{"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/beyond-part-models-person-retrieval-with","title":"Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)","arxiv_id":"1711.09349","date":"2017-11-26","proceeding":"ECCV 2018 9","authors":["Yifan Sun","Liang Zheng","Yi Yang","Qi Tian","Shengjin Wang"],"abstract":"Employing part-level features for pedestrian image description offers\nfine-grained information and has been verified as beneficial for person\nretrieval in very recent literature. A prerequisite of part discovery is that\neach part should be well located. Instead of using external cues, e.g., pose\nestimation, to directly locate parts, this paper lays emphasis on the content\nconsistency within each part.\n  Specifically, we target at learning discriminative part-informed features for\nperson retrieval and make two contributions. (i) A network named Part-based\nConvolutional Baseline (PCB). Given an image input, it outputs a convolutional\ndescriptor consisting of several part-level features. With a uniform partition\nstrategy, PCB achieves competitive results with the state-of-the-art methods,\nproving itself as a strong convolutional baseline for person retrieval.\n  (ii) A refined part pooling (RPP) method. Uniform partition inevitably incurs\noutliers in each part, which are in fact more similar to other parts. RPP\nre-assigns these outliers to the parts they are closest to, resulting in\nrefined parts with enhanced within-part consistency. Experiment confirms that\nRPP allows PCB to gain another round of performance boost. For instance, on the\nMarket-1501 dataset, we achieve (77.4+4.2)% mAP and (92.3+1.5)% rank-1\naccuracy, surpassing the state of the art by a large margin.","url_abs":"http://arxiv.org/abs/1711.09349v3","url_pdf":"http://arxiv.org/pdf/1711.09349v3.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":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/AndlollipopFU/PCB","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/Calylyli/PCB_RPP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/Demonhesusheng/Reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/GuHongyang/Person-ReID-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/HoganZhang/Person_reID_baseline_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/NIRVANALAN/reid_baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/Proxim123/person-reID-No1-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/SurajDonthi/Clean-ST-ReID-Multi-Target-Multi-Camera-Tracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/SurajDonthi/Multi-Camera-Person-Re-Identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/SurajDonthi/Multi-Target-Multi-Camera-Tracking-ST-ReID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/SurajDonthi/Multi-Target-Multi-Camera-Tracking-ST-ReID-Clean-Code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/huanghoujing/beyond-part-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/huanghoujing/person-reid-triplet-loss-baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/ivychill/reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/jiangsikai/Person_reID_baseline_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/lsh110600/person_re_id","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/syfafterzy/PCB_RPP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/syfafterzy/pcb_rpp_for_reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/taroogura/Person_reID_baseline_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/wxb589/Person_reID_baseline_pytorch-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/xuxu116/pytorch-reid-lite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/pcb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/pcb_rpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/MS-Mind/MS-Code-06/tree/main/pcb_rpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/Mind23-2/MindCode-5/tree/main/pcb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/Mind23-2/MindCode-5/tree/main/pcb_rpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/pcb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/pcb_rpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"beyond-part-models-person-retrieval-with","repo_url":"https://github.com/code-implementation1/Code6/tree/main/pcb_rpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"Image Description"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"person-retrieval","task_name":"Person Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"pcb","method_name":"PCB"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pcb","name":"PCB","full_name":"Part-based Convolutional Baseline"}],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"PCB (RPP)","rank_in_archive_order":65,"of":94,"metrics":{"Rank-1":"83.3","mAP":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"PCB (UP)","rank_in_archive_order":70,"of":94,"metrics":{"Rank-1":"81.8","mAP":"66.1"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"PCB + RPP","rank_in_archive_order":82,"of":135,"metrics":{"Rank-1":"93.8","mAP":"81.6"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"PCB","rank_in_archive_order":89,"of":135,"metrics":{"Rank-1":"92.3","mAP":"77.4"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501-c","task":"Person Re-Identification","dataset":"Market-1501-C","model":"PCB","rank_in_archive_order":6,"of":22,"metrics":{" Rank-1":"34.93"," mAP":"12.72"," mINP":"0.41"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-uav-human","task":"Person Re-Identification","dataset":"UAV-Human","model":"PCB","rank_in_archive_order":3,"of":4,"metrics":{" Rank-1":"62.19"," Rank-5":"83.90","mAP":"61.05"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.09349","atlas_url":"https://app.syntology.ai/?focus=1711.09349","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":"1711.09349"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.09349\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.09349"},"call":"get_concepts_for_paper(arxiv_id=\"1711.09349\")"}],"by_repo":[{"repo":"AndlollipopFU/PCB","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Calylyli/PCB_RPP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Demonhesusheng/Reid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"GuHongyang/Person-ReID-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"HoganZhang/Person_reID_baseline_pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"NIRVANALAN/reid_baseline","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Proxim123/person-reID-No1-","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1904.07223"],"harvested_for_calls":[{"arxiv_id":"1904.07223","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.07223"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.07223\")"}]},{"repo":"SurajDonthi/Clean-ST-ReID-Multi-Target-Multi-Camera-Tracking","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SurajDonthi/Multi-Camera-Person-Re-Identification","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.03282"],"harvested_for_calls":[{"arxiv_id":"1812.03282","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.03282"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.03282\")"}]},{"repo":"SurajDonthi/Multi-Target-Multi-Camera-Tracking-ST-ReID","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SurajDonthi/Multi-Target-Multi-Camera-Tracking-ST-ReID-Clean-Code","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"huanghoujing/beyond-part-models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"huanghoujing/person-reid-triplet-loss-baseline","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ivychill/reid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1904.07223"],"harvested_for_calls":[{"arxiv_id":"1904.07223","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.07223"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.07223\")"}]},{"repo":"jiangsikai/Person_reID_baseline_pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1904.07223"],"harvested_for_calls":[{"arxiv_id":"1904.07223","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.07223"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.07223\")"}]},{"repo":"lsh110600/person_re_id","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1904.07223"],"harvested_for_calls":[{"arxiv_id":"1904.07223","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.07223"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.07223\")"}]},{"repo":"syfafterzy/PCB_RPP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"syfafterzy/pcb_rpp_for_reid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"taroogura/Person_reID_baseline_pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1904.07223"],"harvested_for_calls":[{"arxiv_id":"1904.07223","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.07223"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.07223\")"}]},{"repo":"wxb589/Person_reID_baseline_pytorch-master","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xuxu116/pytorch-reid-lite","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-215","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MS-Mind/MS-Code-06","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Mind23-2/MindCode-5","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-paper-code-2/code2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"code-implementation1/Code6","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":"71d49ba4ac8e539df8336b62b3266c62ef14acc9a76636f5ce36e5b2ff31c0e3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}