Eigen-space learning using semi-supervised diffusion maps for human action recognition

Zheng, Feng, Shao, Ling and Song, Zhan (2010) Eigen-space learning using semi-supervised diffusion maps for human action recognition. In: CIVR 2010 - ACM International Conference on Image and Video Retrieval, 5th - 7th July 2010, Xi'an, China.

Full text not available from this repository. (Request a copy)

Abstract

Human actions can be seen as a trajectory in the eigen-space of silhouette of the human body. In this paper, the silhouette is firstly denoted as a vector using R-transform. Then, we exploit semi-supervised diffusion maps (SSDM) for dimensionality reduction and learning the eigen-space of the silhouette. Semi-supervised diffusion maps characterizes the spatiotemporal property of the action, as well as to preserve much of the local geometric structure and label information. We use the K-nearest neighbor classifier for recognizing actions represented as histograms of occurrence of the silhouette in the eigen-space. Experimental results show that the proposed approach performs significantly better than other manifold learning based action recognition techniques.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Action recognition, diffusion maps, label information, manifold learning
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Paul Burns
Date Deposited:	17 Jun 2015 10:43
Last Modified:	13 Oct 2019 00:31
URI:	http://nrl.northumbria.ac.uk/id/eprint/22986

Downloads