Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking

Hengkai Guo, Tang Tang, Guozhong Luo, Riwei Chen, Yongchen Lu, Linfu Wen; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

Abstract


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 MultiDomain 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Guo_2018_ECCV_Workshops,
author = {Guo, Hengkai and Tang, Tang and Luo, Guozhong and Chen, Riwei and Lu, Yongchen and Wen, Linfu},
title = {Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}