In this chapter, we aim to connect the areas of object categorization and figure-ground segmentation. We present a novel method for the categorization of unfamiliar objects in diff...
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set...
We present a method for on-line mathematical formulae recognition based on the structural construction paradigm and twodimensional grammars. In general, this approach can be succes...
Abstract. In the European cognitive vision project VAMPIRE (IST2001-34401), mobile AR-kits are used for interactive teaching of a visual active memory. This is achieved by 3D augme...