Abstract | ||
---|---|---|
We propose a novel approach to human action recognition, with motion capture data (MoCap), based on grouping sub-body parts. By representing configurations of actions as manifolds, joint positions are mapped on a subspace via principal geodesic analysis. The reduced space is still highly informative and allows for classification based on a non-parametric Bayesian approach, generating behaviors for each sub-body part. Having partitioned the set of joints, poses relative to a sub-body part are exchangeable, given a specified prior and can elicit, in principle, infinite behaviors. The generation of these behaviors is specified by a Dirichlet process mixture. We show with several experiments that the recognition gives very promising results, outperforming methods requiring temporal alignment. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICCV.2015.523 | ICCV |
Field | DocType | ISSN |
Computer vision,Motion capture,Pattern recognition,Subspace topology,Computer science,Inference,Action recognition,Principal geodesic analysis,Nonparametric statistics,Artificial intelligence,Manifold,Bayesian probability | Conference | 1550-5499 |
Citations | PageRank | References |
1 | 0.35 | 11 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fabrizio Natola | 1 | 1 | 0.35 |
Valsamis Ntouskos | 2 | 12 | 5.42 |
Marta Sanzari | 3 | 1 | 0.35 |
Fiora Pirri | 4 | 684 | 94.09 |