We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
A successful representation of objects in the literature is as a collection of patches, or parts, with a certain appearance and position. The relative locations of the different p...
Using keyword search to find relevant objects in digital libraries often results in way too large result sets. Based on the metadata associated with such objects, the faceted sear...
In this demo, we present IGroup, a Web image search engine that organizes the search results into semantic clusters. Different from all existing Web image search results clusterin...
In this document, we describe a light-weighted ontology mediation method that allows users to send semantic queries to distant data repositories to browse for learning object meta...