We propose an hybrid and probabilistic classification of image regions belonging to scenes primarily containing natural objects, e.g. sky, trees, etc. as a first step in solving ...
Abstract. Combinatorial maps define a general framework which allows to encode any subdivision of an nD orientable quasi-manifold with or without boundaries. Combinatorial pyramids...
One of the principal bottlenecks in applying learning techniques to classification problems is the large amount of labeled training data required. Especially for images and video, ...
Ajay J. Joshi, Fatih Porikli, Nikolaos Papanikolop...
We propose a novel energy term to make the curve evolution quite robust to spurious edges. The physical intuition behind the formulation is that an object edge is generally contin...
Active learning methods have been considered with increased interest in the statistical learning community. Initially developed within a classification framework, a lot of extensio...