{"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/pcnet-a-human-pose-compensation-network-based","title":"PCNet: a human pose compensation network based on incremental learning for sports actions estimation","arxiv_id":null,"date":"2024-11-11","proceeding":"Complex & Intelligent Systems 2024 11","authors":["Jia-Hong Jiang","Nan Xia"],"abstract":"Human pose estimation has a wide range of applications. Existing methods perform well in conventional domains, but there\r\nare certain defects when they are applied to sports activities. The first is lack of estimation of the extremity posture, making\r\nit impossible to comprehensively evaluate the movement posture; the second is insufficient occlusion handling. Therefore,\r\nwe propose a human pose compensation network based on incremental learning, which obtains shared weights to extract\r\ndetailed features under the premise of limited extremity training data. We propose a higher-order feature compensator (HOF\u0002compensator) to embed the attributes of the extremity into the torso and limbs topology structure, building a complete higher\u0002order feature. In addition, to improve the occlusion handling performance, we propose an occlusion feature enhancement\r\nattention mechanism (OFE-attention) that can identify occluded keypoints and enhance attention to occlusion areas. We\r\ndesign comparative experiments on three public datasets and a self-built sports dataset, achieving the highest mean accuracy\r\namong all comparative methods. In addition, we design a series of ablation analysis and visualization displays to verify that\r\nour method performs best in sports pose estimation","url_abs":"https://link.springer.com/content/pdf/10.1007/s40747-024-01647-1.pdf","url_pdf":"https://link.springer.com/content/pdf/10.1007/s40747-024-01647-1.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":[],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"occlusion-handling","task_name":"Occlusion Handling"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-coco-wholebody-1","task":"2D Human Pose Estimation","dataset":"COCO-WholeBody","model":"PCNet","rank_in_archive_order":2,"of":15,"metrics":{"WB":"66.4","body":"76.9","face":"89.7","foot":"65.3","hand":"65.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}