Papers › PLIP: Language-Image Pre-training for Person Representation Learning

PLIP: Language-Image Pre-training for Person Representation Learning

15 May 2023arXiv:2305.08386archive 2025-07-28

Jialong Zuo, Jiahao Hong, Feng Zhang, Changqian Yu, Hanyu Zhou, Changxin Gao, Nong Sang, Jingdong Wang

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory performance. The reason is that they neglect critical person-related characteristics, i.e., fine-grained attributes and identities. To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP. Specifically, we elaborately design three pretext tasks: 1) Text-guided Image Colorization, aims to establish the correspondence between the person-related image regions and the fine-grained color-part textual phrases. 2) Image-guided Attributes Prediction, aims to mine fine-grained attribute information of the person body in the image; and 3) Identity-based Vision-Language Contrast, aims to correlate the cross-modal representations at the identity level rather than the instance level. Moreover, to implement our pre-train framework, we construct a large-scale person dataset with image-text pairs named SYNTH-PEDES by automatically generating textual annotations. We pre-train PLIP on SYNTH-PEDES and evaluate our models by spanning downstream person-centric tasks. PLIP not only significantly improves existing methods on all these tasks, but also shows great ability in the zero-shot and domain generalization settings. The code, dataset and weights will be released at https://github.com/Zplusdragon/PLIP

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 9 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zplusdragon/plip officialmentioned in papermentioned on GitHubpytorchMITSyntology: 9 samples, 4 ran (0 instrument-failed) · 5 unverified 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

9 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
5unverified

Licence: 0 of the 9 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 zplusdragon/plip. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zplusdragon/plip official repository 9 samples, 4 ran (0 instrument-failed) · 5 unverified
gradual_warmup Downstreams/CMPM-C/utils.py ran MIT (permissive) · 37854be4ad8fe76e · report fixture: signature epoch:int/0/int, optimizer:SGD/0/?, epochs:int/0/int · returned SGD · level recorded 2026-09-26
image_to_patch utils.py ran fingerprinted MIT (permissive) · 87c0152a55e9d1aa · report fixture: signature image:Tensor/4/float, patch_size:int/0/int · returned Tensor · level recorded 2026-09-26
lr_scheduler in 32 papers utils.py ran MIT (permissive) · a31fc96a7b978b35 · report fixture: signature optimizer:Adam/0/?, args:Args/0/?, loader_length:int/0/int · returned LambdaLR · level recorded 2026-09-26
mask_ratio_scheduler utils.py ran MIT (permissive) · 7e5735c288ba3ced · report fixture: signature current_epoch:int/0/int, total_epochs:int/0/int, lower_ratio:float/0/float, upper_ratio:float/0/float, ratio_type:str/0/str · returned float · level recorded 2026-09-26
Create_model Downstreams/CMPM-C/model.py unverified MIT (permissive) · 0d7629fa4e046920 · report
compute_topk Downstreams/CMPM-C/utils.py unverified MIT (permissive) · 4ccd7de6989659c6 · report
create_optimizer in 37 papers Downstreams/CMPM-C/optimizer.py unverified MIT (permissive) · 57ae9f6a6a29d5b3 · report
get_loader_test Downstreams/CMPM-C/dataloader.py unverified MIT (permissive) · b4ebb1de75f2cf57 · report
test in 377 papers zs_infer.py unverified MIT (permissive) · 2b71a5dd46418465 · report

Tasks

AttributePedestrian Attribute RecognitionPerson Re-IdentificationRepresentation LearningText based Person RetrievalText-based Person Retrieval

Datasets

Introduced by this paper, per the archive.

SYNTH-PEDES

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification DukeMTMC-reID PLIP-RN50-MGN mAP 81.7 #35 of 94 Archive leaderboard report
Person Re-Identification Market-1501 PLIP-RN50-ABDNet mAP 91.2 #127 of 135 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES PLIP-RN50 R@1 64.25 #7 of 12 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES PLIP-RN50 R@10 86.32 #7 of 12 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES PLIP-RN50 R@5 80.88 #7 of 12 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

PLIP

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