English

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

Computer Vision and Pattern Recognition 2025-01-28 v1

Abstract

Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-range temporal dependencies and overlook the complementary relationship between temporal pose heatmaps and visual features. To address these limitations, we introduce STDPose, a novel framework that enhances human pose estimation by learning spatiotemporal dynamics in sparsely-labeled videos. STDPose incorporates two key innovations: 1) A novel Dynamic-Aware Mask to capture long-range motion context, allowing for a nuanced understanding of pose changes. 2) A system for encoding and aggregating spatiotemporal representations and motion dynamics to effectively model spatiotemporal relationships, improving the accuracy and robustness of pose estimation. STDPose establishes a new performance benchmark for both video pose propagation (i.e., propagating pose annotations from labeled frames to unlabeled frames) and pose estimation tasks, across three large-scale evaluation datasets. Additionally, utilizing pseudo-labels generated by pose propagation, STDPose achieves competitive performance with only 26.7% labeled data.

Keywords

Cite

@article{arxiv.2501.15073,
  title  = {SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos},
  author = {Yingying Jiao and Zhigang Wang and Sifan Wu and Shaojing Fan and Zhenguang Liu and Zhuoyue Xu and Zheqi Wu},
  journal= {arXiv preprint arXiv:2501.15073},
  year   = {2025}
}
R2 v1 2026-06-28T21:17:18.550Z