Graphical models are a framework for representing and exploiting prior conditional independence structures within distributions using graphs. In the Gaussian case, these models are...
This paper describes a qualitative study of how 11 Arab individuals use technology in the context of their longdistance romantic relationships. Our participants’ communication p...
Spatially-discrete Markov random fields (MRFs) and spatially-continuous variational approaches are ubiquitous in low-level vision, including image restoration, segmentation, opti...
We propose a new objective function for superpixel segmentation. This objective function consists of two components: entropy rate of a random walk on a graph and a balancing term....
Color is a powerful attribute that is used to characterize objects for tracking and other surveillance tasks. Since color is dependent on ambient illumination and the imaging equi...