{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/2003.04030","atlas_url":"https://app.syntology.ai/?focus=2003.04030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.04030"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.04030"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.04030"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.04030\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2003.04030"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2003.04030\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2003.04030"},"call":"get_concepts_for_paper(arxiv_id=\"2003.04030\")"}],"by_repo":[{"repo":"caiyuanhao1998/RSN","kind":"official","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"chenyilun95/tf-cpn","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"HuangJunJie2017/UDP-Pose","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"open-mmlab/mmpose","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.07526"],"harvested_for_calls":[{"arxiv_id":"2312.07526","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.07526"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.07526\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2003.04030.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2003.04030.svg"},"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},"n_samples":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":2,"ran":2,"n_ran_checked":2,"n_instrument":0,"repositories":1},"listed":{"samples":1,"ran":0,"n_ran_checked":0,"n_instrument":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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":2,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"37ff649cdc90971d","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,"signature":"data:dict/0/?","fixture_out_type":"list","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/all-gather","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"37ff649cdc90971d"}},{"code_sha256":"2a3280757ce5a198","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,"signature":"input_dict:dict/0/?, average:bool/0/bool","fixture_out_type":"dict","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/reduce-dict","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2a3280757ce5a198"}},{"code_sha256":"92e487bd163f89e2","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"92e487bd163f89e2"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6f0be45afbdbf52d0bd2652b298c71b8975dce59b5e3a90955d7b1939f61f84b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}