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

Autor:	Guo, Hengkai, Tang, Tang, Luo, Guozhong, Chen, Riwei, Lu, Yongchen, Wen, Linfu
Rok vydání:	2018
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
DOI:	10.1007/978-3-030-11012-3_17
Popis:	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. Comment: Extended abstract for the ECCV 2018 PoseTrack Workshop
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1810.08338 Zobrazit plný text záznamu View this record from Arxiv