Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiplescale mu...
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
Ranking is at the heart of many information retrieval applications. Unlike standard regression or classification in which we predict outputs independently, in ranking we are inter...
30 digitization devices produce very large sets of 3 0 points sampled from the suqaces of the objects being scanned. A mesh construction procedure needs to be:upplied to derive po...
Abstract. Conventional tabletop systems have focused on communication with virtual data, using phicons or physical objects as handles. This approach is versatile, given the full us...