The prevailing approach to evaluating classifiers in the machine learning community involves comparing the performance of several algorithms over a series of usually unrelated data...
In order to support interactive high-fidelity prototyping of postWIMP user interactions, we propose a multi-fidelity design method based on a unifying component-based model and su...
Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the ...
In this paper, line search based on Sequential Quadratic Programming is implemented in order to find a solution to Fuzzy Relation Equations. Sequential Quadratic Programming is a g...
We propose a method for segmentation of frontal human portraits from arbitrary unknown backgrounds. Semantic information is used to project the face into a normalized reference fr...
David C. Schneider, Benjamin Prestele, Peter Eiser...