—CENTRIST (CENsus TRansform hISTogram), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene ...
This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visu...
Howard Zhou, Tucker Hermans, Asmita V. Karandikar,...
In this paper we propose a new method for human action categorization by using an effective combination of a new 3D gradient descriptor with an optic flow descriptor, to represent...
Automatic visual categorization is critically dependent on labeled examples for supervised learning. As an alternative to traditional expert labeling, social-tagged multimedia is ...
This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered...