This paper describes how a visual system can automatically define features of interest from the observation of a large enough number of natural images. The principle complements t...
State-of-the-art methods for human detection and pose estimation require many training samples for best performance. While large, manually collected datasets exist, the captured v...
Leonid Pishchulin, Arjun Jain, Mykhaylo Andriluka,...
This paper presents a two-stage compression method for accelerating GPU-based volume rendering of time-varying scalar data. Our method aims at reducing transfer time by compressin...
For the rendering of vector and tensor fields, several texturebased volumetric rendering methods were presented in recent years. While they have indisputable merits, the classica...
Ovidio Mallo, Ronald Peikert, Christian Sigg, Fili...
Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. Cu...