Fusion of multimedia streams for enhanced performance is a critical problem for retrieval. However, fusion performance tends to easily overfit the hillclimb set used to learn fus...
This paper addresses automatic image annotation problem and its application to multi-modal image retrieval. The contribution of our work is three-fold. (1) We propose a probabilis...
Most database interfaces provide poor guidance on ad hoc query formulation, burdening users to learn, and to recall precisely the query language and the database. Kaleidoscope avo...
In this paper, we present a novel image representation that renders it possible to access natural scenes by local semantic description. Our work is motivated by the continuing effo...
Existing ADLs (Architecture Description Languages) have an advantage of formally specifying the architecture of component-based systems. But ADLs have not come into extensive use ...