In this work, we systematically study the problem of visual event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which vide...
Abstract. In a stereoscopic system, both eyes or cameras have a slightly dierent view. As a consequence, small variations between the projected images exist (`disparities') ...
Abstract. Profiling is often the method of choice for performance analysis of parallel applications due to its low overhead and easily comprehensible results. However, a disadvanta...
This paper presents a principled and practical method for the computation of visual saliency of spatiotemporal events in full motion videos. Based on the assumption that uniquenes...
This paper describes a new representation for the audio and visual information in a video signal. We reduce the dimensionality of the signals with singular-value decompositions (S...