Multimedia has become technically easier to create (e.g. recording lectures) but while users can easily bookmark, search, link to, or tag the WHOLE of a podcast or video recording...
Mike Wald, Gary Wills, David E. Millard, Lester Gi...
We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
In this paper we present the first large-scale scene attribute database. First, we perform crowd-sourced human studies to find a taxonomy of 102 discriminative attributes. Next,...
This paper presents novel methods for classifying images based on knowledge discovered from annotated images using WordNet. The novelty of this work is the automatic class discove...
Image transmission with JPEG2000 can be speeded up by using regions of interest (RoIs). By such a mechanism, parts of an image not belonging to RoIs can be transmitted later or en...