{"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/make-skeleton-based-action-recognition-model-1","title":"Make Skeleton-based Action Recognition Model Smaller, Faster and Better","arxiv_id":"1907.09658","date":"2019-07-23","proceeding":"arXiv 2019 7","authors":["Fan Yang","Sakriani Sakti","Yang Wu","Satoshi Nakamura"],"abstract":"Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To alleviate this issue, we analyze skeleton sequence properties to propose a Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition. By using a lightweight network structure (i.e., 0.15 million parameters), DD-Net can reach a super fast speed, as 3,500 FPS on one GPU, or, 2,000 FPS on one CPU. By employing robust features, DD-Net achieves the state-of-the-art performance on our experimental datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code will be released with this paper later.","url_abs":"https://arxiv.org/abs/1907.09658v8","url_pdf":"https://arxiv.org/pdf/1907.09658v8.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":"make-skeleton-based-action-recognition-model-1","repo_url":"https://github.com/fandulu/DD-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"make-skeleton-based-action-recognition-model-1","repo_url":"https://github.com/paty0504/SIGNTEGRATE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"make-skeleton-based-action-recognition-model-1","repo_url":"https://github.com/BlurryLight/DD-Net-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"hand-gesture-recognition","task_name":"Hand Gesture Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hand-gesture-recognition-on-dhg-14","task":"Hand Gesture Recognition","dataset":"DHG-14","model":"DD-Net","rank_in_archive_order":3,"of":13,"metrics":{"Accuracy":"94.6"},"uses_additional_data":false},{"leaderboard":"/sota/hand-gesture-recognition-on-dhg-28","task":"Hand Gesture Recognition","dataset":"DHG-28","model":"DD-Net","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"91.9"},"uses_additional_data":false},{"leaderboard":"/sota/hand-gesture-recognition-on-shrec-2017-track","task":"Hand Gesture Recognition","dataset":"SHREC 2017 track on 3D Hand Gesture Recognition","model":"DD-Net","rank_in_archive_order":3,"of":3,"metrics":{"14 gestures accuracy":"94.6"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-j-hmdb","task":"Skeleton Based Action Recognition","dataset":"J-HMDB","model":"DD-Net","rank_in_archive_order":12,"of":13,"metrics":{"Accuracy (RGB+pose)":"-","Accuracy (pose)":"77.2"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-jhmdb-2d","task":"Skeleton Based Action Recognition","dataset":"JHMDB (2D poses only)","model":"DD-Net","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"78.0 (average of 3 split train/test)","Average accuracy of 3 splits":"77.2","No. parameters":"1.82 M"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}