We investigate to what extent `bag of visual words' models can be used to distinguish categories which have significant visual similarity. To this end we develop and optimize...
We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel pr...
Linear and affine subspaces are commonly used to describe appearance of objects under different lighting, viewpoint, articulation, and identity. A natural problem arising from the...
Automatic detection of dynamic events in video sequences has a variety of applications including visual surveillance and monitoring, video highlight extraction, intelligent transp...
In this paper, we propose a robust multi-layer background subtraction technique which takes advantages of local texture features represented by local binary patterns (LBP) and pho...