Panel

• Video Quality Metrics and Their Industry Applications

Video Quality Metrics and Their Industry Applications

Video quality metrics and automated video quality assessment have gained momentum in the video industry, thanks to continuous accuracy improvement and complexity reduction of available tools. Given the diverse spectrum of video applications and their ecosystems, it would be interesting to share experiences and learnings on how companies apply these tools in building and operating products and services. This panel brings together experts from industry to discuss the following topics:

• How video streaming and conferencing companies build quality metrics into their workflow and how they meet their business needs

• How codec vendors use automated quality assessment to optimize their encoder performance

• The challenges and opportunities of the traditional psychovisual-based approach vs. the neural net-based approach

• Next unsolved impactful problems in perceptual quality assessment

Organizers: Zhi Li, Lukas Krasula, Anne Aaron, Netflix

Short bio of invited panelists:

• Jiayao Yu is an engineering manager in Snap, leading efforts around media delivery, transcoding, and playback. The team is responsible for making media in Snapchat look great and playback smoothly. He graduated as a BSc in Computer Science from Lancaster University, UK. He started his career in Symbian, working with the pioneers in the first generation smartphone OS. Later he joined Google, worked on several early mobile and advertising products for a few years before joining Snap.

  

• Sasikanth Bendapudi is the group manager for real time video engineering across multiple products in Microsoft including Teams, Skype and ACS. He also leads data analytic efforts related to media quality and reliability and is more recently known for scaling media quality and reliability of Microsoft real time products through the COVID-19 pandemic. He is an alumnus of Carnegie Mellon University, IIT Guwahati and specializes in Computer Vision, Real-Time Media and Scalable Systems.

  

• Tamar Shoham is a leading imaging and video scientist, with over 20 years experience in algorithm development and industry-oriented research, primarily in the field of video quality and compression. As Beamr’s CTO, Tamar has been leading the algorithm development since inception, focused primarily on optimizing image and video content using compliant codec. Prior to joining Beamr, she was a research associate at the Technion Signal and Image Processing Lab, performing and supervising research for the Israeli CSO NEGEV consortium, and prior to that, was in the algorithm group in Comverse, pioneering video solutions in the company. Tamar holds a Bachelor of Science from Tel-Aviv University, and a Masters of Science with honors from the Technion Institute of Technology, both in Electrical Engineering. She has published many academic papers, is a primary inventor of 40 international patents to date and winner of a Technology & Engineering Emmy® award.

  

• Lubomir Bourdev is a co-founder and the CEO of WaveOne, Inc., a company focusing on video compression with deep learning. He is also a founding member of Facebook AI Research and he founded and led the Facebook Computer Vision team responsible for the image and video content recognition engine at Facebook. Prior to that he was a Sr. Research Scientist at Adobe Research where he led development of computer vision and features in Adobe’s Creative Suite products. He holds a Ph.D. in Computer Science from U.C. Berkeley and M.Sc. and B.A. in Computer Science from Brown University.