To support context-based multimodal interpretation in conversational systems, we have developed a semantics-based representation to capture salient information from user inputs an...
This paper extends the well-known technique of slicing to synchronous reactive programs. Synchronous languages exemplified by Esterel, Lustre, Signal and Argos, novel model of exe...
We present a method to automatically extract spatio-temporal descriptions of moving objects from synchronized and calibrated multi-view sequences. The object is modeled by a time-...
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
In this paper, a novel Kalman filter-based power allocation scheme is developed for cooperative networks with inaccurate channel state information (CSI). The channel estimation err...