In this paper, we compute the residual energy of predictive frames (i.e., unidirectional and bidirectional motion prediction) by using the autocorrelation between successive video...
This paper deals with the fully automatic extraction of classifiable person features out of a video stream with challenging background. Basically the task can be split in two part...
Direct volume rendering and isosurfacing are ubiquitous rendering techniques in scientific visualization, commonly employed in imaging 3D data from simulation and scan sources. Con...
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...
Tabletop computers based on diffuse illumination can track fiducial markers placed on the table’s surface. In this paper, we demonstrate how to do the same with objects arranged...