Multi-person human pose estimation and tracking in the wild is important and challenging. For training a powerful model, large-scale training data are crucial. While there are several datasets for human pose estimation, the best practice for training on multi-dataset has not been investigated. In this paper, we present a simple network called Multi-Domain Pose Network (MDPN) to address this problem. By treating the task as multi-domain learning, our methods can learn a better representation for pose prediction. Together with prediction heads fine-tuning and multi-branch combination, it shows significant improvement over baselines and achieves the best performance on PoseTrack ECCV 2018 Challenge without additional datasets other than MPII and COCO.
@article{arxiv.1810.08338,
title = {Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking},
author = {Hengkai Guo and Tang Tang and Guozhong Luo and Riwei Chen and Yongchen Lu and Linfu Wen},
journal= {arXiv preprint arXiv:1810.08338},
year = {2019}
}
Comments
Extended abstract for the ECCV 2018 PoseTrack Workshop