Energy functional minimization is an increasingly popular technique for image segmentation. However, it is far too commonly applied with hand-tuned parameters and initializations t...
We present a general Bayesian framework for hyperparameter tuning in L2-regularized supervised learning models. Paradoxically, our algorithm works by first analytically integratin...
Although privacy is broadly recognized as a dominant concern for the development of novel interactive technologies, our ability to reason analytically about privacy in real settin...
Object tracking is commonly used in video surveillance, but typically video with full frame rate is sent. We previously have shown that full frame rate is not needed, but it is unc...
—With increasing spatial reuse of the radio spectrum, co-channel interference is becoming the dominant noise source and may severely degrade the communication performance of wire...
Kapil Gulati, Aditya Chopra, Brian L. Evans, Keith...