Basis functions derived from an undirected graph connecting nearby samples from a Markov decision process (MDP) have proven useful for approximating value functions. The success o...
The central issue in representing graphstructured data instances in learning algorithms is designing features which are invariant to permuting the numbering of the vertices. We pr...
Semantic matching determines the mappings between the nodes of two graphs (e.g., ontologies) by computing logical relations (e.g., subsumption) holding among the nodes that corresp...
Fausto Giunchiglia, Pavel Shvaiko, Mikalai Yatskev...
Pattern matching for intelligence organizations is a challenging problem. The data sets are large and noisy, and there is a flexible and constantly changing notion of what consti...
Michael Wolverton, Pauline Berry, Ian W. Harrison,...
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...