Automatic image tagging is important yet challenging due to the semantic gap and the lack of learning examples to model a tag’s visual diversity. Meanwhile, social user tagging ...
Performance on an information gathering task is shown to be superior in teleconference. Analysis of errors in an exercise revealed the data sources used in co-located and teleconf...
Visual Query Languages represent an evolution, in terms of understandability and adaptability, with respect to traditional textual languages. We present an iconic query system tha...
Lerina Aversano, Gerardo Canfora, Andrea De Lucia,...
In this paper, we propose a novel graph embedding method for the problem of lipreading. To characterize the temporal connections among video frames of the same utterance, a new di...
Realism has always been a goal in computer graphics. However, the algorithms involved in mimicking ical world are often complex, abstract, and sensitive to changes in experimental...