Papers › Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and...

Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark

5 Jun 2023arXiv:2306.02898archive 2025-07-28

Shuyu Yang, Yinan Zhou, Yaxiong Wang, Yujiao Wu, Li Zhu, Zhedong Zheng

In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 times larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.96%, +7.68%, and +16.95% Recall@1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.02898")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Shuyu-XJTU/APTM officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 6 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

4ran · our draft was wrong
1ran · fixture could not drive it
1ran
6unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Shuyu-XJTU/APTM. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

whitespace_tokenize Shuyu-XJTU/APTM/models/tokenization_bert.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · cf9ffa02a42184af · report
window_partition Shuyu-XJTU/APTM/models/swin_transformer.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report
build_mlp Shuyu-XJTU/APTM/models/aptm.py official repository ran · our draft was wrong MIT (permissive) · 51e7514fd736cca3 · report
load_vocab Shuyu-XJTU/APTM/models/tokenization_bert.py official repository ran · our draft was wrong MIT (permissive) · e7fbc7a74a3457c7 · report
top_k_top_p_filtering Shuyu-XJTU/APTM/models/bert.py official repository ran MIT (permissive) · 9e8f81565e828ebf · report
window_reverse Shuyu-XJTU/APTM/models/swin_transformer.py official repository ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report
accs Shuyu-XJTU/APTM/reTools.py official repository unverified MIT (permissive) · d7bf59874fc1bb8f · report
create_optimizer Shuyu-XJTU/APTM/optim.py official repository unverified MIT (permissive) · 0aa5e4369a69b540 · report
create_scheduler Shuyu-XJTU/APTM/scheduler.py official repository unverified MIT (permissive) · 37c7bac7616d388a · report
interpolate_relative_pos_embed Shuyu-XJTU/APTM/models/swin_transformer.py official repository unverified MIT (permissive) · 199b2766250bd139 · report
load_tf_weights_in_bert Shuyu-XJTU/APTM/models/bert.py official repository unverified MIT (permissive) · 26be70dca3249c0b · report
mlm Shuyu-XJTU/APTM/train_tools.py official repository unverified MIT (permissive) · c28a1bc789b78770 · report

Tasks

AttributeImage-text matchingPedestrian Attribute RecognitionPerson RetrievalPrompt LearningRepresentation LearningRetrievalText MatchingText based Person RetrievalText-based Person Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pedestrian Attribute Recognition PA-100K APTM Accuracy 80.17 #7 of 13 Archive leaderboard report
Text based Person Retrieval CUHK-PEDES APTM R@1 76.53 #2 of 21 Archive leaderboard report
Text based Person Retrieval CUHK-PEDES APTM R@10 94.15 #2 of 21 Archive leaderboard report
Text based Person Retrieval CUHK-PEDES APTM R@5 90.04 #2 of 21 Archive leaderboard report
Text based Person Retrieval CUHK-PEDES APTM mAP 66.91 #2 of 21 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES APTM R@1 68.51 #1 of 12 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES APTM mAP 41.22 #1 of 12 Archive leaderboard report
Text based Person Retrieval RSTPReid APTM R@1 67.50 #2 of 9 Archive leaderboard report
Text based Person Retrieval RSTPReid APTM R@10 91.45 #2 of 9 Archive leaderboard report
Text based Person Retrieval RSTPReid APTM R@5 85.70 #2 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

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