As part of a more extensive study of reading-related practices, we have explored how people share information they encounter in their everyday reading as a complement to the more ...
This paper deals with the fully automatic extraction of classifiable person features out of a video stream with challenging background. Basically the task can be split in two part...
This paper presents a family of techniques that we call congealing for modeling image classes from data. The idea is to start with a set of images and make them appear as similar a...
Libraries have traditionally used manual image annotation for indexing and then later retrieving their image collections. However, manual image annotation is an expensive and labo...
We propose a method for reliably and accurately identifying anatomical landmarks in 3D CT volumes based on dense matching of parts-based graphical models. Such a system can be use...