Graph Based Semi-Supervised Human Pose Estimation: When The Output Space Comes to Help

TitleGraph Based Semi-Supervised Human Pose Estimation: When The Output Space Comes to Help
Publication TypeJournal Article
Year of Publication2012
AuthorsPourdamghani, N., H. R. Rabiee, F. Faghri, and M. H. Rohban
JournalPattern Recognition Letters
Start Page1529
Date Published09/2012
Keywordsgraph based, Human pose estimation, Manifold Regularization, semi-supervised
AbstractIn this letter, we introduce a semi-supervised manifold regularization framework for human pose estimation. We utilize the unlabeled data to compensate for the complexities in the input space and model the underlying manifold by a nearest neighbor graph. We argue that the optimal graph is a subgraph of the k nearest neighbors (k-NN) graph. Then, we estimate distances in the output space to approximate this subgraph. In addition, we use the underlying manifold of the points in the output space to introduce a novel regularization term which captures the correlation among the output dimensions. The modified graph and the proposed regularization term are utilized for a smooth regression over both the learned input and output manifolds. Experimental results on various human activities demonstrate the superiority of the proposed algorithm compared to the current state of the art methods.
URL<a href="/dmlsite/?q=%3Ca%20href%3D%22/dmlsite/%3Fq%3D%253Ca%2520href%253D%2522/dmlsite/%253Fq%253D%25253Ca%252520href%25253D%252522/dmlsite/%25253Fq%25253D%2525253Ca%25252520href%2525253D%25252522/dmlsite/%2525253Fq%2525253D%252525253Ca%2525252520href%25
DOI<a href=";amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp