{"id":13653440,"url":"https://github.com/open-mmlab/mmskeleton","last_synced_at":"2025-04-13T18:37:37.713Z","repository":{"id":39696290,"uuid":"111524376","full_name":"open-mmlab/mmskeleton","owner":"open-mmlab","description":"A OpenMMLAB toolbox  for human pose estimation, skeleton-based action recognition, and action synthesis.","archived":false,"fork":false,"pushed_at":"2022-11-25T20:02:00.000Z","size":95585,"stargazers_count":2981,"open_issues_count":203,"forks_count":1039,"subscribers_count":70,"default_branch":"master","last_synced_at":"2025-04-06T15:09:11.641Z","etag":null,"topics":["action-recognition","deep-learning","graph-convolutional-network","pytorch","skeleton-based-action-recognition"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/open-mmlab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-11-21T09:01:44.000Z","updated_at":"2025-04-02T10:18:22.000Z","dependencies_parsed_at":"2023-01-22T02:36:20.764Z","dependency_job_id":null,"html_url":"https://github.com/open-mmlab/mmskeleton","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2Fmmskeleton","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2Fmmskeleton/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2Fmmskeleton/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2Fmmskeleton/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/open-mmlab","download_url":"https://codeload.github.com/open-mmlab/mmskeleton/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248762277,"owners_count":21157705,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["action-recognition","deep-learning","graph-convolutional-network","pytorch","skeleton-based-action-recognition"],"created_at":"2024-08-02T02:01:10.468Z","updated_at":"2025-04-13T18:37:37.694Z","avatar_url":"https://github.com/open-mmlab.png","language":"Python","readme":"# MMSkeleton\n\n## Introduction\n\nMMSkeleton is an open source toolbox for skeleton-based human understanding.\nIt is a part of the [open-mmlab](https://github.com/open-mmlab) project in the charge of [Multimedia Laboratory, CUHK](http://mmlab.ie.cuhk.edu.hk/).\nMMSkeleton is developed on our research project [ST-GCN](https://github.com/yysijie/st-gcn/blob/master/OLD_README.md).\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"demo/recognition/demo_video.gif\", width=\"700\"\u003e\n\u003c/p\u003e\n\n## Updates\n- [2020-01-21] MMSkeleton v0.7 is released.\n- [2019-10-09] MMSkeleton v0.6 is released.\n- [2019-10-08] Support model zoo.\n- [2019-10-02] Support custom dataset.\n- [2019-09-23] Add video-based pose estimation demo.\n- [2019-08-29] MMSkeleton v0.5 is released.\n\n\n## Features\n\n- **High extensibility**\n\n    MMSkeleton provides a flexible framework for organizing codes and projects systematically, with the ability to extend to various tasks and scale up to complex deep models.\n\n- **Multiple tasks**\n\n    MMSkeleton addresses to multiple tasks in human understanding, including but not limited to:\n    - [x] [skeleton-based action recognition (ST-GCN)](./doc/START_RECOGNITION.md)\n    - [x] [2D pose estimation](./doc/START_POSE_ESTIMATION.md)\n    - [ ] skeleton-based action generation\n    - [ ] 3D pose estimation\n    - [ ] pose tracking\n    - [x] [build custom skeleton-based dataset](./doc/CUSTOM_DATASET.md)\n    - [x] [create your own applications](./doc/CREATE_APPLICATION.md)\n\n## Getting Started\n\nPlease see [GETTING_STARTED.md](./doc/GETTING_STARTED.md) for more details of MMSkeleton.\n\n## License\nThe project is release under the [Apache 2.0 license](./LICENSE).\n\n## Contributing\nWe appreciate all contributions to improve MMSkeleton.\nPlease refer to [CONTRIBUTING.md](./doc/CONTRIBUTING.md) for the contributing guideline.\n\n\n## Citation\nPlease cite the following paper if you use this repository in your reseach.\n\u003c!-- @inproceedings{stgcn2018aaai,\n  title     = {Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition},\n  author    = {Sijie Yan and Yuanjun Xiong and Dahua Lin},\n  booktitle = {AAAI},\n  year      = {2018},\n} --\u003e\n```\n@misc{mmskeleton2019,\n  author =       {Sijie Yan, Yuanjun Xiong, Jingbo Wang, Dahua Lin},\n  title =        {MMSkeleton},\n  howpublished = {\\url{https://github.com/open-mmlab/mmskeleton}},\n  year =         {2019}\n}\n```\n\n## Contact\nFor any question, feel free to contact\n```\nSijie Yan     : ys016@ie.cuhk.edu.hk\nJingbo Wang   : wangjingbo1219@foxmail.com\nYuanjun Xiong : bitxiong@gmail.com\n```\n","funding_links":[],"categories":["Python","Computer Vision","人像\\姿势\\3D人脸"],"sub_categories":["General Purpose CV","网络服务_其他"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopen-mmlab%2Fmmskeleton","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopen-mmlab%2Fmmskeleton","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopen-mmlab%2Fmmskeleton/lists"}