Action recognition using Correlogram of Body Poses and spectral regression

Ling Shao, Di Wu, Xiuli Chen

Research output: Contribution to conferencePaper

18 Citations (Scopus)

Abstract

Human action recognition is an important topic in computer vision with its applications in robotics, video surveillance, human-computer interaction, user interface design, and multimedia video retrieval, etc. In this paper, we propose a novel representation for human actions using Correlogram of Body Poses (CBP) which takes advantage of both the probabilistic distribution and the temporal relationship of human poses. To reduce the high dimensionality of the CBP representation, an efficient subspace learning technique called Spectral Regression Discriminant Analysis (SRDA) is explored. Experimental results on the challenging IXMAS dataset show that the proposed algorithm outperforms the state-of-the-art methods on action recognition.
Original languageEnglish
DOIs
Publication statusPublished - Sep 2011
EventICIP 2011 - 18th IEEE International Conference on Image Processing - Brussels, Belgium
Duration: 1 Sep 2011 → …

Conference

ConferenceICIP 2011 - 18th IEEE International Conference on Image Processing
Period1/09/11 → …

Fingerprint

Dive into the research topics of 'Action recognition using Correlogram of Body Poses and spectral regression'. Together they form a unique fingerprint.

Cite this