We describe our approach to the automatic generation of argument structures in the domain of video documentaries. Our approach releases control of the final video sequencing from...
Real-time applications such as multimedia audio and video are increasingly populating the workstation desktop. To support the execution of these applications in conjunction with t...
It is difficult to adapt discriminative classifiers, particularly kernel based ones such as support vector machines (SVMs), to handle mismatches between the training and test da...
OneClassMaxMinOver (OMMO) is a simple incremental algorithm for one-class support vector classification. We propose several enhancements and heuristics for improving model select...
In this paper we present the evaluation of a virtual mirror used as a navigational tool within a medical augmented reality (AR) system for laparoscopy. 12 surgeons of our clinical...
Christoph Bichlmeier, Sandro Michael Heining, Moha...