In a visualization of a three-dimensional dataset, the insights gained are dependent on what is occluded and what is not. Suggestion of interesting viewpoints can improve both the...
A typical way to perform video annotation requires to classify video elements (e.g. events and objects) according to some pre-defined ontology of the video content domain. Ontolo...
—Web-scale image search engines (e.g. Google Image Search, Bing Image Search) mostly rely on surrounding text features. It is difficult for them to interpret users’ search int...
Xiaoou Tang, Ke Liu, Jingyu Cui, Fang Wen, Xiaogan...
We propose a novel hashing scheme for image retrieval,
clustering and automatic object discovery. Unlike commonly
used bag-of-words approaches, the spatial extent of
image featu...
Ondrej Chum (Czech Technical University), Michal P...
We present a fast, topology-preserving approach for isosurface simplification. The underlying concept behind our approach is to preserve the disconnected surface components in cel...