{"url":"/sota/person-re-identification-on-occluded-dukemtmc","task":{"name":"Person Re-Identification","url":"/task/person-re-identification","note":null},"dataset":{"name":"Occluded-DukeMTMC","url":"/dataset/occluded-dukemtmc"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Person Re-Identification** is a computer vision task in which the goal is to match a person's identity across different cameras or locations in a video or image sequence. It involves detecting and tracking a person and then using features such as appearance, body shape, and clothing to match their identity in different frames. The goal is to associate the same person across multiple non-overlapping camera views in a robust and efficient manner.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":[" Rank-1","mAP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{" Rank-1":null,"mAP":"higher"}},"counts":{"rows":32,"rows_with_code":21,"rows_with_paper_page":32,"rows_dated":32,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"KPR + SOLIDER","metrics":{" Rank-1":"84.31","mAP":"75.11"},"uses_additional_data":false,"paper_date":"2024-07-25","paper":"/paper/keypoint-promptable-re-identification","paper_url":"https://arxiv.org/abs/2407.18112v1","paper_title":"Keypoint Promptable Re-Identification","code":"https://github.com/vlsomers/bpbreid","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"KPR","metrics":{" Rank-1":"79.83","mAP":"67.13"},"uses_additional_data":false,"paper_date":"2024-07-25","paper":"/paper/keypoint-promptable-re-identification","paper_url":"https://arxiv.org/abs/2407.18112v1","paper_title":"Keypoint Promptable Re-Identification","code":"https://github.com/vlsomers/bpbreid","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"PersonViT","metrics":{" Rank-1":"79.8","mAP":"72.2"},"uses_additional_data":false,"paper_date":"2024-08-10","paper":"/paper/personvit-large-scale-self-supervised-vision","paper_url":"https://arxiv.org/abs/2408.05398v2","paper_title":"PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification","code":"https://github.com/hustvl/personvit","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"DROP","metrics":{" Rank-1":"76.8","mAP":"63.3"},"uses_additional_data":false,"paper_date":"2024-01-31","paper":"/paper/drop-decouple-re-identification-and-human","paper_url":"https://arxiv.org/abs/2401.18032v1","paper_title":"DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification","code":"https://github.com/shuguang-52/drop","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"BPBreID","metrics":{" Rank-1":"75.1","mAP":"62.5"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/body-part-based-representation-learning-for","paper_url":"https://arxiv.org/abs/2211.03679v1","paper_title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","code":"https://github.com/vlsomers/bpbreid","n_code_links":3,"syntology":null},{"rank_in_archive_order":6,"model":"DDRN","metrics":{" Rank-1":"71.3","mAP":"62.4"},"uses_additional_data":false,"paper_date":"2024-10-09","paper":"/paper/ddrn-a-data-distribution-reconstruction","paper_url":"https://arxiv.org/abs/2410.06600v1","paper_title":"DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"SOLIDER","metrics":{" Rank-1":"71.2","mAP":"61.9"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/beyond-appearance-a-semantic-controllable","paper_url":"https://arxiv.org/abs/2303.17602v1","paper_title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"DiP (without RK)","metrics":{" Rank-1":"71.1","mAP":"63.1"},"uses_additional_data":false,"paper_date":"2022-12-24","paper":"/paper/dip-learning-discriminative-implicit-parts","paper_url":"https://arxiv.org/abs/2212.13906v2","paper_title":"DiP: Learning Discriminative Implicit Parts for Person Re-Identification","code":"https://github.com/siyuch-fdu/DiP","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"HCGA","metrics":{" Rank-1":"70.1","mAP":"57.5"},"uses_additional_data":false,"paper_date":"2022-12-20","paper":"/paper/human-co-parsing-guided-alignment-for","paper_url":"https://shuguang-52.github.io/hcga/","paper_title":"Human Co-Parsing Guided Alignment for Occluded Person