@inproceedings{874f8ededd8a4e029374c6f0064c5e90,
title = "PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation",
abstract = "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, e.g. 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 key-point 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.",
keywords = "Training, Hands, Shape, Animals, Pose estimation, Prototypes, Predictive models, Skeleton, Pattern recognition, Standards",
author = "Uyoung Jeong and Jonathan Freer and Seungryul Baek and Chang, \{Hyung Jin\} and Kim, \{Kwang In\}",
year = "2025",
month = aug,
day = "13",
doi = "10.1109/CVPR52734.2025.01146",
language = "English",
isbn = "9798331543655 (PoD)",
series = "IEEE Conference on Computer Vision and Pattern Recognition",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
pages = "12278--12288",
booktitle = "2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
note = "2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025 ; Conference date: 11-06-2025 Through 15-06-2025",
url = "https://cvpr.thecvf.com/virtual/2025/index.html",
}