Interest in multioutput kernel methods is increasing, whether under the guise of multitask learning, multisensor networks or structured output data. From the Gaussian process pers...
Mauricio Alvarez, David Luengo, Michalis Titsias, ...
In this paper, we propose a new variational decomposition model which splits an image into two components: a first one containing the structure and a second one the texture or nois...
Text line segmentation in unconstrained handwritten documents remains a challenge because handwritten text lines are multi-skewed and not obviously separated. This paper presents ...
We propose a methodology for investigating how well NLP systems handle meaning preserving syntactic variations. We start by presenting a method for the semi automated creation of ...
For the natural notion of splitting classes into two disjoint subclasses via a recursive classifier working on texts, the question is addressed how these splittings can look in th...