<div align="center">
<img src="https://github.com/open-mmlab/mmaction2/raw/main/resources/mmaction2_logo.png" width="600"/>
<div> </div>
<div align="center">
<b><font size="5">OpenMMLab website</font></b>
<sup>
<a href="https://openmmlab.com">
<i><font size="4">HOT</font></i>
</a>
</sup>
<b><font size="5">OpenMMLab platform</font></b>
<sup>
<a href="https://platform.openmmlab.com">
<i><font size="4">TRY IT OUT</font></i>
</a>
</sup>
</div>
[](https://mmaction2.readthedocs.io/en/latest/)
[](https://github.com/open-mmlab/mmaction2/actions)
[](https://codecov.io/gh/open-mmlab/mmaction2)
[](https://pypi.org/project/mmaction2/)
[](https://github.com/open-mmlab/mmaction2/blob/main/LICENSE)
[](https://github.com/open-mmlab/mmaction2/issues)
[](https://github.com/open-mmlab/mmaction2/issues)
[๐Documentation](https://mmaction2.readthedocs.io/en/latest/) |
[๐ ๏ธInstallation](https://mmaction2.readthedocs.io/en/latest/get_started/installation.html) |
[๐Model Zoo](https://mmaction2.readthedocs.io/en/latest/modelzoo_statistics.html) |
[๐Update News](https://mmaction2.readthedocs.io/en/latest/notes/changelog.html) |
[๐Ongoing Projects](https://github.com/open-mmlab/mmaction2/projects) |
[๐คReporting Issues](https://github.com/open-mmlab/mmaction2/issues/new/choose)
</div>
<div align="center">
<a href="https://openmmlab.medium.com/" style="text-decoration:none;">
<img src="https://user-images.githubusercontent.com/25839884/219255827-67c1a27f-f8c5-46a9-811d-5e57448c61d1.png" width="3%" alt="" /></a>
<img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
<a href="https://discord.com/channels/1037617289144569886/1046608014234370059" style="text-decoration:none;">
<img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a>
<img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
<a href="https://twitter.com/OpenMMLab" style="text-decoration:none;">
<img src="https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png" width="3%" alt="" /></a>
<img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
<a href="https://www.youtube.com/openmmlab" style="text-decoration:none;">
<img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a>
<img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
<a href="https://space.bilibili.com/1293512903" style="text-decoration:none;">
<img src="https://user-images.githubusercontent.com/25839884/219026751-d7d14cce-a7c9-4e82-9942-8375fca65b99.png" width="3%" alt="" /></a>
<img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
<a href="https://www.zhihu.com/people/openmmlab" style="text-decoration:none;">
<img src="https://user-images.githubusercontent.com/25839884/219026120-ba71e48b-6e94-4bd4-b4e9-b7d175b5e362.png" width="3%" alt="" /></a>
</div>
English | [็ฎไฝไธญๆ](/README_zh-CN.md)
## ๐ Table of Contents
- [๐ Table of Contents](#-table-of-contents)
- [๐ฅณ ๐ What's New](#--whats-new-)
- [๐ Introduction](#-introduction-)
- [๐ Major Features](#-major-features-)
- [๐ ๏ธ Installation](#๏ธ-installation-)
- [๐ Model Zoo](#-model-zoo-)
- [๐จโ๐ซ Get Started](#-get-started-)
- [๐ซ License](#-license-)
- [๐๏ธ Citation](#๏ธ-citation-)
- [๐ Contributing](#-contributing-)
- [๐ค Acknowledgement](#-acknowledgement-)
- [๐๏ธ Projects in OpenMMLab](#๏ธ-projects-in-openmmlab-)
## ๐ฅณ ๐ What's New [๐](#-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
## ๐ Introduction [๐](#-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.
<div align="center">
<img src="https://github.com/open-mmlab/mmaction2/raw/main/resources/mmaction2_overview.gif" width="380px">
<img src="https://user-images.githubusercontent.com/34324155/123989146-2ecae680-d9fb-11eb-916b-b9db5563a9e5.gif" width="380px">
<p style="font-size:1.5vw;"> Action Recognition on Kinetics-400 (left) and Skeleton-based Action Recognition on NTU-RGB+D-120 (right)</p>
</div>
<div align="center">
<img src="https://user-images.githubusercontent.com/30782254/155710881-bb26863e-fcb4-458e-b0c4-33cd79f96901.gif" width="580px"/><br>
<p style="font-size:1.5vw;">Skeleton-based Spatio-Temporal Action Detection and Action Recognition Results on Kinetics-400</p>
</div>
<div align="center">
<img src="https://github.com/open-mmlab/mmaction2/raw/main/resources/spatio-temporal-det.gif" width="800px"/><br>
<p style="font-size:1.5vw;">Spatio-Temporal Action Detection Results on AVA-2.1</p>
</div>
## ๐ Major Features [๐](#-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.
## ๐ ๏ธ Installation [๐](#-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.
<details close>
<summary>Quick instructions</summary>
```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 .
