DML
DML Sharif University of Technology
Metric learning for graph based semi-supervised human pose estimation
  Nov   2012       Semi-Supervised Human Pose Estimation Graph Based
N. Pourdamghani , H.R. Rabiee and M. Zolfaghari
Discriminative approaches to human pose estimation have became popular in recent years. These approaches face a big challenge: Similar inputs might correspond to very dissimilar poses. This property misleads the mapping functions which rely on the Euclidean distances in the input space. In this paper, we use the distances between the labels of the training data to learn a metric and map the input data to a space where this problem is minimized. Our mapping is linear and hence preserves the manifold structure of the input data. We benefit from the unlabeled data to estimate this manifold in the new space as a nearest neighbor graph. We finally utilize Tikhonov regularization to find a smooth estimation of the labels over this manifold. Experimental results show the superiority of the proposed method both in the amount of required training data and the performance of labeling.
Type
Conference
Publisher
IAPR
ISSN
1051-4651
ISBN
978-4-9906441-0-9
Accession
13325292
Location
Tsukuba, Japan