This paper describes the participation of Idiap-MULTI to the Robot Vision Task at imageCLEF 2010. Our approach was based on a discriminative classification algorithm using multiple...
For many multi-part object classes, the set of parts can vary not only in location but also in type. For example, player formations in American football involve various subsets of...
Geographic information has spawned many novel Web applications where global positioning system (GPS) plays important roles in bridging the applications and end users. Learning kno...
We introduce a predictive concept recognition methodology for description logics based on a new closed terminology assumption. During knowledge engineering, our system adopts the ...
This paper describes the use of machine learning to improve the performance of natural language question answering systems. We present a model for improving story comprehension th...