We present a three-step post-processing method for increasing the precision of video shot labels in the domain of television news. First, we demonstrate that news shot sequences c...
I describe the format of the new version of an introductory database course that I taught at the University of Washington in Winter, 2003. The key idea underlying the course is to...
The paper reports on the methodology and preliminary results of a case study in automatically extracting ontological knowledge from Italian legislative texts in the environmental d...
This work presents a discriminative model for the retrieval of pictures from text queries. The core idea of this approach is to minimize a loss directly related to the retrieval pe...