Title :
Multi-source Deep Learning for Human Pose Estimation
Author :
Wanli Ouyang ; Xiao Chu ; Xiaogang Wang
Author_Institution :
Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Abstract :
Visual appearance score, appearance mixture type and deformation are three important information sources for human pose estimation. This paper proposes to build a multi-source deep model in order to extract non-linear representation from these different aspects of information sources. With the deep model, the global, high-order human body articulation patterns in these information sources are extracted for pose estimation. The task for estimating body locations and the task for human detection are jointly learned using a unified deep model. The proposed approach can be viewed as a post-processing of pose estimation results and can flexibly integrate with existing methods by taking their information sources as input. By extracting the non-linear representation from multiple information sources, the deep model outperforms state-of-the-art by up to 8.6 percent on three public benchmark datasets.
Keywords :
feature extraction; image representation; learning (artificial intelligence); pose estimation; appearance mixture type; body location estimation; deformation; high-order human body articulation patterns; human detection; human pose estimation; multiple information sources; multisource deep learning; multisource deep model; nonlinear representation extraction; public benchmark datasets; unified deep model; visual appearance score; Abstracts; Computational modeling; Deformable models; Estimation; Head; Torso; Training; Deep learning; deep blief net; deep model; neural net work; pose estimation;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
DOI :
10.1109/CVPR.2014.299