```
</details>
## ๐ Model Zoo [๐](#-table-of-contents)
Results and models are available in the [model zoo](https://mmaction2.readthedocs.io/en/latest/model_zoo/modelzoo.html).
<details close>
<summary>Supported model</summary>
<table style="margin-left:auto;margin-right:auto;font-size:1.3vw;padding:3px 5px;text-align:center;vertical-align:center;">
<tr>
<td colspan="5" style="font-weight:bold;">Action Recognition</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/c3d/README.md">C3D</a> (CVPR'2014)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsn/README.md">TSN</a> (ECCV'2016)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/i3d/README.md">I3D</a> (CVPR'2017)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/c2d/README.md">C2D</a> (CVPR'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/i3d/README.md">I3D Non-Local</a> (CVPR'2018)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/r2plus1d/README.md">R(2+1)D</a> (CVPR'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/trn/README.md">TRN</a> (ECCV'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsm/README.md">TSM</a> (ICCV'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsm/README.md">TSM Non-Local</a> (ICCV'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/slowonly/README.md">SlowOnly</a> (ICCV'2019)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/slowfast/README.md">SlowFast</a> (ICCV'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/csn/README.md">CSN</a> (ICCV'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tin/README.md">TIN</a> (AAAI'2020)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tpn/README.md">TPN</a> (CVPR'2020)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/x3d/README.md">X3D</a> (CVPR'2020)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition_audio/resnet/README.md">MultiModality: Audio</a> (ArXiv'2020)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tanet/README.md">TANet</a> (ArXiv'2020)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/timesformer/README.md">TimeSformer</a> (ICML'2021)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/projects/actionclip/README.md">ActionCLIP</a> (ArXiv'2021)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/swin/README.md">VideoSwin</a> (CVPR'2022)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/videomae/README.md">VideoMAE</a> (NeurIPS'2022)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/mvit/README.md">MViT V2</a> (CVPR'2022)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/uniformer/README.md">UniFormer V1</a> (ICLR'2022)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/uniformerv2/README.md">UniFormer V2</a> (Arxiv'2022)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/videomaev2/README.md">VideoMAE V2</a> (CVPR'2023)</td>
</tr>
<tr>
<td colspan="5" style="font-weight:bold;">Action Localization</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/localization/bsn/README.md">BSN</a> (ECCV'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/localization/bmn/README.md">BMN</a> (ICCV'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/localization/tcanet/README.md">TCANet</a> (CVPR'2021)</td>
<td></td>
<td></td>
</tr>
<tr>
<td colspan="5" style="font-weight:bold;">Spatio-Temporal Action Detection</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/acrn/README.md">ACRN</a> (ECCV'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/slowonly/README.md">SlowOnly+Fast R-CNN</a> (ICCV'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/slowfast/README.md">SlowFast+Fast R-CNN</a> (ICCV'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/lfb/README.md">LFB</a> (CVPR'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/videomae/README.md">VideoMAE</a> (NeurIPS'2022)</td>
</tr>
<tr>
<td colspan="5" style="font-weight:bold;">Skeleton-based Action Recognition</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/stgcn/README.md">ST-GCN</a> (AAAI'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/2s-agcn/README.md">2s-AGCN</a> (CVPR'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/posec3d/README.md">PoseC3D</a> (CVPR'2022)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/stgcnpp/README.md">STGCN++</a> (ArXiv'2022)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/projects/ctrgcn/README.md">CTRGCN</a> (CVPR'2021)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/projects/msg3d/README.md">MSG3D</a> (CVPR'2020)</td>
<td></td>
<td></td>
<td></td>
<td></td>
</tr>
<tr>
<td colspan="5" style="font-weight:bold;">Video Retrieval</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/retrieval/clip4clip/README.md">CLIP4Clip</a> (ArXiv'2022)</td>
<td></td>
<td></td>
<td></td>
<td></td>
</tr>
</table>
</details>
<details close>
<summary>Supported dataset</summary>
<table style="margin-left:auto;margin-right:auto;font-size:1.3vw;padding:3px 5px;text-align:center;vertical-align:center;">
<tr>
