We present the IBM systems submitted and evaluated within the CLEAR'06 evaluation campaign for the tasks of single person visual 3D tracking (localization) and 2D face trackin...
In this paper, we propose a semantic-meaningful approach for region-based image retrieval in image database. Our retrieval system is based on wavelet transform for its decompositi...
While we expect to discover knowledge in the texts available on the Web, such discovery usually requires many complex analysis steps, most of which require different text handling...
This paper describes a novel method for browsing a large video collection. It links various forms of related video fragments together as threads. These threads are based on query r...
Anecdotal evidence suggests that Web document summaries provide the sighted reader with a basis for making decisions regarding the route to take within non-linear text; and additi...