Re-identification","code":"https://github.com/Vill-Lab/2022-TIP-HCGA","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"DPEFormer","metrics":{" Rank-1":"69.9","mAP":"58.9"},"uses_additional_data":false,"paper_date":"2024-02-16","paper":"/paper/dynamic-patch-aware-enrichment-transformer","paper_url":"https://arxiv.org/abs/2402.10435v1","paper_title":"Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"PFD","metrics":{" Rank-1":"69.5","mAP":"61.8"},"uses_additional_data":false,"paper_date":"2021-12-05","paper":"/paper/pose-guided-feature-disentangling-for","paper_url":"https://arxiv.org/abs/2112.02466v2","paper_title":"Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer","code":"https://github.com/WangTaoAs/PFD_Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"SSGR","metrics":{" Rank-1":"69.0","mAP":"57.2"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/occluded-person-re-identification-with-single","paper_url":"http://openaccess.thecvf.com//content/ICCV2021/html/Yan_Occluded_Person_Re-Identification_With_Single-Scale_Global_Representations_ICCV_2021_paper.html","paper_title":"Occluded Person Re-Identification With Single-Scale Global Representations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"TAT","metrics":{" Rank-1":"68.2","mAP":"60.6"},"uses_additional_data":false,"paper_date":"2022-04-01","paper":"/paper/template-aware-transformer-for-person","paper_url":"https://onlinelibrary.wiley.com/doi/10.1155/2022/8917964","paper_title":"Template-Aware Transformer for Person Reidentification","code":"https://github.com/template-aware/TAT","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"FED","metrics":{" Rank-1":"68.1"},"uses_additional_data":false,"paper_date":"2021-12-16","paper":"/paper/feature-erasing-and-diffusion-network-for","paper_url":"https://arxiv.org/abs/2112.08740v2","paper_title":"Feature Erasing and Diffusion Network for Occluded Person Re-Identification","code":"https://github.com/ZacharyWang-007/FED-Occluded-ReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"CLIP-SCGI","metrics":{" Rank-1":"67.5","mAP":"59.2"},"uses_additional_data":false,"paper_date":"2024-10-12","paper":"/paper/clip-scgi-synthesized-caption-guided","paper_url":"https://arxiv.org/abs/2410.09382v1","paper_title":"CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"TransReID","metrics":{" Rank-1":"66.4","mAP":"59.2"},"uses_additional_data":false,"paper_date":"2021-02-08","paper":"/paper/transreid-transformer-based-object-re","paper_url":"https://arxiv.org/abs/2102.04378v2","paper_title":"TransReID: Transformer-based Object Re-Identification","code":"https://github.com/heshuting555/TransReID","n_code_links":4,"syntology":null},{"rank_in_archive_order":17,"model":"SUReID","metrics":{" Rank-1":"65.8","mAP":"54.9"},"uses_additional_data":false,"paper_date":"2024-01-15","paper":"/paper/a-deep-hierarchical-feature-sparse-framework","paper_url":"https://arxiv.org/abs/2401.07469v1","paper_title":"A Deep Hierarchical Feature Sparse Framework for Occluded Person Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"PAT","metrics":{" Rank-1":"64.5","mAP":"53.6"},"uses_additional_data":false,"paper_date":"2021-06-08","paper":"/paper/diverse-part-discovery-occluded-person-re","paper_url":"https://arxiv.org/abs/2106.04095v1","paper_title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"LDS","metrics":{" Rank-1":"64.3","mAP":"55.7"},"uses_additional_data":false,"paper_date":"2021-11-10","paper":"/paper/learning-to-disentangle-scenes-for-person-re","paper_url":"https://arxiv.org/abs/2111.05476v2","paper_title":"Learning to Disentangle Scenes for Person Re-identification","code":"https://github.com/deropty/LDS","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"PGFL","metrics":{" Rank-1":"63.0","mAP":"54.1"},"uses_additional_data":false,"paper_date":"2021-07-31","paper":"/paper/pose-guided-feature-learning-with-knowledge","paper_url":"https://arxiv.org/abs/2108.00139v2","paper_title":"Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"ISP","metrics":{" Rank-1":"62.8","mAP":"52.3"},"uses_additional_data":false,"paper_date":"2020-07-27","paper":"/paper/identity-guided-human-semantic-parsing-for","paper_url":"https://arxiv.org/abs/2007.13467v1","paper_title":"Identity-Guided Human Semantic Parsing for Person