{"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/combining-local-appearance-and-holistic-view","title":"Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation","arxiv_id":"1504.07159","date":"2015-04-27","proceeding":"CVPR 2015 6","authors":["Xiaochuan Fan","Kang Zheng","Yuewei Lin","Song Wang"],"abstract":"We propose a new learning-based method for estimating 2D human pose from a\nsingle image, using Dual-Source Deep Convolutional Neural Networks (DS-CNN).\nRecently, many methods have been developed to estimate human pose by using pose\npriors that are estimated from physiologically inspired graphical models or\nlearned from a holistic perspective. In this paper, we propose to integrate\nboth the local (body) part appearance and the holistic view of each local part\nfor more accurate human pose estimation. Specifically, the proposed DS-CNN\ntakes a set of image patches (category-independent object proposals for\ntraining and multi-scale sliding windows for testing) as the input and then\nlearns the appearance of each local part by considering their holistic views in\nthe full body. Using DS-CNN, we achieve both joint detection, which determines\nwhether an image patch contains a body joint, and joint localization, which\nfinds the exact location of the joint in the image patch. Finally, we develop\nan algorithm to combine these joint detection/localization results from all the\nimage patches for estimating the human pose. The experimental results show the\neffectiveness of the proposed method by comparing to the state-of-the-art\nhuman-pose estimation methods based on pose priors that are estimated from\nphysiologically inspired graphical models or learned from a holistic\nperspective.","url_abs":"http://arxiv.org/abs/1504.07159v1","url_pdf":"http://arxiv.org/pdf/1504.07159v1.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":"combining-local-appearance-and-holistic-view","repo_url":"https://github.com/2023-MindSpore-1/ms-code-15/tree/main/dscnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1504.07159","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}