<td colspan="4" style="font-weight:bold;">Action Recognition</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/hmdb51/README.md">HMDB51</a> (<a href="https://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/">Homepage</a>) (ICCV'2011)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ucf101/README.md">UCF101</a> (<a href="https://www.crcv.ucf.edu/research/data-sets/ucf101/">Homepage</a>) (CRCV-IR-12-01)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/activitynet/README.md">ActivityNet</a> (<a href="http://activity-net.org/">Homepage</a>) (CVPR'2015)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/kinetics/README.md">Kinetics-[400/600/700]</a> (<a href="https://deepmind.com/research/open-source/kinetics/">Homepage</a>) (CVPR'2017)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/sthv1/README.md">SthV1</a> (ICCV'2017)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/sthv2/README.md">SthV2</a> (<a href="https://developer.qualcomm.com/software/ai-datasets/something-something">Homepage</a>) (ICCV'2017)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/diving48/README.md">Diving48</a> (<a href="http://www.svcl.ucsd.edu/projects/resound/dataset.html">Homepage</a>) (ECCV'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/jester/README.md">Jester</a> (<a href="https://developer.qualcomm.com/software/ai-datasets/jester">Homepage</a>) (ICCV'2019)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/mit/README.md">Moments in Time</a> (<a href="http://moments.csail.mit.edu/">Homepage</a>) (TPAMI'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/mmit/README.md">Multi-Moments in Time</a> (<a href="http://moments.csail.mit.edu/challenge_iccv_2019.html">Homepage</a>) (ArXiv'2019)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/hvu/README.md">HVU</a> (<a href="https://github.com/holistic-video-understanding/HVU-Dataset">Homepage</a>) (ECCV'2020)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/omnisource/README.md">OmniSource</a> (<a href="https://kennymckormick.github.io/omnisource/">Homepage</a>) (ECCV'2020)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/gym/README.md">FineGYM</a> (<a href="https://sdolivia.github.io/FineGym/">Homepage</a>) (CVPR'2020)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/kinetics710/README.md">Kinetics-710</a> (<a href="https://arxiv.org/pdf/2211.09552.pdf">Homepage</a>) (Arxiv'2022)</td>
<td></td>
<td></td>
</tr>
<tr>
<td colspan="4" style="font-weight:bold;">Action Localization</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/thumos14/README.md">THUMOS14</a> (<a href="https://www.crcv.ucf.edu/THUMOS14/download.html">Homepage</a>) (THUMOS Challenge 2014)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/activitynet/README.md">ActivityNet</a> (<a href="http://activity-net.org/">Homepage</a>) (CVPR'2015)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/hacs/README.md">HACS</a> (<a href="https://github.com/hangzhaomit/HACS-dataset">Homepage</a>) (ICCV'2019)</td>
<td></td>
</tr>
<tr>
<td colspan="4" style="font-weight:bold;">Spatio-Temporal Action Detection</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ucf101_24/README.md">UCF101-24*</a> (<a href="http://www.thumos.info/download.html">Homepage</a>) (CRCV-IR-12-01)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/jhmdb/README.md">JHMDB*</a> (<a href="http://jhmdb.is.tue.mpg.de/">Homepage</a>) (ICCV'2015)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ava/README.md">AVA</a> (<a href="https://research.google.com/ava/index.html">Homepage</a>) (CVPR'2018)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ava_kinetics/README.md">AVA-Kinetics</a> (<a href="https://research.google.com/ava/index.html">Homepage</a>) (Arxiv'2020)</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/multisports/README.md">MultiSports</a> (<a href="https://deeperaction.github.io/datasets/multisports.html">Homepage</a>) (ICCV'2021)</td>
<td></td>
<td></td>
<td></td>
</tr>
<tr>
<td colspan="4" style="font-weight:bold;">Skeleton-based Action Recognition</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md">PoseC3D-FineGYM</a> (<a href="https://kennymckormick.github.io/posec3d/">Homepage</a>) (ArXiv'2021)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md">PoseC3D-NTURGB+D</a> (<a href="https://kennymckormick.github.io/posec3d/">Homepage</a>) (ArXiv'2021)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md">PoseC3D-UCF101</a> (<a href="https://kennymckormick.github.io/posec3d/">Homepage</a>) (ArXiv'2021)</td>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md">PoseC3D-HMDB51</a> (<a href="https://kennymckormick.github.io/posec3d/">Homepage</a>) (ArXiv'2021)</td>
</tr>
<tr>
<td colspan="4" style="font-weight:bold;">Video Retrieval</td>
</tr>
<tr>
<td><a href="https://github.com/open-mmlab/mmaction2/blob/main/tools/data/video_retrieval/README.md">MSRVTT</a> (<a href="https://www.microsoft.com/en-us/research/publication/msr-vtt-a-large-video-description-dataset-for-bridging-video-and-language/">Homepage</a>) (CVPR'2016)</td>
<td></td>
<td></td>
<td></td>
</tr>
</table>
</details>
## ๐จโ๐ซ Get Started [๐](#-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)
<details close>
<summary>Research works built on MMAction2 by users from community</summary>
- 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)
</details>
## ๐ซ License [๐](#-table-of-contents)
This project is released under the [Apache 2.0 license](LICENSE).
