{"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/zoomnas-searching-for-whole-body-human-pose","title":"ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild","arxiv_id":"2208.11547","date":"2022-08-23","proceeding":null,"authors":["Lumin Xu","Sheng Jin","Wentao Liu","Chen Qian","Wanli Ouyang","Ping Luo","Xiaogang Wang"],"abstract":"This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts. We further propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. ZoomNAS jointly searches the model architecture and the connections between different sub-modules, and automatically allocates computational complexity for searched sub-modules. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0, which annotates 133 keypoints for in-the-wild images. Extensive experiments demonstrate the effectiveness of ZoomNAS and the significance of COCO-WholeBody V1.0.","url_abs":"https://arxiv.org/abs/2208.11547v1","url_pdf":"https://arxiv.org/pdf/2208.11547v1.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":"zoomnas-searching-for-whole-body-human-pose","repo_url":"https://github.com/jin-s13/COCO-WholeBody","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"zoomnet","method_name":"ZoomNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-coco-wholebody-1","task":"2D Human Pose Estimation","dataset":"COCO-WholeBody","model":"ZoomNAS (V1.0 data)","rank_in_archive_order":3,"of":15,"metrics":{"WB":"65.4","body":"74.0","face":"88.9","foot":"61.7","hand":"62.5"},"uses_additional_data":false},{"leaderboard":"/sota/2d-human-pose-estimation-on-coco-wholebody-1","task":"2D Human Pose Estimation","dataset":"COCO-WholeBody","model":"ZoomNet (V1.0 data)","rank_in_archive_order":6,"of":15,"metrics":{"WB":"63.0","body":"74.5","face":"88.0","foot":"60.9","hand":"57.9"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2208.11547","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}