks to their contributors.
If you think this repo is helpful, please cite us:
@misc{2024opentad,
title={OpenTAD: An Open-Source Toolbox for Temporal Action Detection},
author={Shuming Liu, Chen Zhao, Fatimah Zohra, Mattia Soldan, Carlos Hinojosa, Alejandro Pardo, Anthony Cioppa, Lama Alssum, Mengmeng Xu, Merey Ramazanova, Juan LeΓ³n AlcΓ‘zar, Silvio Giancola, Bernard Ghanem},
howpublished = {\url{https://github.com/sming256/opentad}},
year={2024}
}
If you have any questions, please contact: shuming.liu@kaust.edu.sa
.