## ๐๏ธ Citation [๐](#-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}
}
```
## ๐ Contributing [๐](#-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.
## ๐ค Acknowledgement [๐](#-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.
## ๐๏ธ Projects in OpenMMLab [๐](#-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.
Raw data
{
"_id": null,
"home_page": "https://github.com/open-mmlab/mmaction2",
"name": "otxmmaction2",
"maintainer": "MMAction2 Contributors",
"docs_url": null,
"requires_python": "",
"maintainer_email": "openmmlab@gmail.com",
"keywords": "computer vision,video understanding",
"author": "MMAction2 Contributors",
"author_email": "openmmlab@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/f8/84/5fddb7d83804814800e7f1f3118bf480ce722969ed7f55ad25ccfdb66652/otxmmaction2-1.2.0.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <img src=\"https://github.com/open-mmlab/mmaction2/raw/main/resources/mmaction2_logo.png\" width=\"600\"/>\n <div> </div>\n <div align=\"center\">\n <b><font size=\"5\">OpenMMLab website</font></b>\n <sup>\n <a href=\"https://openmmlab.com\">\n <i><font size=\"4\">HOT</font></i>\n </a>\n </sup>\n \n <b><font size=\"5\">OpenMMLab platform</font></b>\n <sup>\n <a href=\"https://platform.openmmlab.com\">\n <i><font size=\"4\">TRY IT OUT</font></i>\n </a>\n </sup>\n </div>\n\n[](https://mmaction2.readthedocs.io/en/latest/)\n[](https://github.com/open-mmlab/mmaction2/actions)\n[](https://codecov.io/gh/open-mmlab/mmaction2)\n[](https://pypi.org/project/mmaction2/)\n[](https://github.com/open-mmlab/mmaction2/blob/main/LICENSE)\n[](https://github.com/open-mmlab/mmaction2/issues)\n[](https://github.com/open-mmlab/mmaction2/issues)\n\n[\ud83d\udcd8Documentation](https://mmaction2.readthedocs.io/en/latest/) |\n[\ud83d\udee0\ufe0fInstallation](https://mmaction2.readthedocs.io/en/latest/get_started/installation.html) |\n[\ud83d\udc40Model Zoo](https://mmaction2.readthedocs.io/en/latest/modelzoo_statistics.html) |\n[\ud83c\udd95Update News](https://mmaction2.readthedocs.io/en/latest/notes/changelog.html) |\n[\ud83d\ude80Ongoing Projects](https://github.com/open-mmlab/mmaction2/projects) |\n[\ud83e\udd14Reporting Issues](https://github.com/open-mmlab/mmaction2/issues/new/choose)\n\n</div>\n\n<div align=\"center\">\n <a href=\"https://openmmlab.medium.com/\" style=\"text-decoration:none;\">\n <img src=\"https://user-images.githubusercontent.com/25839884/219255827-67c1a27f-f8c5-46a9-811d-5e57448c61d1.png\" width=\"3%\" alt=\"\" /></a>\n <img src=\"https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png\" width=\"3%\" alt=\"\" />\n <a href=\"https://discord.com/channels/1037617289144569886/1046608014234370059\" style=\"text-decoration:none;\">\n <img src=\"https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png\" width=\"3%\" alt=\"\" /></a>\n <img src=\"https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png\" width=\"3%\" alt=\"\" />\n <a href=\"https://twitter.com/OpenMMLab\" style=\"text-decoration:none;\">\n <img src=\"https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png\" width=\"3%\" alt=\"\" /></a>\n <img src=\"https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png\" width=\"3%\" alt=\"\" />\n <a href=\"https://www.youtube.com/openmmlab\" style=\"text-decoration:none;\">\n <img src=\"https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png\" width=\"3%\" alt=\"\" /></a>\n <img src=\"https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png\" width=\"3%\" alt=\"\" />\n <a href=\"https://space.bilibili.com/1293512903\" style=\"text-decoration:none;\">\n <img src=\"https://user-images.githubusercontent.com/25839884/219026751-d7d14cce-a7c9-4e82-9942-8375fca65b99.png\" width=\"3%\" alt=\"\" /></a>\n <img src=\"https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png\" width=\"3%\" alt=\"\" />\n <a href=\"https://www.zhihu.com/people/openmmlab\" style=\"text-decoration:none;\">\n <img src=\"https://user-images.githubusercontent.com/25839884/219026120-ba71e48b-6e94-4bd4-b4e9-b7d175b5e362.png\" width=\"3%\" alt=\"\" /></a>\n</div>\n\nEnglish | [\u7b80\u4f53\u4e2d\u6587](/README_zh-CN.md)\n\n## \ud83d\udcc4 Table of Contents\n\n- [\ud83d\udcc4 Table of Contents](#-table-of-contents)\n- [\ud83e\udd73 \ud83d\ude80 What's New](#--whats-new-)\n- [\ud83d\udcd6 Introduction](#-introduction-)\n- [\ud83c\udf81 Major Features](#-major-features-)\n- [\ud83d\udee0\ufe0f Installation](#\ufe0f-installation-)\n- [\ud83d\udc40 Model Zoo](#-model-zoo-)\n- [\ud83d\udc68\u200d\ud83c\udfeb Get Started](#-get-started-)\n- [\ud83c\udfab License](#-license-)\n- [\ud83d\udd8a\ufe0f Citation](#\ufe0f-citation-)\n- [\ud83d\ude4c Contributing](#-contributing-)\n- [\ud83e\udd1d Acknowledgement](#-acknowledgement-)\n- [\ud83c\udfd7\ufe0f Projects in OpenMMLab](#\ufe0f-projects-in-openmmlab-)\n\n## \ud83e\udd73 \ud83d\ude80 What's New [\ud83d\udd1d](#-table-of-contents)\n\n**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.