In this paper we investigate how a small number of high-level concepts derived for video shots, such as Sports, Face, Indoor, etc., can be used effectively for ad hoc search in vi...
Overlapping genes (encoded on the same DNA strand but in different frames) are thought to be rare and, therefore, were largely neglected in the past. In a test set of 800 viruses ...
A substantial subset of the web data follows some kind of underlying structure. Nevertheless, HTML does not contain any schema or semantic information about the data it represents...
We study the usefulness of intermediate semantic concepts in bridging the semantic gap in automatic video retrieval. The results of a series of large-scale retrieval experiments, w...
A major obstacle to the construction of a probabilistic translation model is the lack of large parallel corpora. In this paper we first describe a parallel text mining system that...