Abstract | ||
---|---|---|
We present a novel feature description algorithm to describe 3D local spatio-temporal features for human action recognition. Our descriptor avoids the singularity and limited discrimination power issues of traditional 3D descriptors by quantizing and describing visual features in the simplex topological vector space. Specifically, given a feature's support region containing a set of 3D visual cues, we decompose the cues' orientation into three angles, transform the decomposed angles into the simplex space, and describe them in such a space. Then, quadrant decomposition is performed to improve discrimination, and a final feature vector is composed from the resulting histograms. We develop intuitive visualization tools for analyzing feature characteristics in the simplex topological vector space. Experimental results demonstrate that our novel simplex-based orientation decomposition (SOD) descriptor substantially outperforms traditional 3D descriptors for the KTH, UCF Sport, and Hollywood-2 benchmark action datasets. In addition, the results show that our SOD descriptor is a superior individual descriptor for action recognition. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/CVPR.2014.265 | CVPR |
Keywords | Field | DocType |
simplex-based 3d spatio-temporal feature description algorithm,kth,feature vector,intuitive visualization tools,topological vector space,spatio-temporal features,quadrant decomposition,simplex,human action recognition,image recognition,cue orientation,feature extraction,data visualisation,visual features,feature characteristic analysis,feature description,feature description, spatio-temporal features, action recognition, simplex,sod descriptor,action recognition,feature support region,3d visual cues,ucf sport,hollywood-2 benchmark action datasets,simplex-based orientation decomposition,vectors,indexes,visualization,histograms | Sensory cue,Computer vision,Histogram,Feature vector,Pattern recognition,Feature (computer vision),Computer science,Visualization,Topological vector space,Simplex,Feature (machine learning),Artificial intelligence | Conference |
ISSN | Citations | PageRank |
1063-6919 | 16 | 0.63 |
References | Authors | |
21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hao Zhang | 1 | 189 | 23.73 |
Wenjun Zhou | 2 | 207 | 22.34 |
Christopher Reardon | 3 | 73 | 9.46 |
Lynne E. Parker | 4 | 1233 | 132.54 |