3D R transform on spatio-temporal interest points for action recognition
| dc.contributor.author | Yuan, Chunfeng | en |
| dc.contributor.author | Li, Xi | en |
| dc.contributor.author | Hu, Weiming | en |
| dc.contributor.author | Ling, Haibin | en |
| dc.contributor.author | Maybank, Steve | en |
| dc.contributor.conference | IEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon) | en |
| dc.contributor.conference | CVPR 2013 | en |
| dc.contributor.school | School of Computer Science | en |
| dc.date.issued | 2013 | en |
| dc.description.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. | en |
| dc.description.statementofresponsibility | Chunfeng Yuan, Xi Li, Weiming Hu, Haibin Ling, and Stephen Maybank | en |
| dc.description.uri | http://www.pamitc.org/cvpr13/ | en |
| dc.identifier.citation | Proceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, 23-28 June 2013, Portland, Oregon, USA: pp. 724-730 | en |
| dc.identifier.doi | 10.1109/CVPR.2013.99 | en |
| dc.identifier.isbn | 9780769549897 | en |
| dc.identifier.issn | 1063-6919 | en |
| dc.identifier.uri | http://hdl.handle.net/2440/82695 | |
| dc.language.iso | en | en |
| dc.publisher | IEEE | en |
| dc.rights | © 2013 IEEE | en |
| dc.title | 3D R transform on spatio-temporal interest points for action recognition | en |
| dc.type | Conference paper | en |