Sparse representations using overcomplete dictionaries are used in a variety of field such as pattern recognition and compression. However, the size of dictionary is usually a tra...
We present our work on using Wikipedia as a knowledge source for Natural Language Processing. We first describe our previous work on computing semantic relatedness from Wikipedia...
Several theoretical methods have been developed in the past years to evaluate the generalization ability of a classifier: they provide extremely useful insights on the learning ph...
Content-based image retrieval methods based on the Euclidean metric expect the feature space to be isotropic. They suer from unequal dierential relevance of features in comput...
We address the practical problem of automating the process of translating figures from mathematics, science, and engineering textbooks to a tactile form suitable for blind student...
Chandrika Jayant, Matthew Renzelmann, Dana Wen, Sa...