OpenMMLab website HOT      OpenMMLab platform TRY IT OUT
[![Documentation](https://readthedocs.org/projects/mmaction2/badge/?version=latest)](https://mmaction2.readthedocs.io/en/latest/) [![actions](https://github.com/open-mmlab/mmaction2/workflows/build/badge.svg)](https://github.com/open-mmlab/mmaction2/actions) [![codecov](https://codecov.io/gh/open-mmlab/mmaction2/branch/main/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmaction2) [![PyPI](https://img.shields.io/pypi/v/mmaction2)](https://pypi.org/project/mmaction2/) [![LICENSE](https://img.shields.io/github/license/open-mmlab/mmaction2.svg)](https://github.com/open-mmlab/mmaction2/blob/main/LICENSE) [![Average time to resolve an issue](https://isitmaintained.com/badge/resolution/open-mmlab/mmaction2.svg)](https://github.com/open-mmlab/mmaction2/issues) [![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmaction2.svg)](https://github.com/open-mmlab/mmaction2/issues) [๐Ÿ“˜Documentation](https://mmaction2.readthedocs.io/en/latest/) | [๐Ÿ› ๏ธInstallation](https://mmaction2.readthedocs.io/en/latest/get_started/installation.html) | [๐Ÿ‘€Model Zoo](https://mmaction2.readthedocs.io/en/latest/modelzoo_statistics.html) | [๐Ÿ†•Update News](https://mmaction2.readthedocs.io/en/latest/notes/changelog.html) | [๐Ÿš€Ongoing Projects](https://github.com/open-mmlab/mmaction2/projects) | [๐Ÿค”Reporting Issues](https://github.com/open-mmlab/mmaction2/issues/new/choose)
English | [็ฎ€ไฝ“ไธญๆ–‡](/README_zh-CN.md) ## ๐Ÿ“„ Table of Contents - [๐Ÿ“„ Table of Contents](#-table-of-contents) - [๐Ÿฅณ ๐Ÿš€ What's New](#--whats-new-) - [๐Ÿ“– Introduction](#-introduction-) - [๐ŸŽ Major Features](#-major-features-) - [๐Ÿ› ๏ธ Installation](#๏ธ-installation-) - [๐Ÿ‘€ Model Zoo](#-model-zoo-) - [๐Ÿ‘จโ€๐Ÿซ Get Started](#-get-started-) - [๐ŸŽซ License](#-license-) - [๐Ÿ–Š๏ธ Citation](#๏ธ-citation-) - [๐Ÿ™Œ Contributing](#-contributing-) - [๐Ÿค Acknowledgement](#-acknowledgement-) - [๐Ÿ—๏ธ Projects in OpenMMLab](#๏ธ-projects-in-openmmlab-) ## ๐Ÿฅณ ๐Ÿš€ What's New [๐Ÿ”](#-table-of-contents) **The default branch has been switched to `main`(previous `1.x`) from `master`(current `0.x`), and we encourage users to migrate to the latest version with more supported models, stronger pre-training checkpoints and simpler coding. Please refer to [Migration Guide](https://mmaction2.readthedocs.io/en/latest/migration.html) for more details.** **Release (2023.10.12)**: v1.2.0 with the following new features: - Support VindLU multi-modality algorithm and the Training of ActionClip - Support lightweight model MobileOne TSN/TSM - Support video retrieval dataset MSVD - Support SlowOnly K700 feature to train localization models - Support Video and Audio Demos ## ๐Ÿ“– Introduction [๐Ÿ”](#-table-of-contents) MMAction2 is an open-source toolbox for video understanding based on PyTorch. It is a part of the [OpenMMLab](http://openmmlab.com/) project.

