We present two new hyperbolic source probability models to effectively represent sub-gaussian and super-gaussian families of sources for dynamic and convolutive Blind Source Recov...
We introduce factored language models (FLMs) and generalized parallel backoff (GPB). An FLM represents words as bundles of features (e.g., morphological classes, stems, data-drive...
We present a set of techniques for the synthesis of artificial images that depict branching structures like rivers, cracks, lightning, mountain ranges, or blood vessels. The centr...
Abstract-- With increasing richness in features such as personalization of content, web applications are becoming more complex and hence compute intensive. Traditional approaches t...
This paper provides a method for recognizing 3D objects in a single camera image and for determining their 3D poses. A model is trained solely based on the geometry information of ...
Markus Ulrich, Christian Wiedemann, Carsten Steger