**\n\n**Release (2023.10.12)**: v1.2.0 with the following new features:\n\n- Support VindLU multi-modality algorithm and the Training of ActionClip\n- Support lightweight model MobileOne TSN/TSM\n- Support video retrieval dataset MSVD\n- Support SlowOnly K700 feature to train localization models\n- Support Video and Audio Demos\n\n## \ud83d\udcd6 Introduction [\ud83d\udd1d](#-table-of-contents)\n\nMMAction2 is an open-source toolbox for video understanding based on PyTorch.\nIt is a part of the [OpenMMLab](http://openmmlab.com/) project.\n\n<div align=\"center\">\n <img src=\"https://github.com/open-mmlab/mmaction2/raw/main/resources/mmaction2_overview.gif\" width=\"380px\">\n <img src=\"https://user-images.githubusercontent.com/34324155/123989146-2ecae680-d9fb-11eb-916b-b9db5563a9e5.gif\" width=\"380px\">\n <p style=\"font-size:1.5vw;\"> Action Recognition on Kinetics-400 (left) and Skeleton-based Action Recognition on NTU-RGB+D-120 (right)</p>\n</div>\n\n<div align=\"center\">\n <img src=\"https://user-images.githubusercontent.com/30782254/155710881-bb26863e-fcb4-458e-b0c4-33cd79f96901.gif\" width=\"580px\"/><br>\n <p style=\"font-size:1.5vw;\">Skeleton-based Spatio-Temporal Action Detection and Action Recognition Results on Kinetics-400</p>\n</div>\n<div align=\"center\">\n <img src=\"https://github.com/open-mmlab/mmaction2/raw/main/resources/spatio-temporal-det.gif\" width=\"800px\"/><br>\n <p style=\"font-size:1.5vw;\">Spatio-Temporal Action Detection Results on AVA-2.1</p>\n</div>\n\n## \ud83c\udf81 Major Features [\ud83d\udd1d](#-table-of-contents)\n\n- **Modular design**: We decompose a video understanding framework into different components. One can easily construct a customized video understanding framework by combining different modules.\n\n- **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.\n\n- **Well tested and documented**: We provide detailed documentation and API reference, as well as unit tests.\n\n## \ud83d\udee0\ufe0f Installation [\ud83d\udd1d](#-table-of-contents)\n\nMMAction2 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).\n\nPlease refer to [install.md](https://mmaction2.readthedocs.io/en/latest/get_started/installation.html) for detailed instructions.\n\n<details close>\n<summary>Quick instructions</summary>\n\n```shell\nconda create --name openmmlab python=3.8 -y\nconda activate openmmlab\nconda install pytorch torchvision -c pytorch # This command will automatically install the latest version PyTorch and cudatoolkit, please check whether they match your environment.\npip install -U openmim\nmim install mmengine\nmim install mmcv\nmim install mmdet # optional\nmim install mmpose # optional\ngit clone https://github.com/open-mmlab/mmaction2.git\ncd mmaction2\npip install -v -e .\n```\n\n</details>\n\n## \ud83d\udc40 Model Zoo [\ud83d\udd1d](#-table-of-contents)\n\nResults and models are available in the [model zoo](https://mmaction2.readthedocs.io/en/latest/model_zoo/modelzoo.html).\n\n<details close>\n\n<summary>Supported model</summary>\n\n<table style=\"margin-left:auto;margin-right:auto;font-size:1.3vw;padding:3px 5px;text-align:center;vertical-align:center;\">\n <tr>\n <td colspan=\"5\" style=\"font-weight:bold;\">Action Recognition</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/c3d/README.md\">C3D</a> (CVPR'2014)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsn/README.md\">TSN</a> (ECCV'2016)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/i3d/README.md\">I3D</a> (CVPR'2017)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/c2d/README.md\">C2D</a> (CVPR'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/i3d/README.md\">I3D Non-Local</a> (CVPR'2018)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/r2plus1d/README.md\">R(2+1)D</a> (CVPR'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/trn/README.md\">TRN</a> (ECCV'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsm/README.md\">TSM</a> (ICCV'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsm/README.md\">TSM Non-Local</a> (ICCV'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/slowonly/README.md\">SlowOnly</a> (ICCV'2019)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/slowfast/README.md\">SlowFast</a> (ICCV'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/csn/README.md\">CSN</a> (ICCV'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tin/README.md\">TIN</a> (AAAI'2020)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tpn/README.md\">TPN</a> (CVPR'2020)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/x3d/README.md\">X3D</a> (CVPR'2020)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition_audio/resnet/README.md\">MultiModality: