Large-scale digitization projects aimed at periodicals often have as input streams of completely unlabeled document images. In such situations, the results produced by the automat...
Iuliu Vasile Konya, Christoph Seibert, Sebastian G...
Traditional content-based image retrieval (CBIR) systems often fail to meet a user's need due to the `semantic gap' between the extracted features of the systems and the...
We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered sce...
We address the problem of shape based classification. We interpret the shape of an object as a probability distribution governing the location of the points of the object. An imag...
See www.research.microsoft.com/jojic/epitome.htm for videos, comparisons and applications. We present novel simple appearance and shape models that we call epitomes. The epitome o...