This work introduces a general mathematical framework for non-stationary fitness functions which enables the exact definition of certain problem properties. The properties' in...
This paper describes an approach to attention based layout segmentation using general principles of the human visual perception to achieve this goal. The text is considered as tex...
Tiling systems that recognize two-dimensional languages are intrinsically non-deterministic models. We introduce the notion of deterministic tiling system that generalizes determin...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
There is a growing interest in building probabilistic models with high order potentials (HOPs), or interactions, among discrete variables. Message passing inference in such models...