{"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/perceive-where-to-focus-learning-visibility","title":"Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification","arxiv_id":"1904.00537","date":"2019-04-01","proceeding":"CVPR 2019 6","authors":["Yifan Sun","Qin Xu","Ya-Li Li","Chi Zhang","Yikang Li","Shengjin Wang","Jian Sun"],"abstract":"This paper considers a realistic problem in person re-identification (re-ID)\ntask, i.e., partial re-ID. Under partial re-ID scenario, the images may contain\na partial observation of a pedestrian. If we directly compare a partial\npedestrian image with a holistic one, the extreme spatial misalignment\nsignificantly compromises the discriminative ability of the learned\nrepresentation. We propose a Visibility-aware Part Model (VPM), which learns to\nperceive the visibility of regions through self-supervision. The visibility\nawareness allows VPM to extract region-level features and compare two images\nwith focus on their shared regions (which are visible on both images). VPM\ngains two-fold benefit toward higher accuracy for partial re-ID. On the one\nhand, compared with learning a global feature, VPM learns region-level features\nand benefits from fine-grained information. On the other hand, with visibility\nawareness, VPM is capable to estimate the shared regions between two images and\nthus suppresses the spatial misalignment. Experimental results confirm that our\nmethod significantly improves the learned representation and the achieved\naccuracy is on par with the state of the art.","url_abs":"http://arxiv.org/abs/1904.00537v1","url_pdf":"http://arxiv.org/pdf/1904.00537v1.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":"perceive-where-to-focus-learning-visibility","repo_url":"https://github.com/YifanSun-ReID/VPM-reID","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-market-1501-c","task":"Person Re-Identification","dataset":"Market-1501-C","model":"VPM","rank_in_archive_order":12,"of":22,"metrics":{" Rank-1":"31.17"," mAP":"10.15"," mINP":"0.31"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00537"}},"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/YifanSun-ReID/VPM-reID","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"86c7510a3d312224","entry":"evaluate_all","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/evaluators.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/evaluators.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"86c7510a3d312224"}},{"code_sha256_prefix":"25770f415d336fca","entry":"extract_features","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/evaluators.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/evaluators.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"25770f415d336fca"}},{"code_sha256_prefix":"071c5eaccfef0c9d","entry":"extract_features","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/evaluators_adaptive_part.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/evaluators_adaptive_part.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"071c5eaccfef0c9d"}},{"code_sha256_prefix":"24aef7ffe5dd04cf","entry":"generate_column_labels","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/generate_column_labels.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/generate_column_labels.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"24aef7ffe5dd04cf"}},{"code_sha256_prefix":"48cf1aad1e6a206d","entry":"oim","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/loss/oim.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/loss/oim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"48cf1aad1e6a206d"}},{"code_sha256_prefix":"e6f090a0a1fb4c32","entry":"pairwise_distance","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/evaluators.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/evaluators.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e6f090a0a1fb4c32"}},{"code_sha256_prefix":"b8bc227c6ed07393","entry":"pairwise_distance","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/evaluators_adaptive_part.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/evaluators_adaptive_part.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b8bc227c6ed07393"}},{"code_sha256_prefix":"17d93169d26911cf","entry":"pairwise_distance_partial","repo":"YifanSun-ReID/VPM-reID","repo_kind":"official","path":"reid/evaluators_partial_ilids.py","file_url":"https://github.com/YifanSun-ReID/VPM-reID/blob/HEAD/reid/evaluators_partial_ilids.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"17d93169d26911cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}