Papers › HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

10 Mar 2023CVPR 2023 1arXiv:2303.05675archive 2025-07-28

Shixiang Tang, Cheng Chen, Qingsong Xie, Meilin Chen, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang

Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the metaverse. It is desirable to have a general pretrain model for versatile human-centric downstream tasks. This paper forges ahead along this path from the aspects of both benchmark and pretraining methods. Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting. To learn both coarse-grained and fine-grained knowledge in human bodies, we further propose a \textbf{P}rojector \textbf{A}ssis\textbf{T}ed \textbf{H}ierarchical pretraining method (\textbf{PATH}) to learn diverse knowledge at different granularity levels. Comprehensive evaluations on HumanBench show that our PATH achieves new state-of-the-art results on 17 downstream datasets and on-par results on the other 2 datasets. The code will be publicly at \href{https://github.com/OpenGVLab/HumanBench}{https://github.com/OpenGVLab/HumanBench}.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="2303.05675")

Code

Syntology Ran 15 of 25 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 25 samples from 1 repository, 15 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/humanbench 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

25 samples harvested; 15 ran; 1 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
4ran · our draft was wrong
1ran · fixture could not drive it
9ran
10unverified

Licence: 0 of the 25 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/HumanBench. “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.

NestedTensor OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 39af89396152713c · report
PatchEmbed OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 9af8e85813684a76 · report
autocast OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · our draft was wrong MIT (permissive) · 69b9d45d322d1680 · report
enable_checkpointing OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran MIT (permissive) · 68e7a844f6a217c9 · report
enable_recomputing OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran MIT (permissive) · d32957ea95e1f955 · report
get_2d_sincos_pos_embed OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · honoured contract fingerprinted MIT (permissive) · 0973dbf09d2066c7 · report
get_abs_pos OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · fixture could not drive it MIT (permissive) · 8dc7dc2bedef1191 · report
is_autocast_enabled OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran MIT (permissive) · a88ee7f6d338ad8d · report
is_checkpointing OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran MIT (permissive) · dfb3581e62456ff2 · report
is_recomputing OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran MIT (permissive) · 60a3f862716c1212 · report
pack_kwargs OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran MIT (permissive) · 87cadb13cda1c63e · report
patch_batchnorm OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · our draft was wrong MIT (permissive) · 37dc7bc4f8eea14d · report
split_non_tensors OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · c0b365b386a2ce5a · report
unpack_kwargs OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · c577116b3b35c1c3 · report
unpack_non_tensors OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository ran MIT (permissive) · e9cfd29d0d37ed43 · report
Attention OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · d2b8be1e94eca236 · report
Block OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · 344d0eb15f2cb514 · report
CheckpointFunction OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · 8e99c11a4e7efdd5 · report
ViT OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · c8bcf97bcffa2bfd · report
WindowAttention OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · fc286c766c71de79 · report
_checkpointed_forward OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · 839f42723dc179f9 · report
calc_rel_pos_spatial OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · 37c5cac4e0bae684 · report
checkpoint_wrapper OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · 5de1a5737d6af117 · report
get_rng_state OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · f6675e1e59cce43a · report
set_rng_state OpenGVLab/HumanBench/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py official repository unverified MIT (permissive) · 9deeaa92c6fb18e5 · report

Tasks

AttributeAutonomous DrivingCrowd CountingHuman ParsingPedestrian Attribute RecognitionPedestrian DetectionPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pedestrian Attribute Recognition PA-100K PATH (Partial FT) Accuracy 90.8 #1 of 13 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) PATH (Partial FT) AP 77.1 #7 of 10 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.

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