We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
Because of the great variability of factors to take into account, designing a spoken dialogue system is still a tailoring task. Rapid design and reusability of previous work is ma...
Abstract. In this paper we propose a novel approach to define task-driven regularization constraints in deformable image registration using learned deformation priors. Our method ...
Ben Glocker, Nikos Komodakis, Nassir Navab, Georgi...
Abstract. The Internet has instigated a critical need for automated tools that facilitate integrating countless databases. Since non-technical end users are often the ultimate repo...
Based on Information Theory, optimal feature selection should be carried out by searching Markov blankets. In this paper, we formally analyze the current Markov blanket discovery ...