Social media enabled video sharing and distribution at massive scale. We will cover the basics of video processing, with emphasis on adaptive bitrate streaming, transcoding pipelines, objective quality metrics and efficiency of video encoders, both in terms of rate-distortion and in terms of energy tradeoffs. The importance of convex hull to characterize and optimize such efficiencies will be presented, together with the Dynamic Optimizer framework that can be used to perform this type of optimizations at individual shot, sequence or corpus levels. We will expand into a low-complexity variant of dynamic optimizer that can be used to solve efficiency problems at scale. Finally, we will offer insights into how modern video coding standards can be designed to offer even higher coding efficiency without necessarily increasing energy requirements.
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.
