This paper introduces a new region based feature for object recognition and image matching. In contrast to many other region based features, this one makes use of colour in the fe...
This paper proposes a framework for semi-supervised structured output learning (SOL), specifically for sequence labeling, based on a hybrid generative and discriminative approach...
Chunk parsing has focused on the recognition of partial constituent structures at the level of individual chunks. Little attention has been paid to the question of how such partia...
Visual recognition faces the difficult problem of recognizing objects despite the multitude of their appearances. Ample neuroscientific evidence shows that the cortex uses a topogr...
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all ...