This paper develops the concept of usefulness in the context of supervised learning. We argue that usefulness can be used to improve the performance of classification rules (as me...
Gholamreza Nakhaeizadeh, Charles Taylor, Carsten L...
The main focus of this paper is to present a method of reusing motion captured data by learning a generative model of motion. The model allows synthesis and blending of cyclic moti...
In this paper, we investigate the components of a Research 2.0 infrastructure. We propose building blocks and their concrete implementation to leverage Research 2.0 practice and te...
Thomas Daniel Ullmann, Fridolin Wild, Peter Scott,...
: The performance of a statistical machine translation (SMT) system heavily depends on the quantity and quality of the bilingual language resource. However, the pervious work mainl...
In this paper, we propose a semi-supervised kernel matching method to address domain adaptation problems where the source distribution substantially differs from the target distri...