in Proc. IEEE Int’l Conf. on Computer Vision (ICCV), October, 2007 Traditional Bayesian restoration methods depend heavily on the accuracy of underlying generative models. For t...
Yunqiang Chen, Lin Cheng, Tong Fang, Rainer Raupac...
Automatic speaker localization is an important task in several applications such as acoustic scene analysis, hands-free videoconferencing orspeechenhancement.Trackingspeakersinmult...
Carlos Segura, Alberto Abad, Javier Hernando, Clim...
We develop a new surface matching framework to handle surface comparisons based on a novel mathematical analysis of curves on surfaces, and propose a unique signature for any clos...
This paper introduces a novel high speed convolutional character recognition system. Convolutional mode operation means that no prior localization or segmentation of characters is...
straction of Complex Network Compositions∗ Azer Bestavros, Adam D. Bradley, Assaf J. Kfoury, and Ibrahim Matta Department of Computer Science Boston University The heterogeneity...
Azer Bestavros, Adam Bradley, Assaf J. Kfoury, Ibr...