Abstract. In this paper, we present novel image-derived, invariant features that accurately capture both the geometric and color properties of an imaged object. These features can ...
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
In silico bioinformatics experiments involve integration of and access to computational tools and biological databases. The emerging grid computing technologies enable bioinformat...
Abstract. Automatic delineation of anatomical structures in 3-D volumetric data is a challenging task due to the complexity of the object appearance as well as the quantity of info...
Wei Hong, Bogdan Georgescu, Xiang Sean Zhou, Srira...
Many modern database applications require content-based similarity search capability in numeric attribute space. Further, users' notion of similarity varies between search se...