{"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/cascaded-pyramid-network-for-multi-person","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","arxiv_id":"1711.07319","date":"2017-11-20","proceeding":"CVPR 2018 6","authors":["Yilun Chen","Zhicheng Wang","Yuxiang Peng","Zhiqiang Zhang","Gang Yu","Jian Sun"],"abstract":"The topic of multi-person pose estimation has been largely improved recently,\nespecially with the development of convolutional neural network. However, there\nstill exist a lot of challenging cases, such as occluded keypoints, invisible\nkeypoints and complex background, which cannot be well addressed. In this\npaper, we present a novel network structure called Cascaded Pyramid Network\n(CPN) which targets to relieve the problem from these \"hard\" keypoints. More\nspecifically, our algorithm includes two stages: GlobalNet and RefineNet.\nGlobalNet is a feature pyramid network which can successfully localize the\n\"simple\" keypoints like eyes and hands but may fail to precisely recognize the\noccluded or invisible keypoints. Our RefineNet tries explicitly handling the\n\"hard\" keypoints by integrating all levels of feature representations from the\nGlobalNet together with an online hard keypoint mining loss. In general, to\naddress the multi-person pose estimation problem, a top-down pipeline is\nadopted to first generate a set of human bounding boxes based on a detector,\nfollowed by our CPN for keypoint localization in each human bounding box. Based\non the proposed algorithm, we achieve state-of-art results on the COCO keypoint\nbenchmark, with average precision at 73.0 on the COCO test-dev dataset and 72.1\non the COCO test-challenge dataset, which is a 19% relative improvement\ncompared with 60.5 from the COCO 2016 keypoint challenge.Code\n(https://github.com/chenyilun95/tf-cpn.git) and the detection results are\npublicly available for further research.","url_abs":"http://arxiv.org/abs/1711.07319v2","url_pdf":"http://arxiv.org/pdf/1711.07319v2.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":"cascaded-pyramid-network-for-multi-person","repo_url":"https://github.com/chenyilun95/tf-cpn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cascaded-pyramid-network-for-multi-person","repo_url":"https://github.com/Cli98/pytorch-cpn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"cascaded-pyramid-network-for-multi-person","repo_url":"https://github.com/caiyuanhao1998/RSN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cascaded-pyramid-network-for-multi-person","repo_url":"https://github.com/megvii-detection/MSPN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"cascaded-pyramid-network-for-multi-person","repo_url":"https://github.com/tuvovan/CPN_KR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"CPN+","rank_in_archive_order":12,"of":24,"metrics":{"Test AP":"73.0"},"uses_additional_data":false},{"leaderboard":"/sota/keypoint-detection-on-coco-test-challenge","task":"Keypoint Detection","dataset":"COCO test-challenge","model":"CPN+","rank_in_archive_order":4,"of":8,"metrics":{"AP":"72.1","AP50":"90.5","AP75":"78.9","APL":"84.7","AR":"78.7","AR50":"94.7","AR75":"84.8","ARL":"78.1","ARM":"74.3"},"uses_additional_data":false},{"leaderboard":"/sota/keypoint-detection-on-coco-test-dev","task":"Keypoint Detection","dataset":"COCO test-dev","model":"CPN+","rank_in_archive_order":6,"of":16,"metrics":{"AP50":"91.7","AP75":"80.9","APL":"78.1","APM":"69.5","AR":"79.0","AR50":"95.1","AR75":"85.9","ARL":"84.6","ARM":"74.8"},"uses_additional_data":false},{"leaderboard":"/sota/keypoint-detection-on-coco-test-dev","task":"Keypoint Detection","dataset":"COCO test-dev","model":"CPN","rank_in_archive_order":7,"of":16,"metrics":{"AP50":"91.4","AP75":"80.0","APL":"77.2","APM":"68.7","AR":"78.5","AR50":"95.1","AR75":"85.3","ARL":"84.3","ARM":"74.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-coco","task":"Multi-Person Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"CPN+","rank_in_archive_order":4,"of":15,"metrics":{"AP":"0.730"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"CPN+ [6, 9]","rank_in_archive_order":26,"of":47,"metrics":{"AP":"73.0","AP50":"91.7","AP75":"80.9","APL":"78.1","AR":"79.0"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"CPN","rank_in_archive_order":29,"of":47,"metrics":{"AP":"72.1","AP50":"91.4","AP75":"80.0","APL":"77.2","AR":"78.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.07319","atlas_url":"https://app.syntology.ai/?focus=1711.07319","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1711.07319"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.07319\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.07319"},"call":"get_concepts_for_paper(arxiv_id=\"1711.07319\")"}],"by_repo":[{"repo":"chenyilun95/tf-cpn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2003.04030"],"harvested_for_calls":[{"arxiv_id":"2003.04030","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.04030"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.04030\")"}]},{"repo":"Cli98/pytorch-cpn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"caiyuanhao1998/RSN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2003.04030"],"harvested_for_calls":[{"arxiv_id":"2003.04030","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.04030"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.04030\")"}]},{"repo":"megvii-detection/MSPN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tuvovan/CPN_KR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9fd2d942c190244ebb6ce8949dca9cfe77f273c12a7cb88087662fc33fadf21b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}