This paper presents a new model of human attention that allows salient areas to be extracted from video frames. As automatic understanding of video semantic content is still far fr...
The recent advances in non-scalable video encoding brought by the H.264/AVC standard offered significant improvements in terms of rate-distortion performance. This paper proposes ...
What do you do to make sense of a mass of information on a given topic? Paradoxically, you likely add yet more information to the pile: annotations, underlining, bookmarks, cross-...
Lois M. L. Delcambre, David Maier, Shawn Bowers, M...
The ability to automatically record the marks applied to paper documents on their electronic originals would preserve the information represented by those annotations. Users could...
Clustering data in high dimensions is believed to be a hard problem in general. A number of efficient clustering algorithms developed in recent years address this problem by proje...
Kamalika Chaudhuri, Sham M. Kakade, Karen Livescu,...