We introduce a method for predicting a control signal from another related signal, and apply it to voice puppetry: Generating full facial animation from expressive information in ...
Abstract. We describe progress in the automatic detection and identification of humans in video, given a minimal number of labelled faces as training data. This is an extremely cha...
Abstract. We propose a novel method for addressing the model selection problem in the context of kernel methods. In contrast to existing methods which rely on hold-out testing or t...
Abstract. A new method is introduced for estimating single-trial magnetoor electro-encephalography (M/EEG), based on a non-linear fit of timefrequency atoms. The method can be appl...
In this paper we address the problem of simultaneous estimation of structure and restoration of images from blurred photometric measurements. Given the blurred observations of a s...