Unconstrained face recognition is the problem of deciding if an image pair is showing the same individual or not, without having class specific training material or knowing anythi...
Richly labeled images representing several sub-structures of an organ occur quite frequently in medical images. For example, a typical brain image can be labeled into grey matter, ...
James G. Malcolm, Yogesh Rathi, Martha Elizabeth...
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...
One of the main obstacles to producing high quality joint models is the lack of jointly annotated data. Joint modeling of multiple natural language processing tasks outperforms si...
Although many methods of refining initialization have appeared, the sensitivity of K-Means to initial centers is still an obstacle in applications. In this paper, we investigate a...