{"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/human-pose-estimation-using-deep-consensus","title":"Human Pose Estimation using Deep Consensus Voting","arxiv_id":"1603.08212","date":"2016-03-27","proceeding":null,"authors":["Ita Lifshitz","Ethan Fetaya","Shimon Ullman"],"abstract":"In this paper we consider the problem of human pose estimation from a single\nstill image. We propose a novel approach where each location in the image votes\nfor the position of each keypoint using a convolutional neural net. The voting\nscheme allows us to utilize information from the whole image, rather than rely\non a sparse set of keypoint locations. Using dense, multi-target votes, not\nonly produces good keypoint predictions, but also enables us to compute\nimage-dependent joint keypoint probabilities by looking at consensus voting.\nThis differs from most previous methods where joint probabilities are learned\nfrom relative keypoint locations and are independent of the image. We finally\ncombine the keypoints votes and joint probabilities in order to identify the\noptimal pose configuration. We show our competitive performance on the MPII\nHuman Pose and Leeds Sports Pose datasets.","url_abs":"http://arxiv.org/abs/1603.08212v1","url_pdf":"http://arxiv.org/pdf/1603.08212v1.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":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":null,"task_name":"Position"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"Lifshitz et al.","rank_in_archive_order":37,"of":46,"metrics":{"PCKh-0.5":"85.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.08212","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}