Traditional Markov network structure learning algorithms perform a search for globally useful features. However, these algorithms are often slow and prone to finding local optima d...
We propose a new loss function for discriminative learning of Markov random fields, which is an intermediate loss function between the sequential loss and the pointwise loss. We s...
A method is proposed to detect multi-part man-made or natural objects in complex images. It consists in first extracting simple curves and straight lines from the edge map. Then, ...
In this paper a completely automatic face recognition system is presented. It consists of two main modules: in the first, the facial fiducial points are localized, and in the seco...
This paper presents patterns of cooperative interaction derived from ethnographic studies of cooperative work as devices for generalisation, re-use and design. These patterns cons...