{"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/investigation-of-different-skeleton-features","title":"Investigation of Different Skeleton Features for CNN-based 3D Action Recognition","arxiv_id":"1705.00835","date":"2017-05-02","proceeding":null,"authors":["Zewei Ding","Pichao Wang","Philip O. Ogunbona","Wanqing Li"],"abstract":"Deep learning techniques are being used in skeleton based action recognition\ntasks and outstanding performance has been reported. Compared with RNN based\nmethods which tend to overemphasize temporal information, CNN-based approaches\ncan jointly capture spatio-temporal information from texture color images\nencoded from skeleton sequences. There are several skeleton-based features that\nhave proven effective in RNN-based and handcrafted-feature-based methods.\nHowever, it remains unknown whether they are suitable for CNN-based approaches.\nThis paper proposes to encode five spatial skeleton features into images with\ndifferent encoding methods. In addition, the performance implication of\ndifferent joints used for feature extraction is studied. The proposed method\nachieved state-of-the-art performance on NTU RGB+D dataset for 3D human action\nanalysis. An accuracy of 75.32\\% was achieved in Large Scale 3D Human Activity\nAnalysis Challenge in Depth Videos.","url_abs":"http://arxiv.org/abs/1705.00835v1","url_pdf":"http://arxiv.org/pdf/1705.00835v1.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":"investigation-of-different-skeleton-features","repo_url":"https://github.com/dzwallkilled/IEforAR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-human-action-recognition","task_name":"3D Action Recognition"},{"task_slug":"action-analysis","task_name":"Action Analysis"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"Five Spatial Skeleton Features","rank_in_archive_order":135,"of":135,"metrics":{"Accuracy (CV)":"82.31"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}