Re-Identification","code":"https://github.com/CASIA-IVA-Lab/ISP-reID","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"OAMN","metrics":{" Rank-1":"62.6","mAP":"46.1"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/occlude-them-all-occlusion-aware-attention","paper_url":"http://openaccess.thecvf.com//content/ICCV2021/html/Chen_Occlude_Them_All_Occlusion-Aware_Attention_Network_for_Occluded_Person_Re-ID_ICCV_2021_paper.html","paper_title":"Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"PartFormer","metrics":{" Rank-1":"62.5","mAP":"70.2"},"uses_additional_data":false,"paper_date":"2024-08-29","paper":"/paper/partformer-awakening-latent-diverse","paper_url":"https://arxiv.org/abs/2408.16684v1","paper_title":"PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"VGTri","metrics":{" Rank-1":"62.2","mAP":"46.3"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/learning-to-know-where-to-see-a-visibility","paper_url":"http://openaccess.thecvf.com//content/ICCV2021/html/Yang_Learning_To_Know_Where_To_See_A_Visibility-Aware_Approach_for_ICCV_2021_paper.html","paper_title":"Learning To Know Where To See: A Visibility-Aware Approach for Occluded Person Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"HG","metrics":{" Rank-1":"61.4","mAP":"50.5"},"uses_additional_data":false,"paper_date":"2021-04-13","paper":"/paper/holistic-guidance-for-occluded-person-re","paper_url":"https://arxiv.org/abs/2104.06524v2","paper_title":"Holistic Guidance for Occluded Person Re-Identification","code":"https://github.com/madhukiranets/holisitcguidanceoccreid2","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"PAFormer","metrics":{" Rank-1":"60.4","mAP":"66.4"},"uses_additional_data":false,"paper_date":"2024-08-12","paper":"/paper/paformer-part-aware-transformer-for-person-re","paper_url":"https://arxiv.org/abs/2408.05918v1","paper_title":"PAFormer: Part Aware Transformer for Person Re-identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"IGOAS","metrics":{" Rank-1":"60.1","mAP":"49.4"},"uses_additional_data":false,"paper_date":"2021-04-06","paper":"/paper/incremental-generative-occlusion-adversarial","paper_url":"https://shuguang-52.github.io/igoas/","paper_title":"Incremental Generative Occlusion Adversarial Suppression Network for Person ReID","code":"https://github.com/Vill-Lab/2021-TIP-IGOAS","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"MHSA-Net","metrics":{" Rank-1":"59.7","mAP":"44.8"},"uses_additional_data":false,"paper_date":"2020-08-10","paper":"/paper/mhsa-net-multi-head-self-attention-network","paper_url":"https://arxiv.org/abs/2008.04015v4","paper_title":"MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification","code":"https://github.com/hongchenphd/MHSA-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"HOReID","metrics":{" Rank-1":"55.1","mAP":"43.8"},"uses_additional_data":false,"paper_date":"2020-03-18","paper":"/paper/high-order-information-matters-learning","paper_url":"https://arxiv.org/abs/2003.08177v4","paper_title":"High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification","code":"https://github.com/wangguanan/light-reid","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":30,"model":"PGFA","metrics":{" Rank-1":"51.4","mAP":"37.3"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/pose-guided-feature-alignment-for-occluded","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Miao_Pose-Guided_Feature_Alignment_for_Occluded_Person_Re-Identification_ICCV_2019_paper.html","paper_title":"Pose-Guided Feature Alignment for Occluded Person Re-Identification","code":"https://github.com/lightas/ICCV19_Pose_Guided_Occluded_Person_ReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"CLIPReID-Baseline+UFFM+AMC","metrics":{"mAP":"61.9"},"uses_additional_data":false,"paper_date":"2024-05-02","paper":"/paper/enhancing-person-re-identification-via","paper_url":"https://arxiv.org/abs/2405.01101v5","paper_title":"Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination","code":"https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"BoT+UFFM+AMC","metrics":{"mAP":"61.0"},"uses_additional_data":false,"paper_date":"2024-05-02","paper":"/paper/enhancing-person-re-identification-via","paper_url":"https://arxiv.org/abs/2405.01101v5","paper_title":"Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination","code":"https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}