We here describe the subword approach we used in the 2006 ImageCLEF Medical Image Retrieval task. It is based on the assupmtion that neither fully inflected nor automatically stem...
Discovering users' specific and implicit geographic intention in web search can greatly help satisfy users' information needs. We build a geo intent analysis system that...
We present a method that uses measured scene radiance and global illumination in order to add new objects to light-based models with correct lighting. The method uses a high dynam...
In this paper we unify two supposedly distinct tasks in multimedia retrieval. One task involves answering queries with a few examples. The other involves learning models for seman...
Abstract. In this paper, we address the problem of computing a canonical representation of an n-dimensional combinatorial map. To do so, we define two combinatorial map signatures...