Our goal is to optimize regularized image reconstruction methods for emission tomography with respect to the task of detecting small lesions of unknown location in the reconstruct...
We introduce a regularized kernel-based rule for unsupervised change detection based on a simpler version of the recently proposed kernel Fisher discriminant ratio. Compared to ot...
We present a simple technique for single-rate compression of point clouds sampled from a surface, based on a spanning tree of the points. Unlike previous methods, we predict futur...
Abstract. Stacked generalization is a flexible method for multiple classifier combination; however, it tends to overfit unless the combiner function is sufficiently smooth. Prev...
In this paper we describe an approach to representation of data and knowledge using two technologies: XML and regular expressions in a domain of natural language syntactic analysis...