George Papandreou – Home Page
 |
Contact info 8145 Math Sciences Building Phone: +1-310-310-4614 |
About Me
I am a postdoctoral research scholar at the UCLA Department of Statistics, working with Prof. Alan Yuille. My research interests are in computer vision, image analysis, machine learning, and multimodal processing. I approach these problems with methods from Bayesian statistics, signal processing, and applied mathematics.
I hold a Diploma (2003) and a PhD (2009) in Electrical and Computer Engineering from NTUA, Greece, where I was a CVSP group member, advised by Prof. Petros Maragos. Before that I worked as a research assistant (2001-2003) at IIT-Demokritos, Athens, Greece. I have also been a summer intern (2006) at the Sigmedia group in Trinity College Dublin, Ireland.
Recent Research Highlight: Perturb-and-MAP Random Fields
 |
We have been developing a new Perturb-and-MAP framework for one-shot random
sampling in Gaussian or discete-label Markov random fields (MRF). With
Perturb-and-MAP random fields we turn powerful deterministic energy
minimization methods into efficient random sampling algorithms. By avoiding
costly MCMC, we can generate in a fraction of a second independent random
samples from million-node networks. Applications include model parameter
estimation and solution uncertainty quantification in computer vision
applications. |
News
June 23, 2011 — Our paper on Perturb-and-MAP Discrete-Valued Random Fields has been accepted and selected for oral presentation at ICCV-2011.
October 5, 2011 — Our paper on Bayesian Compressed Sensing has been accepted and selected for oral presentation at the IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition, in conjunction with ICCV-2011.