Audio</a> (ArXiv'2020)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tanet/README.md\">TANet</a> (ArXiv'2020)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/timesformer/README.md\">TimeSformer</a> (ICML'2021)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/projects/actionclip/README.md\">ActionCLIP</a> (ArXiv'2021)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/swin/README.md\">VideoSwin</a> (CVPR'2022)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/videomae/README.md\">VideoMAE</a> (NeurIPS'2022)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/mvit/README.md\">MViT V2</a> (CVPR'2022)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/uniformer/README.md\">UniFormer V1</a> (ICLR'2022)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/uniformerv2/README.md\">UniFormer V2</a> (Arxiv'2022)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/videomaev2/README.md\">VideoMAE V2</a> (CVPR'2023)</td>\n </tr>\n <tr>\n <td colspan=\"5\" style=\"font-weight:bold;\">Action Localization</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/localization/bsn/README.md\">BSN</a> (ECCV'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/localization/bmn/README.md\">BMN</a> (ICCV'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/localization/tcanet/README.md\">TCANet</a> (CVPR'2021)</td>\n <td></td>\n <td></td>\n </tr>\n <tr>\n <td colspan=\"5\" style=\"font-weight:bold;\">Spatio-Temporal Action Detection</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/acrn/README.md\">ACRN</a> (ECCV'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/slowonly/README.md\">SlowOnly+Fast R-CNN</a> (ICCV'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/slowfast/README.md\">SlowFast+Fast R-CNN</a> (ICCV'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/detection/lfb/README.md\">LFB</a> (CVPR'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/videomae/README.md\">VideoMAE</a> (NeurIPS'2022)</td>\n </tr>\n <tr>\n <td colspan=\"5\" style=\"font-weight:bold;\">Skeleton-based Action Recognition</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/stgcn/README.md\">ST-GCN</a> (AAAI'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/2s-agcn/README.md\">2s-AGCN</a> (CVPR'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/posec3d/README.md\">PoseC3D</a> (CVPR'2022)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/skeleton/stgcnpp/README.md\">STGCN++</a> (ArXiv'2022)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/projects/ctrgcn/README.md\">CTRGCN</a> (CVPR'2021)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/projects/msg3d/README.md\">MSG3D</a> (CVPR'2020)</td>\n <td></td>\n <td></td>\n <td></td>\n <td></td>\n </tr>\n <tr>\n <td colspan=\"5\" style=\"font-weight:bold;\">Video Retrieval</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/configs/retrieval/clip4clip/README.md\">CLIP4Clip</a> (ArXiv'2022)</td>\n <td></td>\n <td></td>\n <td></td>\n <td></td>\n </tr>\n\n</table>\n\n</details>\n\n<details close>\n\n<summary>Supported dataset</summary>\n\n<table style=\"margin-left:auto;margin-right:auto;font-size:1.3vw;padding:3px 5px;text-align:center;vertical-align:center;\">\n <tr>\n <td colspan=\"4\" style=\"font-weight:bold;\">Action Recognition</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/hmdb51/README.md\">HMDB51</a> (<a href=\"https://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/\">Homepage</a>) (ICCV'2011)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ucf101/README.md\">UCF101</a> (<a href=\"https://www.crcv.ucf.edu/research/data-sets/ucf101/\">Homepage</a>) (CRCV-IR-12-01)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/activitynet/README.md\">ActivityNet</a> (<a href=\"http://activity-net.org/\">Homepage</a>) (CVPR'2015)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/kinetics/README.md\">Kinetics-[400/600/700]</a> (<a href=\"https://deepmind.com/research/open-source/kinetics/\">Homepage</a>) (CVPR'2017)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/sthv1/README.md\">SthV1</a> (ICCV'2017)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/sthv2/README.md\">SthV2</a> (<a href=\"https://developer.qualcomm.com/software/ai-datasets/something-something\">Homepage</a>) (ICCV'2017)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/diving48/README.md\">Diving48</a> (<a href=\"http://www.svcl.ucsd.edu/projects/resound/dataset.html\">Homepage</a>) (ECCV'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/jester/README.md\">Jester</a> (<a href=\"https://developer.qualcomm.com/software/ai-datasets/jester\">Homepage</a>) (ICCV'2019)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/mit/README.md\">Moments in Time</a> (<a href=\"http://moments.csail.mit.edu/\">Homepage</a>) (TPAMI'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/mmit/README.md\">Multi-Moments in Time</a> (<a