When blind people wish to walk through an area not fully known to them, they have to prepare themselves even more thoroughly than sighted pedestrians. We propose a new approach to...
Word sense disambiguation algorithms, with few exceptions, have made use of only one lexical knowledge source. We describe a system which t)erforms word sense disambiguation on al...
We propose an approach to find and describe objects within broad domains. We introduce a new dataset that provides annotation for sharing models of appearance and correlation acr...
New cameras are installed daily all around the world. Hence it becomes increasingly important to develop methods for reducing the manual effort that is still required for video ana...
The development of Dialog-Based ComputerAssisted Language Learning (DB-CALL) systems requires research on the simulation of language learners. This paper presents a new method for...