We present a discriminative latent topic model for scene recognition. The capacity of our model is originated from the modeling of two types of visual contexts, i.e., the category...
Sounds constantly occur around us, keeping us aware of our surroundings. People who are deaf have difficulty maintaining an awareness of these ambient sounds. We present an invest...
In this paper we introduce a novel approach to share context to enhance the social quality of remote mobile communication. We provide an analysis of how people start a conversation...
— Our long-term objective is to develop robots that engage in natural language-mediated cooperative tasks with humans. To support this goal, we are developing an amodal represent...