Papers › PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation

PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation

23 May 2025CVPR 2025 1arXiv:2505.17475archive 2025-07-28

Uyoung Jeong, Jonathan Freer, Seungryul Baek, Hyung Jin Chang, Kwang In Kim

We study multi-dataset training (MDT) for pose estimation, where skeletal heterogeneity presents a unique challenge that existing methods have yet to address. In traditional domains, \eg regression and classification, MDT typically relies on dataset merging or multi-head supervision. However, the diversity of skeleton types and limited cross-dataset supervision complicate integration in pose estimation. To address these challenges, we introduce PoseBH, a new MDT framework that tackles keypoint heterogeneity and limited supervision through two key techniques. First, we propose nonparametric keypoint prototypes that learn within a unified embedding space, enabling seamless integration across skeleton types. Second, we develop a cross-type self-supervision mechanism that aligns keypoint predictions with keypoint embedding prototypes, providing supervision without relying on teacher-student models or additional augmentations. PoseBH substantially improves generalization across whole-body and animal pose datasets, including COCO-WholeBody, AP-10K, and APT-36K, while preserving performance on standard human pose benchmarks (COCO, MPII, and AIC). Furthermore, our learned keypoint embeddings transfer effectively to hand shape estimation (InterHand2.6M) and human body shape estimation (3DPW). The code for PoseBH is available at: https://github.com/uyoung-jeong/PoseBH.

PaperPDFConference PDFCode

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.

Code

uyoung-jeong/PoseBH 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

Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation COCO test-dev PoseBH-H AP 79.5 #4 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseBH-H AP50 91.9 #4 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseBH-H AP75 85.8 #4 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseBH-H APL 86.5 #4 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseBH-H APM 75.9 #4 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseBH-H AR 84.5 #4 of 47 Archive leaderboard report
Pose Estimation OCHuman PoseBH-H Test AP 87.0 #3 of 19 Archive leaderboard report
Pose Estimation OCHuman PoseBH-H Validation AP 86.0 #3 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