This paper proposes a state based approach to gesture learning and recognition. Using spatial clustering and temporal alignment, each gesture is defined to be an ordered sequence ...
One aspect in which retrieving named entities is different from retrieving documents is that the items to be retrieved – persons, locations, organizations – are only indirect...
Image categorization is undoubtedly one of the most challenging open problems faced in Computer Vision, far from being solved by employing pure visual cues. Recently, additional t...
Marco Cristani, Alessandro Perina, Umberto Castell...
Being able to incorporate, inspect, and analyze data with newly developed technologies, diagnostics, and visualizations in an easy and flexible way has been a longstanding challen...
Dean N. Williams, Charles M. Doutriaux, Robert S. ...
We build a generic methodology based on learning and reasoning to detect specific attitudes of human agents and patterns of their interactions. Human attitudes are determined in te...
Boris Galitsky, Boris Kovalerchuk, Sergei O. Kuzne...