{"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/deepercut-a-deeper-stronger-and-faster-multi","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","arxiv_id":"1605.03170","date":"2016-05-10","proceeding":null,"authors":["Eldar Insafutdinov","Leonid Pishchulin","Bjoern Andres","Mykhaylo Andriluka","Bernt Schiele"],"abstract":"The goal of this paper is to advance the state-of-the-art of articulated pose\nestimation in scenes with multiple people. To that end we contribute on three\nfronts. We propose (1) improved body part detectors that generate effective\nbottom-up proposals for body parts; (2) novel image-conditioned pairwise terms\nthat allow to assemble the proposals into a variable number of consistent body\npart configurations; and (3) an incremental optimization strategy that explores\nthe search space more efficiently thus leading both to better performance and\nsignificant speed-up factors. Evaluation is done on two single-person and two\nmulti-person pose estimation benchmarks. The proposed approach significantly\noutperforms best known multi-person pose estimation results while demonstrating\ncompetitive performance on the task of single person pose estimation. Models\nand code available at http://pose.mpi-inf.mpg.de","url_abs":"http://arxiv.org/abs/1605.03170v3","url_pdf":"http://arxiv.org/pdf/1605.03170v3.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":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/Ayaanesmail/Test.-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/PJunhyuk/exercise-pose-analyzer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/PJunhyuk/people-counting-pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/chongchen20/Deeplabcut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/eho-tacc/DeepLabCut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/eldar/deepcut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/eldar/deepcut-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/eldar/pose-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/estelabalboa/Proyecto_Final_Pilates","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/gsoykan/comp541_term_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/gsoykan/deepercut-replication","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/gyaansastra/DeepLab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/janbertelngo/count-people","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/orkqueen/depplabseongil","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/srini2dl/DogPoseEstimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deepercut-a-deeper-stronger-and-faster-multi","repo_url":"https://github.com/yttrilab/b-soid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-mpii-multi-person","task":"Keypoint Detection","dataset":"MPII Multi-Person","model":"DeeperCut","rank_in_archive_order":9,"of":9,"metrics":{"mAP@0.5":"59.4%"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-mpii-multi","task":"Multi-Person Pose Estimation","dataset":"MPII Multi-Person","model":"DeeperCut","rank_in_archive_order":9,"of":9,"metrics":{"AP":"59.4%"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-waf","task":"Multi-Person Pose Estimation","dataset":"WAF","model":"DeeperCut","rank_in_archive_order":1,"of":3,"metrics":{"AOP":"88.1%"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-leeds-sports-poses","task":"Pose Estimation","dataset":"Leeds Sports Poses","model":"ResNet-152 + intermediate supervision","rank_in_archive_order":13,"of":18,"metrics":{"PCK":"90.1%"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"ResNet-152 + intermediate supervision","rank_in_archive_order":33,"of":46,"metrics":{"PCKh-0.5":"88.52"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.03170","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}