We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradient-based learning algorithms to systems composed of modules th...
We introduce a novel data-driven mean-shift belief propagation
(DDMSBP) method for non-Gaussian MRFs, which
often arise in computer vision applications. With the aid
of scale sp...
Abstract. In recent years, the use of multimedia content has experienced an exponential growth. In this context, the need of new image/video sequence representation is becoming a n...