Action Recognition on Kinetics-400 (left) and Skeleton-based Action Recognition on NTU-RGB+D-120 (right)


Skeleton-based Spatio-Temporal Action Detection and Action Recognition Results on Kinetics-400


Spatio-Temporal Action Detection Results on AVA-2.1

## ๐ŸŽ Major Features [๐Ÿ”](#-table-of-contents) - **Modular design**: We decompose a video understanding framework into different components. One can easily construct a customized video understanding framework by combining different modules. - **Support five major video understanding tasks**: MMAction2 implements various algorithms for multiple video understanding tasks, including action recognition, action localization, spatio-temporal action detection, skeleton-based action detection and video retrieval. - **Well tested and documented**: We provide detailed documentation and API reference, as well as unit tests. ## ๐Ÿ› ๏ธ Installation [๐Ÿ”](#-table-of-contents) MMAction2 depends on [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv), [MMEngine](https://github.com/open-mmlab/mmengine), [MMDetection](https://github.com/open-mmlab/mmdetection) (optional) and [MMPose](https://github.com/open-mmlab/mmpose) (optional). Please refer to [install.md](https://mmaction2.readthedocs.io/en/latest/get_started/installation.html) for detailed instructions.
Quick instructions ```shell conda create --name openmmlab python=3.8 -y conda activate openmmlab conda install pytorch torchvision -c pytorch # This command will automatically install the latest version PyTorch and cudatoolkit, please check whether they match your environment. pip install -U openmim mim install mmengine mim install mmcv mim install mmdet # optional mim install mmpose # optional git clone https://github.com/open-mmlab/mmaction2.git cd mmaction2 pip install -v -e . ```
## ๐Ÿ‘€ Model Zoo [๐Ÿ”](#-table-of-contents) Results and models are available in the [model zoo](https://mmaction2.readthedocs.io/en/latest/model_zoo/modelzoo.html).
Supported model
Action Recognition
C3D (CVPR'2014) TSN (ECCV'2016) I3D (CVPR'2017) C2D (CVPR'2018) I3D Non-Local (CVPR'2018)
R(2+1)D (CVPR'2018) TRN (ECCV'2018) TSM (ICCV'2019) TSM Non-Local (ICCV'2019) SlowOnly (ICCV'2019)
SlowFast (ICCV'2019) CSN (ICCV'2019) TIN (AAAI'2020) TPN (CVPR'2020) X3D (CVPR'2020)
MultiModality: Audio (ArXiv'2020) TANet (ArXiv'2020) TimeSformer (ICML'2021) ActionCLIP (ArXiv'2021) VideoSwin (CVPR'2022)
VideoMAE (NeurIPS'2022) MViT V2 (CVPR'2022) UniFormer V1 (ICLR'2022) UniFormer V2 (Arxiv'2022) VideoMAE V2 (CVPR'2023)
Action Localization
BSN (ECCV'2018) BMN (ICCV'2019) TCANet (CVPR'2021)
Spatio-Temporal Action Detection
ACRN (ECCV'2018) SlowOnly+Fast R-CNN (ICCV'2019) SlowFast+Fast R-CNN (ICCV'2019) LFB (CVPR'2019) VideoMAE (NeurIPS'2022)
Skeleton-based Action Recognition
ST-GCN (AAAI'2018) 2s-AGCN (CVPR'2019) PoseC3D (CVPR'2022) STGCN++ (ArXiv'2022) CTRGCN (CVPR'2021)
MSG3D (CVPR'2020)
Video Retrieval
CLIP4Clip (ArXiv'2022)
Supported dataset
Action Recognition
HMDB51 (Homepage) (ICCV'2011) UCF101 (Homepage) (CRCV-IR-12-01) ActivityNet (Homepage) (CVPR'2015) Kinetics-[400/600/700] (Homepage) (CVPR'2017)
SthV1 (ICCV'2017) SthV2 (Homepage) (ICCV'2017) Diving48 (Homepage) (ECCV'2018) Jester (Homepage) (ICCV'2019)
Moments in Time (Homepage) (TPAMI'2019) Multi-Moments in Time (Homepage) (ArXiv'2019) HVU (Homepage) (ECCV'2020) OmniSource (Homepage) (ECCV'2020)
FineGYM (Homepage) (CVPR'2020) Kinetics-710 (Homepage) (Arxiv'2022)
Action Localization
THUMOS14 (Homepage) (THUMOS Challenge 2014) ActivityNet (Homepage) (CVPR'2015) HACS (Homepage) (ICCV'2019)
Spatio-Temporal Action Detection
UCF101-24* (Homepage) (CRCV-IR-12-01) JHMDB* (Homepage) (ICCV'2015) AVA (Homepage) (CVPR'2018) AVA-Kinetics (Homepage) (Arxiv'2020)
MultiSports (Homepage) (ICCV'2021)
Skeleton-based Action Recognition
PoseC3D-FineGYM (Homepage) (ArXiv'2021) PoseC3D-NTURGB+D (Homepage) (ArXiv'2021) PoseC3D-UCF101 (Homepage) (ArXiv'2021) PoseC3D-HMDB51 (Homepage) (ArXiv'2021)
Video Retrieval
MSRVTT (Homepage) (CVPR'2016)
