{"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/learning-delicate-local-representations-for","title":"Learning Delicate Local Representations for Multi-Person Pose Estimation","arxiv_id":"2003.04030","date":"2020-03-09","proceeding":"ECCV 2020 8","authors":["Yuanhao Cai","Zhicheng Wang","Zhengxiong Luo","Binyi Yin","Angang Du","Haoqian Wang","Xiangyu Zhang","Xinyu Zhou","Erjin Zhou","Jian Sun"],"abstract":"In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN/","url_abs":"https://arxiv.org/abs/2003.04030v3","url_pdf":"https://arxiv.org/pdf/2003.04030v3.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":"learning-delicate-local-representations-for","repo_url":"https://github.com/caiyuanhao1998/RSN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-delicate-local-representations-for","repo_url":"https://github.com/chenyilun95/tf-cpn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-delicate-local-representations-for","repo_url":"https://github.com/HuangJunJie2017/UDP-Pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-delicate-local-representations-for","repo_url":"https://github.com/open-mmlab/mmpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"4xRSN-50(384×288)","rank_in_archive_order":1,"of":24,"metrics":{"Test AP":"78.6"},"uses_additional_data":false},{"leaderboard":"/sota/keypoint-detection-on-coco-test-challenge","task":"Keypoint Detection","dataset":"COCO test-challenge","model":"4×RSN-50","rank_in_archive_order":1,"of":8,"metrics":{"AP":"77.1","AP50":"93.3","AP75":"83.6","APL":"82.6","AR":"82.6","AR50":"96.1","AR75":"88.2","ARL":"88.7","ARM":"78.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-coco","task":"Multi-Person Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"RSN","rank_in_archive_order":1,"of":15,"metrics":{"AP":"0.792"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"4xRSN-50 (ensemble)","rank_in_archive_order":5,"of":47,"metrics":{"AP":"79.2","AP50":"94.4","AP75":"87.1","APL":"76.1","APM":"83.8","AR":"84.1"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"4xRSN-50","rank_in_archive_order":8,"of":47,"metrics":{"AP":"78.6","AP50":"94.3","AP75":"86.6","APL":"75.5","APM":"83.3","AR":"83.8"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"4xRSN-50","rank_in_archive_order":7,"of":46,"metrics":{"PCKh-0.5":"93.0"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii-single-person","task":"Pose Estimation","dataset":"MPII Single Person","model":"4xRSN-50","rank_in_archive_order":1,"of":5,"metrics":{"PCKh@0.5":"93"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.04030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.04030"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenyilun95/tf-cpn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmpose","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HuangJunJie2017/UDP-Pose","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/caiyuanhao1998/RSN","reach":null}],"summary":{"ran_violates":2,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"37ff649cdc90971d","entry":"all_gather","repo":"caiyuanhao1998/RSN","repo_kind":"official","path":"lib/utils/comm.py","file_url":"https://github.com/caiyuanhao1998/RSN/blob/HEAD/lib/utils/comm.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37ff649cdc90971d"}},{"code_sha256_prefix":"2a3280757ce5a198","entry":"reduce_dict","repo":"caiyuanhao1998/RSN","repo_kind":"official","path":"lib/utils/comm.py","file_url":"https://github.com/caiyuanhao1998/RSN/blob/HEAD/lib/utils/comm.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a3280757ce5a198"}},{"code_sha256_prefix":"92e487bd163f89e2","entry":"get_seg","repo":"chenyilun95/tf-cpn","repo_kind":"listed","path":"models/COCO.res101.256x192.CPN/dataset.py","file_url":"https://github.com/chenyilun95/tf-cpn/blob/HEAD/models/COCO.res101.256x192.CPN/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92e487bd163f89e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}