: Accurate and efficient video classification demands the fusion of multimodal information and the use of intermediate representations. Combining the two ideas into one framework, ...
This paper proposes an approach to automatically generate semantics for scientific e-documents, and presents its applications in e-document understanding, question answering and q...
This paper describes the rationale and subsequent development stages of a work in progress: a graffiti toolkit for rich spatial 3D environments and an actual world mnemonic collec...
Subdivision-based representations are recognized as important tools for the generation of high-quality surfaces for Computer Graphics. In this paper we describe two parameterizati...
Shadow maps are a widely used shadowing technique in real time graphics. One major drawback of their use is that they cannot be filtered in the same way as color textures, typica...