We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up,...
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
Audio descriptor extraction is the activity of finding mathematical models which describe properties of the sound, requiring signal processing skills. The scientific literature pr...
Correlating and analyzing security alerts is a critical and challenging task in security management. Recently, some techniques have been proposed for security alert correlation. H...
Transmitting voice communication over untrusted networks puts personal information at risk. Although voice streams are typically encrypted to prevent unwanted eavesdropping, additi...