We present a method for unsupervised learning of event classes from videos in which multiple actions might occur simultaneously. It is assumed that all such activities are produce...
Muralikrishna Sridhar, Anthony G. Cohn, David C. H...
Although many powerful AI and machine learning techniques exist, it remains difficult to quickly create AI for embodied virtual agents that produces visually lifelike behavior. T...
Jonathan Dinerstein, Parris K. Egbert, Dan Ventura
A better understanding of “human error” is needed to help overcome problems of people assuming they are to blame for their inability to use poorly designed technology. In order...
: In multimodal image-guided surgery, surgeons have to manage large amounts of information (i.e. images) to plan and perform the surgical procedure. To facilitate management we att...
Pierre Jannin, M. Raimbault, Xavier Morandi, E. Se...
Current image retrieval systems do not provide users with adequate interfaces able to reduce the semantic gap existing between the high-level semantics of images (as perceived by t...