We propose a new framework for discussing computational complexity of problems involving uncountably many objects, such as real numbers, sets and functions, that can be represente...
We propose a new approach to the notion of recognition, which departs from the classical definitions by three specific features. First, it does not rely on automata. Secondly, it...
We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning...
Image segmentation techniques are predominately based on parameter-laden optimization processes. The segmentation objective function traditionally involves parameters (i.e. weights...
This paper presents a hybrid 1D motion estimation algorithm which combines pixel-based and region-based approaches that can give depth images from translational video sequences wi...