We report on results of combining graphical modeling techniques with Information Extraction resources (Pattern Dictionary and Lexicon) for both frame and semantic role assignment....
We show that the set of all ow- elds in a sequence of frames imaging a rigid scene resides in a lowdimensional linear subspace. Based on this observation, we develop a method for ...
A multi-class traffic scene segmentation approach based on scene flow data is presented. Opposed to many other approaches using color or texture features, our approach is purely ba...
Alexander Barth, Jan Siegemund, Annemarie Mei&szli...
Abstract. Prosody has been actively studied as an important knowledge source for speech recognition and understanding. In this paper, we are concerned with the question of exploiti...
Most design recovery approaches start from analysing source code. Nonetheless, it is very difficult to get adequate design information only depending on source code. Additional av...