href=\"http://moments.csail.mit.edu/challenge_iccv_2019.html\">Homepage</a>) (ArXiv'2019)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/hvu/README.md\">HVU</a> (<a href=\"https://github.com/holistic-video-understanding/HVU-Dataset\">Homepage</a>) (ECCV'2020)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/omnisource/README.md\">OmniSource</a> (<a href=\"https://kennymckormick.github.io/omnisource/\">Homepage</a>) (ECCV'2020)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/gym/README.md\">FineGYM</a> (<a href=\"https://sdolivia.github.io/FineGym/\">Homepage</a>) (CVPR'2020)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/kinetics710/README.md\">Kinetics-710</a> (<a href=\"https://arxiv.org/pdf/2211.09552.pdf\">Homepage</a>) (Arxiv'2022)</td>\n <td></td>\n <td></td>\n </tr>\n <tr>\n <td colspan=\"4\" style=\"font-weight:bold;\">Action Localization</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/thumos14/README.md\">THUMOS14</a> (<a href=\"https://www.crcv.ucf.edu/THUMOS14/download.html\">Homepage</a>) (THUMOS Challenge 2014)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/activitynet/README.md\">ActivityNet</a> (<a href=\"http://activity-net.org/\">Homepage</a>) (CVPR'2015)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/hacs/README.md\">HACS</a> (<a href=\"https://github.com/hangzhaomit/HACS-dataset\">Homepage</a>) (ICCV'2019)</td>\n <td></td>\n </tr>\n <tr>\n <td colspan=\"4\" style=\"font-weight:bold;\">Spatio-Temporal Action Detection</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ucf101_24/README.md\">UCF101-24*</a> (<a href=\"http://www.thumos.info/download.html\">Homepage</a>) (CRCV-IR-12-01)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/jhmdb/README.md\">JHMDB*</a> (<a href=\"http://jhmdb.is.tue.mpg.de/\">Homepage</a>) (ICCV'2015)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ava/README.md\">AVA</a> (<a href=\"https://research.google.com/ava/index.html\">Homepage</a>) (CVPR'2018)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/ava_kinetics/README.md\">AVA-Kinetics</a> (<a href=\"https://research.google.com/ava/index.html\">Homepage</a>) (Arxiv'2020)</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/multisports/README.md\">MultiSports</a> (<a href=\"https://deeperaction.github.io/datasets/multisports.html\">Homepage</a>) (ICCV'2021)</td>\n <td></td>\n <td></td>\n <td></td>\n </tr>\n <tr>\n <td colspan=\"4\" style=\"font-weight:bold;\">Skeleton-based Action Recognition</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md\">PoseC3D-FineGYM</a> (<a href=\"https://kennymckormick.github.io/posec3d/\">Homepage</a>) (ArXiv'2021)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md\">PoseC3D-NTURGB+D</a> (<a href=\"https://kennymckormick.github.io/posec3d/\">Homepage</a>) (ArXiv'2021)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md\">PoseC3D-UCF101</a> (<a href=\"https://kennymckormick.github.io/posec3d/\">Homepage</a>) (ArXiv'2021)</td>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/skeleton/README.md\">PoseC3D-HMDB51</a> (<a href=\"https://kennymckormick.github.io/posec3d/\">Homepage</a>) (ArXiv'2021)</td>\n </tr>\n <tr>\n <td colspan=\"4\" style=\"font-weight:bold;\">Video Retrieval</td>\n </tr>\n <tr>\n <td><a href=\"https://github.com/open-mmlab/mmaction2/blob/main/tools/data/video_retrieval/README.md\">MSRVTT</a> (<a href=\"https://www.microsoft.com/en-us/research/publication/msr-vtt-a-large-video-description-dataset-for-bridging-video-and-language/\">Homepage</a>) (CVPR'2016)</td>\n <td></td>\n <td></td>\n <td></td>\n </tr>\n\n</table>\n\n</details>\n\n## \ud83d\udc68\u200d\ud83c\udfeb Get Started [\ud83d\udd1d](#-table-of-contents)\n\nFor tutorials, we provide the following user guides for basic usage:\n\n- [Migration from MMAction2 0.X](https://mmaction2.readthedocs.io/en/latest/migration.html)\n- [Learn about Configs](https://mmaction2.readthedocs.io/en/latest/user_guides/config.html)\n- [Prepare Datasets](https://mmaction2.readthedocs.io/en/latest/user_guides/prepare_dataset.html)\n- [Inference with Existing Models](https://mmaction2.readthedocs.io/en/latest/user_guides/inference.html)\n- [Training and Testing](https://mmaction2.readthedocs.io/en/latest/user_guides/train_test.html)\n\n<details close>\n<summary>Research works built on MMAction2 by users from community</summary>\n\n- Video Swin Transformer. [\\[paper\\]](https://arxiv.org/abs/2106.13230)[\\[github\\]](https://github.com/SwinTransformer/Video-Swin-Transformer)\n- Evidential Deep Learning for Open Set Action Recognition, ICCV 2021 **Oral**. [\\[paper\\]](https://arxiv.org/abs/2107.10161)[\\[github\\]](https://github.com/Cogito2012/DEAR)\n- 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)\n\n</details>\n\n## \ud83c\udfab License [\ud83d\udd1d](#-table-of-contents)\n\nThis project is released under the [Apache 2.0 license](LICENSE).