{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pyskl-towards-good-practices-for-skeleton","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","arxiv_id":"2205.09443","date":"2022-05-19","proceeding":null,"authors":["Haodong Duan","Jiaqi Wang","Kai Chen","Dahua Lin"],"abstract":"We present PYSKL: an open-source toolbox for skeleton-based action recognition based on PyTorch. The toolbox supports a wide variety of skeleton action recognition algorithms, including approaches based on GCN and CNN. In contrast to existing open-source skeleton action recognition projects that include only one or two algorithms, PYSKL implements six different algorithms under a unified framework with both the latest and original good practices to ease the comparison of efficacy and efficiency. We also provide an original GCN-based skeleton action recognition model named ST-GCN++, which achieves competitive recognition performance without any complicated attention schemes, serving as a strong baseline. Meanwhile, PYSKL supports the training and testing of nine skeleton-based action recognition benchmarks and achieves state-of-the-art recognition performance on eight of them. To facilitate future research on skeleton action recognition, we also provide a large number of trained models and detailed benchmark results to give some insights. PYSKL is released at https://github.com/kennymckormick/pyskl and is actively maintained. We will update this report when we add new features or benchmarks. The current version corresponds to PYSKL v0.2.","url_abs":"https://arxiv.org/abs/2205.09443v1","url_pdf":"https://arxiv.org/pdf/2205.09443v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pyskl-towards-good-practices-for-skeleton","repo_url":"https://github.com/kennymckormick/pyskl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[{"method_slug":"gcn","method_name":"GCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"ST-GCN++ [PYSKL, 3D Skeleton]","rank_in_archive_order":32,"of":135,"metrics":{"Accuracy (CS)":"92.6","Accuracy (CV)":"97.4","Ensembled Modalities":"4"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"ST-GCN [PYSKL, 2D Skeleton]","rank_in_archive_order":42,"of":135,"metrics":{"Accuracy (CS)":"91.4","Accuracy (CV)":"98.3","Ensembled Modalities":"4"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"ST-GCN++ [PYSKL, 3D Skeleton]","rank_in_archive_order":28,"of":83,"metrics":{"Accuracy (Cross-Setup)":"90.8","Accuracy (Cross-Subject)":"88.6","Ensembled Modalities":"4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.09443","atlas_url":"https://app.syntology.ai/?focus=2205.09443","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}