Papers › You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person...

You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

9 Dec 2023arXiv:2312.05525archive 2025-07-28

Sheng Jin, Shuhuai Li, Tong Li, Wentao Liu, Chen Qian, Ping Luo

Human-centric perception (e.g. detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-stage multi-person multi-task human-centric perception (HCP). Our approach centers on learning a unified human query representation, denoted as Human Query, which captures intricate instance-level features for individual persons and disentangles complex multi-person scenarios. Although different HCP tasks have been well-studied individually, single-stage multi-task learning of HCP tasks has not been fully exploited in the literature due to the absence of a comprehensive benchmark dataset. To address this gap, we propose COCO-UniHuman benchmark to enable model development and comprehensive evaluation. Experimental results demonstrate the proposed method's state-of-the-art performance among multi-task HCP models and its competitive performance compared to task-specific HCP models. Moreover, our experiments underscore Human Query's adaptability to new HCP tasks, thus demonstrating its robust generalization capability. Codes and data are available at https://github.com/lishuhuai527/COCO-UniHuman.

PaperPDFCode

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

Code

lishuhuai527/coco-unihuman officialmentioned in papermentioned on GitHubpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeHuman Instance SegmentationMulti-Task LearningPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human Instance Segmentation OCHuman HQNet (ResNet-50) AP 31.1 #3 of 18 Archive leaderboard report
Pose Estimation OCHuman HQNet (ViT-L) Test AP 45.6 #7 of 19 Archive leaderboard report
Pose Estimation OCHuman HQNet (ResNet-50) Test AP 40.0 #11 of 19 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