Sciweavers

ICASSP
2011
IEEE

Hierarchical Latent Dirichlet Allocation models for realistic action recognition

13 years 4 months ago
Hierarchical Latent Dirichlet Allocation models for realistic action recognition
It has always been very difficult to recognize realistic actions from unconstrained videos because there are tremendous variations from camera motion, background clutter, object appearance and so on. In this paper, a SingleFeature Hierarchical Latent Dirichlet Allocation model called SF-HLDA by extending Latent Dirichlet Allocation to the hierarchical one is first proposed for realistic action recognition. And then, by extending SF-HLDA, we present another model called Multi-Feature Hierarchical Latent Dirichlet Allocation model MF-HLDA which can effectively fuse several different features into one model for recognizing the realistic actions. Experiments demonstrate the effectiveness of our proposed models.
Heping Li, Jie Liu, Shuwu Zhang
Added 21 Aug 2011
Updated 21 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors Heping Li, Jie Liu, Shuwu Zhang
Comments (0)