Papers › UniHCP: A Unified Model for Human-Centric Perceptions

UniHCP: A Unified Model for Human-Centric Perceptions

6 Mar 2023CVPR 2023 1arXiv:2303.02936archive 2025-07-28

Yuanzheng Ci, Yizhou Wang, Meilin Chen, Shixiang Tang, Lei Bai, Feng Zhu, Rui Zhao, Fengwei Yu, Donglian Qi, Wanli Ouyang

Human-centric perceptions (e.g., pose estimation, human parsing, pedestrian detection, person re-identification, etc.) play a key role in industrial applications of visual models. While specific human-centric tasks have their own relevant semantic aspect to focus on, they also share the same underlying semantic structure of the human body. However, few works have attempted to exploit such homogeneity and design a general-propose model for human-centric tasks. In this work, we revisit a broad range of human-centric tasks and unify them in a minimalist manner. We propose UniHCP, a Unified Model for Human-Centric Perceptions, which unifies a wide range of human-centric tasks in a simplified end-to-end manner with the plain vision transformer architecture. With large-scale joint training on 33 human-centric datasets, UniHCP can outperform strong baselines on several in-domain and downstream tasks by direct evaluation. When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e.g., 69.8 mIoU on CIHP for human parsing, 86.18 mA on PA-100K for attribute prediction, 90.3 mAP on Market1501 for ReID, and 85.8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.

PaperPDFConference PDFCodeCode 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="2303.02936")

Code

Syntology Ran 8 of 13 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

opengvlab/unihcp officialmentioned in paperpytorchMIT 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

13 samples harvested; 8 ran; 0 honoured the contract we drafted; 5 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.

8ran
5unverified

Licence: 0 of the 13 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 OpenGVLab/UniHCP. “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.

accuracy OpenGVLab/UniHCP/core/utils.py official repository ran MIT (permissive) · 78d1f9f766be74b7 · report
accuracy_multi OpenGVLab/UniHCP/core/utils.py official repository ran fingerprinted MIT (permissive) · 8a63c5da44344ba6 · report
flat OpenGVLab/UniHCP/core/config.py official repository ran fingerprinted MIT (permissive) · 4570d6d70bccdfb6 · report
init OpenGVLab/UniHCP/core/fp16/amp.py official repository ran MIT (permissive) · eb8a2600afc1de95 · report
param_group_fc OpenGVLab/UniHCP/core/make_param_group.py official repository ran MIT (permissive) · 70165e0988ce9571 · report
param_group_multitask OpenGVLab/UniHCP/core/make_param_group.py official repository ran MIT (permissive) · e4a7663d686ce91a · report
param_group_no_wd OpenGVLab/UniHCP/core/make_param_group.py official repository ran MIT (permissive) · 0540cf098dbc3d42 · report
retry_if_cuda_oom OpenGVLab/UniHCP/core/memory.py official repository ran MIT (permissive) · ff1253be17efe1ae · report
dist_init OpenGVLab/UniHCP/core/distributed_utils.py official repository unverified MIT (permissive) · 82c208a1743fdfc6 · report
float_function OpenGVLab/UniHCP/core/fp16/amp.py official repository unverified MIT (permissive) · f27c7ab614e20039 · report
half_function OpenGVLab/UniHCP/core/fp16/amp.py official repository unverified MIT (permissive) · 6b4eee4b4bb1f238 · report
simple_group_split OpenGVLab/UniHCP/core/distributed_utils.py official repository unverified MIT (permissive) · b1471eccec180d87 · report
specific_group_split OpenGVLab/UniHCP/core/distributed_utils.py official repository unverified MIT (permissive) · 4e36f197c125d4d3 · report

Tasks

2D Pose EstimationAttributeHuman ParsingHuman Part SegmentationObject DetectionPedestrian Attribute RecognitionPedestrian DetectionPerson Re-IdentificationPose EstimationSemantic Segmentationmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Pose Estimation Human3.6M UniHCP (finetune) EPE 6.6 #1 of 1 Archive leaderboard report
Human Part Segmentation ATR UniHCP (FT) pACC 97.74 #1 of 1 Archive leaderboard report
Human Part Segmentation CIHP UniHCP (finetune) Mean IoU 69.8 #3 of 6 Archive leaderboard report
Human Part Segmentation Human3.6M UniHCP (finetune) mIoU 65.95 #3 of 3 Archive leaderboard report
Object Detection CrowdHuman (full body) UniHCP (finetune) AP 92.5 #8 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) UniHCP (finetune) mMR 41.6 #8 of 19 Archive leaderboard report
Pedestrian Attribute Recognition PA-100K UniHCP (finetune) Accuracy 86.18 #6 of 13 Archive leaderboard report
Pedestrian Attribute Recognition PETA UniHCP (FT) Accuracy 88.78% #1 of 6 Archive leaderboard report
Pedestrian Attribute Recognition RAPv2 UniHCP (finetune) Accuracy 82.34 #3 of 4 Archive leaderboard report
Pedestrian Detection Caltech UniHCP (FT) Heavy MR^-2 27.2 #33 of 33 Archive leaderboard report
Person Re-Identification CUHK03 UniHCP (finetune) MAP 83.1 #6 of 19 Archive leaderboard report
Person Re-Identification MSMT17 UniHCP (finetune) mAP 67.3 #20 of 43 Archive leaderboard report
Person Re-Identification Market-1501 UniHCP (finetune) mAP 90.3 #129 of 135 Archive leaderboard report
Person Re-Identification SenseReID UniHCP (DE) Top-1 46 #1 of 1 Archive leaderboard report
Pose Estimation AIC UniHCP (finetune) AP 33.6 #4 of 10 Archive leaderboard report
Pose Estimation MPII Human Pose UniHCP (FT) PCKh-0.5 93.2 #6 of 46 Archive leaderboard report
Pose Estimation MS-COCO UniHCP (finetune) AP 76.5 #1 of 1 Archive leaderboard report
Pose Estimation OCHuman UniHCP (direct eval) Test AP 87.4 #2 of 19 Archive leaderboard report
Semantic Segmentation LIP val UniHCP (finetune) mIoU 63.86% #3 of 13 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

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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