3D R transform on spatio-temporal interest points for action recognition
Date
2013
Authors
Yuan, Chunfeng
Li, Xi
Hu, Weiming
Ling, Haibin
Maybank, Steve
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, 23-28 June 2013, Portland, Oregon, USA: pp. 724-730
Statement of Responsibility
Chunfeng Yuan, Xi Li, Weiming Hu, Haibin Ling, and Stephen Maybank
Conference Name
IEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon)
CVPR 2013
CVPR 2013
Abstract
Spatio-temporal interest points serve as an elementary building block in many modern action recognition algorithms, and most of them exploit the local spatio-temporal volume features using a Bag of Visual Words (BOVW) representation. Such representation, however, ignores potentially valuable information about the global spatio-temporal distribution of interest points. In this paper, we propose a new global feature to capture the detailed geometrical distribution of interest points. It is calculated by using the R transform which is defined as an extended 3D discrete Radon transform, followed by applying a two-directional two-dimensional principal component analysis. Such R feature captures the geometrical information of the interest points and keeps invariant to geometry transformation and robust to noise. In addition, we propose a new fusion strategy to combine the R feature with the BOVW representation for further improving recognition accuracy. We utilize a context-aware fusion method to capture both the pairwise similarities and higher-order contextual interactions of the videos. Experimental results on several publicly available datasets demonstrate the effectiveness of the proposed approach for action recognition.
School/Discipline
School of Computer Science
Dissertation Note
Provenance
Description
Access Status
Rights
© 2013 IEEE