We initiate a study comparing effectiveness of the transformed spaces learned by recently proposed supervised, and semisupervised metric learning algorithms to those generated by ...
Paramveer S. Dhillon, Partha Pratim Talukdar, Koby...
Graph matching is an important problem in computer
vision. It is used in 2D and 3D object matching and recognition.
Despite its importance, there is little literature on
learnin...
Most word sense disambiguation (WSD) methods require large quantities of manually annotated training data and/or do not exploit fully the semantic relations of thesauri. We propos...
George Tsatsaronis, Michalis Vazirgiannis, Ion And...
Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the h...
A possible alternative to fine topology tuning for Neural Network (NN) optimization is to use Echo State Networks (ESNs), recurrent NNs built upon a large reservoir of sparsely r...