Abstract | ||
---|---|---|
This paper addresses the problem of human activity recognition in still images. We propose a novel method that focuses on human-object interaction for feature representation of activities on Riemannian manifolds, and exploits underlying Riemannian geometry for classification. The main contributions of the paper include: (a) represent human activity by appearance features from local patches centered at hands containing interacting objects, and by structural features formed from the detected human skeleton containing the head, torso axis and hands; (b) formulate SVM kernel function based on geodesics on Riemannian manifolds under the log-Euclidean metric; (c) apply multi-class SVM classifier on the manifold under the one-against-all strategy. Experiments were conducted on a dataset containing 17196 images in 12 classes of activities from 4 subjects. Test results, evaluations, and comparisons with state-of-the-art methods provide support to the effectiveness of the proposed scheme. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2659021.2659063 | ICDSC |
Keywords | Field | DocType |
algorithms,design,experimentation,riemannian manifold,measurement,symmetric positive definite matrices,human activity recognition,distributed applications,covariance descriptor,scene analysis,performance,support vector machines | Information geometry,Computer vision,Activity recognition,Computer science,Riemannian manifold,Support vector machine,Artificial intelligence,Riemannian geometry,Manifold,Geodesic,Kernel (statistics) | Conference |
Citations | PageRank | References |
0 | 0.34 | 21 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yixiao Yun | 1 | 36 | 5.09 |
Keren Fu | 2 | 295 | 26.25 |
Irene Yu-Hua Gu | 3 | 613 | 35.06 |
Hamid K. Aghajan | 4 | 282 | 35.49 |
Jie Yang | 5 | 282 | 57.59 |