Action recognition is one of the most active research fields in computer vision. In this paper, we propose a novel method for classifying human actions in a series of image seque...
We propose a unified framework based on a general definition of geometric transform (GeT) for modeling appearance. GeT represents the appearance by applying designed functionals o...
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...
This paper proposes a novel graph matching algorithm and applies it to shape recognition based on object silhouettes. The main idea is to match skeleton graphs by comparing the geo...
Single processor technology has been evolving across last decades, but due to physical limitations of chip manufacturing process, the industry is pursuing alternatives to sustain ...
Thiago S. M. C. de Farias, Mozart W. S. Almeida, J...