{"url":"/sota/nlp-based-person-retrival-on-cuhk-pedes","task":{"name":"Text based Person Retrieval","url":"/task/nlp-based-person-retrival","note":null},"dataset":{"name":"CUHK-PEDES","url":"/dataset/cuhk-pedes"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"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":["R@1","R@5","R@10","mAP","Rank-1","Rank-10","Rank-5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"R@1":null,"R@5":null,"R@10":null,"mAP":"higher","Rank-1":null,"Rank-10":null,"Rank-5":null}},"counts":{"rows":21,"rows_with_code":14,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"MARS","metrics":{"R@1":"77.62","R@10":"94.27","R@5":"90.63","mAP":"71.41"},"uses_additional_data":false,"paper_date":"2024-07-05","paper":"/paper/mars-paying-more-attention-to-visual","paper_url":"https://arxiv.org/abs/2407.04287v1","paper_title":"MARS: Paying more attention to visual attributes for text-based person search","code":"https://github.com/ergastialex/mars","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"APTM","metrics":{"R@1":"76.53","R@10":"94.15","R@5":"90.04","mAP":"66.91"},"uses_additional_data":true,"paper_date":"2023-06-05","paper":"/paper/towards-unified-text-based-person-retrieval-a","paper_url":"https://arxiv.org/abs/2306.02898v4","paper_title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","code":"https://github.com/Shuyu-XJTU/APTM","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":6,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"RaSa","metrics":{"R@1":"76.51","R@10":"94.25","R@5":"90.29","mAP":"69.38"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/rasa-relation-and-sensitivity-aware","paper_url":"https://arxiv.org/abs/2305.13653v1","paper_title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","code":"https://github.com/flame-chasers/rasa","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"WoRA","metrics":{"R@1":"76.38","R@10":"93.49","R@5":"89.72","mAP":"67.22"},"uses_additional_data":true,"paper_date":"2024-04-16","paper":"/paper/from-data-deluge-to-data-curation-a-filtering","paper_url":"https://arxiv.org/abs/2404.10292v3","paper_title":"From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search","code":"https://github.com/JT-Sun/Filtering-WoRA","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"SRCF","metrics":{"R@1":"64.88","R@10":"88.56","R@5":"83.02"},"uses_additional_data":false,"paper_date":"2022-11-04","paper":"/paper/a-simple-and-robust-correlation-filtering","paper_url":"https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136950719.pdf","paper_title":"A Simple and Robust Correlation Filtering Method for Text-based Person Search","code":"https://github.com/Suo-Wei/SRCF","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"LGUR","metrics":{"R@1":"64.21"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"SAF","metrics":{"R@1":"64.13","R@10":"88.4","R@5":"82.62"},"uses_additional_data":false,"paper_date":"2021-12-13","paper":"/paper/learning-semantic-aligned-feature","paper_url":"https://arxiv.org/abs/2112.06714v1","paper_title":"Learning Semantic-Aligned Feature Representation for Text-based Person Search","code":"https://github.com/reallsp/SAF","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"TextReID","metrics":{"R@1":"64.08","R@10":"88.19","R@5":"81.73","mAP":"60.08"},"uses_additional_data":true,"paper_date":"2021-10-20","paper":"/paper/text-based-person-search-with-limited-data","paper_url":"https://arxiv.org/abs/2110.10807v1","paper_title":"Text-Based Person Search with Limited Data","code":"https://github.com/brandonhanx/textreid","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"TIPCB","metrics":{"R@1":"63.63","R@10":"89.01","R@5":"82.82"},"uses_additional_data":false,"paper_date":"2021-05-25","paper":"/paper/tipcb-a-simple-but-effective-part-based","paper_url":"https://arxiv.org/abs/2105.11628v1","paper_title":"TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search","code":"https://github.com/OrangeYHChen/TIPCB","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"AXM-Net","metrics":{"R@1":"61.9","R@10":"85.75","R@5":"79.4","mAP":"57.38"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/axm-net-cross-modal-context-sharing-attention","paper_url":"https://arxiv.org/abs/2101.08238v3","paper_title":"AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"SSAN","metrics":{"R@1":"61.37","R@10":"86.73","R@5":"80.15"},"uses_additional_data":false,"paper_date":"2021-07-27","paper":"/paper/semantically-self-aligned-network-for-text-