Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
In this paper, a spatially constrained mixture model for the segmentation of MR brain images is presented. The novelty of this work is a new, edge preserving, smoothness prior whic...
Giorgos Sfikas, Christophoros Nikou, Nikolas P. ...
Conditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by exte...
This paper investigates the combination of spatial and probabilistic models for reasoning about pedestrian behaviour in visual surveillance systems. Models are learnt by a multi-s...
—This paper addresses the problem of self-validated labeling of Markov random fields (MRFs), namely to optimize an MRF with unknown number of labels. We present graduated graph c...