Sciweavers

Share
CVPR
2008
IEEE

Discriminative learning of visual words for 3D human pose estimation

9 years 9 months ago
Discriminative learning of visual words for 3D human pose estimation
This paper addresses the problem of recovering 3D human pose from a single monocular image, using a discriminative bag-of-words approach. In previous work, the visual words are learned by unsupervised clustering algorithms. They capture the most common patterns and are good features for coarse-grain recognition tasks like object classification. But for those tasks which deal with subtle differences such as pose estimation, such representation may lack the needed discriminative power. In this paper, we propose to jointly learn the visual words and the pose regressors in a supervised manner. More specifically, we learn an individual distance metric for each visual word to optimize the pose estimation performance. The learned metrics rescale the visual words to suppress unimportant dimensions such as those corresponding to background. Another contribution is that we design an Appearance and Position Context (APC) local descriptor that achieves both selectivity and invariance while requir...
Huazhong Ning, Wei Xu, Yihong Gong, Thomas S. Huan
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Huazhong Ning, Wei Xu, Yihong Gong, Thomas S. Huang
Comments (0)
books