Professor Avideh Zakhor, UC Berkeley, USA
Biography
Avideh Zakhor is currently Qualcomm Chair and professor in EECS at U.C. Berkeley. Her areas of interest include theories and applications of signal, image and video processing and 3D computer vision. She has won a number of best paper awards, including the IEEE Signal Processing Society in 1997 and 2009, IEEE Circuits and Systems Society in 1997 and 1999 and IEEE Solid Circuits Society in 2008.
Prof. Zakhor received the B. S. degree from Caltech and the S. M. and Ph. D. degrees from MIT all in electrical engineering, in 1983, 1985, and 1987 respectively. She was a General Motors scholar from 1982 to 1983, was a Hertz fellow from 1984 to 1988, received the Presidential Young Investigators (PYI) award from President George Herbert Walker Bush in 1990, and Office of Naval Research (ONR) young investigator award in 1992. In 2001, she was elected as IEEE fellow and in 2018 she was chosen as the Electronics Imaging Scientist of the year by Society of Photographic instrumentation Engineers (SPIE).
She co-founded OPC technology in 1996, which was later by Mentor Graphics (Nasdaq: MENT) in 1998, and UrbanScan Inc. in 2005 which was acquired by Google (Nasdaq:GOOGL) in 2007. She founded Indoor Reality in 2015 to develop technologies for rapid 3D mapping and visualization of buildings and assets;
Professor Alex Dimakis, Univ. of Texas at Austin, USA
Deep Generative Models and Inverse Problems
Abstract: Linear inverse problems involve the reconstruction of an unknown vector (e.g. a tomography image) from an underdetermined system of noisy linear measurements. Most results in the literature require that the reconstructed signal has some known structure, e.g. it is sparse in some basis (usually Fourier or Wavelet). In this work we show how to remove such prior assumptions and rely instead on deep generative models (e.g. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs)). We show how the problems of image inpainting (completing missing pixels) and super-resolution are special cases of our general framework. We generalize theoretical results on compressive sensing for deep generative models and discuss several open problems.
Biography
Alex Dimakis is an Associate Professor at the Electrical and Computer Engineering department, University of Texas at Austin. From 2009 until 2012 he was with the Viterbi School of Engineering, University of Southern California. He received his Ph.D. in 2008 and M.S. degree in 2005 in electrical engineering and computer sciences from UC Berkeley and the Diploma degree from the National Technical University of Athens in 2003. During 2009 he was a CMI postdoctoral scholar at Caltech. He received an ARO young investigator award in 2014, the NSF Career award in 2011, a Google faculty research award in 2012 and the Eli Jury dissertation award in 2008. He is the co-recipient of several best paper awards including the joint Information Theory and Communications Society Best Paper Award in 2012. He served two terms as an associate editor for IEEE Signal Processing letters and is currently serving as an associate editor for IEEE Transactions on Information Theory. His research interests include information theory, coding theory and machine learning.
Dr. Ioannis Katsavounidis, Meta (formerly Facebook), USA
“Energy efficient video processing – what do future video coding standards need to deliver?”
Abstract: With the proliferation of social media, the volume of videos uploaded and shared on the Web has been continuously growing – and along with it the amount of energy needed to process, store and distribute them globally. Video coding standards have offered significant improvements in video quality, or equivalently, big reduction in bitrates while maintaining the same visual quality. Traditionally, such improvements in video coding carried equally significant, and as of late even more disproportionate so, increases in compute/energy requirements to deliver these savings. We will look into the problem of energy efficient video processing holistically and propose a few ways to address the growing demand in video processing through system-level optimization and by elevating energy efficiency to become a first-class citizen in future video coding standards.
Biography
Dr. Ioannis Katsavounidis is part of the Video Infrastructure team, leading technical efforts in improving video quality and quality of experience across all video products at Meta (formerly known as Facebook). Before joining Meta, he spent 3.5 years at Netflix, contributing to the development and popularization of VMAF, Netflix’s open-source video quality metrics, as well as inventing the Dynamic Optimizer, a shot-based perceptual video quality optimization framework that brought significant bitrate savings across the whole streaming spectrum. VMAF and the dynamic optimizer awarded Netflix two technical Emmys in 2020. He was a professor for 8 years at the University of Thessaly’s Electrical and Computer Engineering Department in Greece, teaching video compression, signal processing and information theory. He was one of the cofounders of Cidana, a mobile multimedia software company in Shanghai, China. He was the director of software for advanced video codecs at InterVideo, the makers of WinDVD, the most popular SW DVD player, in the early 2000’s and he has also spent 4 years working in high-energy experimental Physics in Italy. He is one of the co-chairs for the statistical analysis methods (SAM) and no-reference metrics (NORM) groups at the Video Quality Experts Group (VQEG). He is actively involved within the Aliance for Open Media (AOM) as co-chair of the software implementation working group (SWIG). He has over 150 publications, including 50 patents. His research interests lie in video coding, quality of experience, adaptive streaming, and energy efficient HW/SW multimedia processing.