## ๐Ÿ‘จโ€๐Ÿซ Get Started [๐Ÿ”](#-table-of-contents) For tutorials, we provide the following user guides for basic usage: - [Migration from MMAction2 0.X](https://mmaction2.readthedocs.io/en/latest/migration.html) - [Learn about Configs](https://mmaction2.readthedocs.io/en/latest/user_guides/config.html) - [Prepare Datasets](https://mmaction2.readthedocs.io/en/latest/user_guides/prepare_dataset.html) - [Inference with Existing Models](https://mmaction2.readthedocs.io/en/latest/user_guides/inference.html) - [Training and Testing](https://mmaction2.readthedocs.io/en/latest/user_guides/train_test.html)
Research works built on MMAction2 by users from community - Video Swin Transformer. [\[paper\]](https://arxiv.org/abs/2106.13230)[\[github\]](https://github.com/SwinTransformer/Video-Swin-Transformer) - Evidential Deep Learning for Open Set Action Recognition, ICCV 2021 **Oral**. [\[paper\]](https://arxiv.org/abs/2107.10161)[\[github\]](https://github.com/Cogito2012/DEAR) - Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective, ICCV 2021 **Oral**. [\[paper\]](https://arxiv.org/abs/2103.17263)[\[github\]](https://github.com/xvjiarui/VFS)
## ๐ŸŽซ License [๐Ÿ”](#-table-of-contents) This project is released under the [Apache 2.0 license](LICENSE). ## ๐Ÿ–Š๏ธ Citation [๐Ÿ”](#-table-of-contents) If you find this project useful in your research, please consider cite: ```BibTeX @misc{2020mmaction2, title={OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark}, author={MMAction2 Contributors}, howpublished = {\url{https://github.com/open-mmlab/mmaction2}}, year={2020} } ``` ## ๐Ÿ™Œ Contributing [๐Ÿ”](#-table-of-contents) We appreciate all contributions to improve MMAction2. Please refer to [CONTRIBUTING.md](https://github.com/open-mmlab/mmcv/blob/2.x/CONTRIBUTING.md) in MMCV for more details about the contributing guideline. ## ๐Ÿค Acknowledgement [๐Ÿ”](#-table-of-contents) MMAction2 is an open-source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features and users who give valuable feedback. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their new models. ## ๐Ÿ—๏ธ Projects in OpenMMLab [๐Ÿ”](#-table-of-contents) - [MMEngine](https://github.com/open-mmlab/mmengine): OpenMMLab foundational library for training deep learning models. - [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab foundational library for computer vision. - [MIM](https://github.com/open-mmlab/mim): MIM installs OpenMMLab packages. - [MMEval](https://github.com/open-mmlab/mmeval): A unified evaluation library for multiple machine learning libraries. - [MMPreTrain](https://github.com/open-mmlab/mmpretrain): OpenMMLab pre-training toolbox and benchmark. - [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark. - [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection. - [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark. - [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO series toolbox and benchmark. - [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark. - [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox. - [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark. - [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 3D human parametric model toolbox and benchmark. - [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab self-supervised learning toolbox and benchmark. - [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab model compression toolbox and benchmark. - [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab fewshot learning toolbox and benchmark. - [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark. - [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark. - [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark. - [MMagic](https://github.com/open-mmlab/mmagic): Open**MM**Lab **A**dvanced, **G**enerative and **I**ntelligent **C**reation toolbox. - [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox. - [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab model deployment framework. - [Playground](https://github.com/open-mmlab/playground): A central hub for gathering and showcasing amazing projects built upon OpenMMLab.