Abstract. A challenge for virtual reality (VR) applications is to increase the realism of an observer’s visual experience. For this purpose the variation of the blur an observer ...
Abstract—In this paper, three approaches to utilizing objectlevel spatial contextual information for semantic image analysis are presented and comparatively evaluated. Contextual...
Georgios Th. Papadopoulos, Carsten Saathoff, Hugo ...
The Earth Mover's Distance (EMD) is a similarity measure that captures perceptual difference between two distributions. Its computational complexity, however, prevents a direc...
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
ZuiScat is a visualization concept for querying large information spaces on Personal Digital Assistants (PDA). Retrieval results are presented in a dynamic scatterplot, which is e...