</> Code with Papers by Syntology

Datasets › RSTPReid

RSTPReid (Real Scenario Text-based Person Re-identification)

Introduced by Aichun Zhu et al. in DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval12 Sep 2021 archive 2025-07-28

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.

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Text based Person Retrieval RSTPReid MARS R@1 67.55 MARS: Paying more attention to visual attributes for... ergastialex/mars 9 Compare
Text-based Person Retrieval with Noisy Correspondence RSTPReid RDE Rank 1 64.45 Noisy-Correspondence Learning for Text-to-Image Person... QinYang79/RDE 6 Compare

Papers archive 2025-07-28

13 shown of 13 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 45. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
MARS: Paying more attention to visual attributes for text-based person search 1 1 5 Jul 2024 not harvested
From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search 1 1 16 Apr 2024 not harvested
Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval 0 1 4 Dec 2023 not harvested
Noisy-Correspondence Learning for Text-to-Image Person Re-identification 1 2 19 Aug 2023 ran 12 of 14 samples (2 unverified; 14 pointer-only for licence)
An Empirical Study of CLIP for Text-based Person Search 1 1 19 Aug 2023 not harvested
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark 1 1 5 Jun 2023 ran 6 of 12 samples (6 unverified)
RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search 1 1 23 May 2023 ran 3 of 7 samples (4 unverified)
Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval 1 2 22 Mar 2023 ran 5 of 9 samples (4 unverified)
Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval 1 1 10 Oct 2022 not harvested
See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval 1 1 18 Aug 2022 not harvested
DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval 1 1 12 Sep 2021 not harvested
Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification 1 1 27 Jul 2021 not harvested
Learning Transferable Visual Models From Natural Language Supervision 82 1 26 Feb 2021 ran 16 of 20 samples (4 unverified; 16 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Person Re-IdentificationText based Person RetrievalText-based Person Retrieval with Noisy CorrespondencePerson RetrievalCross-Modal Person Re-IdentificationText based Person Search

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

ImagesTexts

Languages archive 2025-07-28

English

Variants archive 2025-07-28

  • RSTPReid

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections