An algorithm for speaker's lip segmentation and features extraction is presented in this paper. A color video sequence of speaker's face is acquired, under natural light...
Verifying security properties of protocols requires developers to manually create protocol-specific intruder models, which could be tedious and error prone. We present Slede, a ve...
We propose a non-linear graphical model for structured prediction. It combines the power of deep neural networks to extract high level features with the graphical framework of Mar...
This paper addresses the problem of classification in situations where the data distribution is not homogeneous: Data instances might come from different locations or times, and t...
It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domai...