\n\n## \ud83d\udd8a\ufe0f Citation [\ud83d\udd1d](#-table-of-contents)\n\nIf you find this project useful in your research, please consider cite:\n\n```BibTeX\n@misc{2020mmaction2,\n title={OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark},\n author={MMAction2 Contributors},\n howpublished = {\\url{https://github.com/open-mmlab/mmaction2}},\n year={2020}\n}\n```\n\n## \ud83d\ude4c Contributing [\ud83d\udd1d](#-table-of-contents)\n\nWe 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.\n\n## \ud83e\udd1d Acknowledgement [\ud83d\udd1d](#-table-of-contents)\n\nMMAction2 is an open-source project that is contributed by researchers and engineers from various colleges and companies.\nWe appreciate all the contributors who implement their methods or add new features and users who give valuable feedback.\nWe 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.\n\n## \ud83c\udfd7\ufe0f Projects in OpenMMLab [\ud83d\udd1d](#-table-of-contents)\n\n- [MMEngine](https://github.com/open-mmlab/mmengine): OpenMMLab foundational library for training deep learning models.\n- [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab foundational library for computer vision.\n- [MIM](https://github.com/open-mmlab/mim): MIM installs OpenMMLab packages.\n- [MMEval](https://github.com/open-mmlab/mmeval): A unified evaluation library for multiple machine learning libraries.\n- [MMPreTrain](https://github.com/open-mmlab/mmpretrain): OpenMMLab pre-training toolbox and benchmark.\n- [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark.\n- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.\n- [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark.\n- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO series toolbox and benchmark.\n- [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.\n- [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox.\n- [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.\n- [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 3D human parametric model toolbox and benchmark.\n- [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab self-supervised learning toolbox and benchmark.\n- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab model compression toolbox and benchmark.\n- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab fewshot learning toolbox and benchmark.\n- [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark.\n- [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.\n- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark.\n- [MMagic](https://github.com/open-mmlab/mmagic): Open**MM**Lab **A**dvanced, **G**enerative and **I**ntelligent **C**reation toolbox.\n- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox.\n- [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab model deployment framework.\n- [Playground](https://github.com/open-mmlab/playground): A central hub for gathering and showcasing amazing projects built upon OpenMMLab.\n",
"bugtrack_url": null,
"license": "Apache License 2.0",
"summary": "OpenMMLab Video Understanding Toolbox and Benchmark",
"version": "1.2.0",
"project_urls": {
"Homepage": "https://github.com/open-mmlab/mmaction2"
},
"split_keywords": [
"computer vision",
"video understanding"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "bd40eb42baa2647fc5d7c74c6bea6b860353dd62723400535eab6d355e2d18b1",
"md5": "5d43201f27f997531b189f30b8847677",
"sha256": "cb9b47987176104d7d33e38c6fba215e86f25f2efd86c0dc63262cc76866a9d4"
},
"downloads": -1,
"filename": "otxmmaction2-1.2.0-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "5d43201f27f997531b189f30b8847677",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": null,
"size": 895491,
"upload_time": "2024-01-03T03:00:14",
"upload_time_iso_8601": "2024-01-03T03:00:14.338724Z",
"url": "https://files.pythonhosted.org/packages/bd/40/eb42baa2647fc5d7c74c6bea6b860353dd62723400535eab6d355e2d18b1/otxmmaction2-1.2.0-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "f8845fddb7d83804814800e7f1f3118bf480ce722969ed7f55ad25ccfdb66652",
"md5": "574153eeb7d73c3eedcaa6c63cbb22e2",
"sha256": "6119e1ae4e157cc6dc69dc37b28df9c542fc7d58620f1e3435c0be41c9f7fb65"
},
"downloads": -1,
"filename": "otxmmaction2-1.2.0.tar.gz",
"has_sig": false,
"md5_digest": "574153eeb7d73c3eedcaa6c63cbb22e2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 485699,
"upload_time": "2024-01-03T03:00:19",
"upload_time_iso_8601": "2024-01-03T03:00:19.302014Z",
"url": "https://files.pythonhosted.org/packages/f8/84/5fddb7d83804814800e7f1f3118bf480ce722969ed7f55ad25ccfdb66652/otxmmaction2-1.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-03 03:00:19",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "open-mmlab",
"github_project": "mmaction2",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"circle": true,
"requirements": [],
"lcname": "otxmmaction2"
}
JSON
