We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Ou...
—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 ...
We propose a first attempt to classify events in static images by integrating scene and object categorizations. We define an event in a static image as a human activity taking pla...
Automatic scene generation using voice and text offers a unique multimedia approach to classic storytelling and human computer interaction with 3D graphics. In this paper, we pre...
Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for opendomain recognition. Our s...
Andrew M. Lovett, Morteza Dehghani, Kenneth D. For...