{"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/tokenpose-learning-keypoint-tokens-for-human","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","arxiv_id":"2104.03516","date":"2021-04-08","proceeding":"ICCV 2021 10","authors":["YanJie Li","Shoukui Zhang","Zhicheng Wang","Sen yang","Wankou Yang","Shu-Tao Xia","Erjin Zhou"],"abstract":"Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints. In this paper, we propose a novel approach based on Token representation for human Pose estimation~(TokenPose). In detail, each keypoint is explicitly embedded as a token to simultaneously learn constraint relationships and appearance cues from images. Extensive experiments show that the small and large TokenPose models are on par with state-of-the-art CNN-based counterparts while being more lightweight. Specifically, our TokenPose-S and TokenPose-L achieve $72.5$ AP and $75.8$ AP on COCO validation dataset respectively, with significant reduction in parameters ($\\downarrow80.6\\%$; $\\downarrow$ $56.8\\%$) and GFLOPs ($\\downarrow$ $75.3\\%$; $\\downarrow$ $24.7\\%$). Code is publicly available.","url_abs":"https://arxiv.org/abs/2104.03516v3","url_pdf":"https://arxiv.org/pdf/2104.03516v3.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":"tokenpose-learning-keypoint-tokens-for-human","repo_url":"https://github.com/leeyegy/TokenPose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.03516","atlas_url":"https://app.syntology.ai/?focus=2104.03516","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}