{"url":"/dataset/rstpreid","name":"RSTPReid","full_name":"Real Scenario Text-based Person Re-identification","description_markdown":"RSTPReid contains 20505 images of 4,101 persons from 15 cameras. Each person has 5 corresponding images taken by different cameras with complex both indoor and outdoor scene transformations and backgrounds in various periods of time, which makes RSTPReid much more challenging and more adaptable to real scenarios. Each image is annotated with 2 textual descriptions. For data division, 3701 (index < 18505), 200 (18505 <= index < 19505) and 200 (index >= 19505) identities are utilized for training, validation and testing, respectively (Marked by item 'split' in the JSON file). Each sentence is no shorter than 23 words.","description_withheld":null,"homepage":"https://github.com/NjtechCVLab/RSTPReid-Dataset","introduced_date":"2021-09-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/dssl-deep-surroundings-person-separation","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","first_author":"Aichun Zhu","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Person Re-Identification","url":"/task/person-re-identification","datasets_with_task":"/datasets/task/person-re-identification"},{"name":"Text based Person Retrieval","url":"/task/nlp-based-person-retrival","datasets_with_task":"/datasets/task/nlp-based-person-retrival"},{"name":"Text-based Person Retrieval with Noisy Correspondence","url":"/task/text-based-person-retrieval-with-noisy","datasets_with_task":"/datasets/task/text-based-person-retrieval-with-noisy"},{"name":"Person Retrieval","url":"/task/person-retrieval","datasets_with_task":"/datasets/task/person-retrieval"},{"name":"Cross-Modal Person Re-Identification","url":null,"datasets_with_task":"/datasets/task/cross-modal-person-re-identification"},{"name":"Text based Person Search","url":"/task/text-based-person-search","datasets_with_task":"/datasets/task/text-based-person-search"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RSTPReid"],"data_loaders":[],"num_papers_in_archive":45,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-based-person-retrieval-on-rstpreid-1","task":"Text based Person Retrieval","dataset_variant":"RSTPReid","rows":9,"metrics":["R@1","R@5","R@10","mAP","Rank-1","Rank-10","Rank-5","mINP"],"first_row_in_archive_order":{"model":"MARS","paper":"/paper/mars-paying-more-attention-to-visual","metrics":{"R@1":"67.55","R@10":"91.35","R@5":"86.65","mAP":"52.92"},"code_links":[{"title":"ergastialex/mars","url":"https://github.com/ergastialex/mars"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-based-person-retrieval-with-noisy-2","task":"Text-based Person Retrieval with Noisy Correspondence","dataset_variant":"RSTPReid","rows":6,"metrics":["Rank 1","Rank 10","Rank 5","mAP","mINP"],"first_row_in_archive_order":{"model":"RDE","paper":"/paper/noisy-correspondence-learning-for-text-to","metrics":{"Rank 1":"64.45","Rank 10":"90.00","Rank 5":"83.50","mAP":"49.78","mINP":"27.43"},"code_links":[{"title":"QinYang79/RDE","url":"https://github.com/QinYang79/RDE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mars-paying-more-attention-to-visual","title":"MARS: Paying more attention to visual attributes for text-based person search","date":"2024-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/from-data-deluge-to-data-curation-a-filtering","title":"From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search","date":"2024-04-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cross-modal-adaptive-dual-association-for","title":"Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval","date":"2023-12-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/noisy-correspondence-learning-for-text-to","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","date":"2023-08-19","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":12,"samples_unverified":2,"pointer_only_for_licence":14,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-empirical-study-of-clip-for-text-based","title":"An Empirical Study of CLIP for Text-based Person Search","date":"2023-08-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-unified-text-based-person-retrieval-a","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","date":"2023-06-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":6,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rasa-relation-and-sensitivity-aware","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","date":"2023-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cross-modal-implicit-relation-reasoning-and","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","date":"2023-03-22","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-evidential-learning-with-noisy","title":"Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval","date":"2022-10-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/see-finer-see-more-implicit-modality","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval","date":"2022-08-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dssl-deep-surroundings-person-separation","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","date":"2021-09-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantically-self-aligned-network-for-text-to","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","date":"2021-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","rows_on_this_dataset":1,"code_links":82,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":16,"samples_unverified":4,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":62,"samples_ran":42,"samples_unverified":20,"pointer_only_for_licence":30,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}