In this paper we introduce graph-evolution rules, a novel type of frequency-based pattern that describe the evolution of large networks over time, at a local level. Given a sequenc...
We present a novel approach to automatically find spatial configurations of local features occurring frequently on instances of a given object class, and rarely on the background....
Till Quack, Vittorio Ferrari, Bastian Leibe, Luc J...
We present a simple yet powerful hierarchical search algorithm for automatic word alignment. Our algorithm induces a forest of alignments from which we can efficiently extract a r...
This article focusses on the problems of feature extraction and the recognition of handwritten digits. A trainable feature extractor based on the LeNet5 convolutional neural netwo...
Web Mining Systems exploit the redundancy of data published on the Web to automatically extract information from existing web documents. The first step in the Information Extract...
Kostyantyn M. Shchekotykhin, Dietmar Jannach, Gerh...