to","paper_url":"https://arxiv.org/abs/2107.12666v2","paper_title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","code":"https://github.com/zifyloo/SSAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"DSSL","metrics":{"R@1":"59.98","R@10":"87.56","R@5":"80.41"},"uses_additional_data":false,"paper_date":"2021-09-12","paper":"/paper/dssl-deep-surroundings-person-separation","paper_url":"https://arxiv.org/abs/2109.05534v1","paper_title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","code":"https://github.com/njtechcvlab/rstpreid-dataset","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"NAFS","metrics":{"R@1":"59.94","R@10":"86.7","R@5":"79.86"},"uses_additional_data":false,"paper_date":"2021-01-08","paper":"/paper/contextual-non-local-alignment-over-full","paper_url":"https://arxiv.org/abs/2101.03036v1","paper_title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","code":"https://github.com/TencentYoutuResearch/PersonReID-CACENET","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"HGAN","metrics":{"R@1":"59.00","R@10":"86.62","R@5":"79.49"},"uses_additional_data":false,"paper_date":"2020-10-10","paper":"/paper/hierarchical-gumbel-attention-network-for","paper_url":"https://www.researchgate.net/publication/346192190_Hierarchical_Gumbel_Attention_Network_for_Text-based_Person_Search","paper_title":"Hierarchical Gumbel Attention Network for Text-based Person Search","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"CMAAM","metrics":{"R@1":"56.68","R@10":"84.86","R@5":"77.18"},"uses_additional_data":false,"paper_date":"2020-03-14","paper":"/paper/text-based-person-search-via-attribute-aided","paper_url":"https://openaccess.thecvf.com/content_WACV_2020/html/Aggarwal_Text-based_Person_Search_via_Attribute-aided_Matching_WACV_2020_paper.html","paper_title":"Text-based Person Search via Attribute-aided Matching","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"ViTAA","metrics":{"R@1":"55.97","R@10":"83.52","R@5":"75.84"},"uses_additional_data":false,"paper_date":"2020-05-15","paper":"/paper/vitaa-visual-textual-attributes-alignment-in","paper_url":"https://arxiv.org/abs/2005.07327v2","paper_title":"ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language","code":"https://github.com/Jarr0d/ViTAA","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"MIA","metrics":{"R@1":"53.10","R@10":"82.90","R@5":"75.00"},"uses_additional_data":false,"paper_date":"2019-06-23","paper":"/paper/improving-description-based-person-re","paper_url":"https://arxiv.org/abs/1906.09610v1","paper_title":"Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"CMPM+CMPC","metrics":{"R@1":"49.37","R@10":"79.27","R@5":"-"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/deep-cross-modal-projection-learning-for","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Ying_Zhang_Deep_Cross-Modal_Projection_ECCV_2018_paper.html","paper_title":"Deep Cross-Modal Projection Learning for Image-Text Matching","code":"https://github.com/YingZhangDUT/Cross-Modal-Projection-Learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Dual Path","metrics":{"R@1":"44.4","R@10":"75.07","R@5":"66.26"},"uses_additional_data":false,"paper_date":"2017-11-15","paper":"/paper/dual-path-convolutional-image-text-embedding","paper_url":"https://arxiv.org/abs/1711.05535v4","paper_title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","code":"https://github.com/layumi/Image-Text-Embedding","n_code_links":2,"syntology":null},{"rank_in_archive_order":20,"model":"GLA","metrics":{"R@1":"43.58","R@10":"76.26","R@5":"66.93"},"uses_additional_data":false,"paper_date":"2018-08-05","paper":"/paper/improving-deep-visual-representation-for","paper_url":"http://arxiv.org/abs/1808.01571v1","paper_title":"Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"CADA","metrics":{"Rank-1":"78.37","Rank-10":"94.58","Rank-5":"91.57","mAP":"68.87"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/cross-modal-adaptive-dual-association-for","paper_url":"https://arxiv.org/abs/2312.01745v1","paper_title":"Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval","code":null,"n_code_links":0,"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 6,795 of the 9,581 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":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":10,"n_unverified":10,"n_samples":20,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":10,"n_unverified":10,"n_samples":20,"n_pointer_only_licence":0,"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"}}}