We propose a flexible summarization framework for teamsport videos, which is able to integrate both the knowledge about displayed content (e.g. level of interest, type of view, et...
Our goal is to optimize regularized image reconstruction methods for emission tomography with respect to the task of detecting small lesions of unknown location in the reconstruct...
Current methods for finding relevant content, especially in media-rich web environments, suggest that metadata is critical for accurate and efficient information retrieval. We des...
We introduce a new approach to approximating weighted Max-SAT problems that is based on simplifying a given instance, and then tightening the approximation. First, we relax its str...
The current surge of interest in virtual worlds suggests they are poised to make an evolutionary leap to the workplace, as instant messaging did a decade ago. In recent work we ha...