We introduce a method for learning Bayesian networks that handles the discretization of continuous variables as an integral part of the learning process. The main ingredient in th...
A method is proposed for the compression of hyperspectral signature vectors on severely resourceconstrained encoding platforms. The proposed technique, compressive-projection prin...
We propose a calibration-free gaze sensing method using visual saliency maps. Our goal is to construct a gaze estimator only using eye images captured from a person watching a vid...
We present a flexible method for fusing information from optical and range sensors based on an accelerated highdimensional filtering approach. Our system takes as input a sequen...
Jennifer Dolson, Jongmin Baek, Christian Plagemann...
We propose a method that rates the suitability of given templates for template-based tracking in real-time. This is important for applications with online template selection, such...