We analyze a problem, which is relevant for physiological modeling of vascular networks: the initialization and optimization of specific, individual models of a functioning vessel ...
The objective of this paper is to study the existing methods for unsupervised object recognition and image categorization and propose a model that can learn directly from the outp...
Abstract. Active Appearance Models (AAM) are compact representations of the shape and appearance of objects. Fitting AAMs to images is a difficult, non-linear optimization task. Tr...
We describe a method to retrieve images found on web pages with specified object class labels, using an analysis of text around the image and of image appearance. Our method dete...
In this paper we derive an independent-component analysis (ICA) method for analyzing two or more data sets simultaneously. Our model permits there to be components individual to t...
Ana S. Lukic, Lars Kai Hansen, Miles N. Wernick, S...