Events
You are invited to attend the 2022 Machine Learning Lab Public Lecture with Alan Bovik on Wednesday, November 16, 2022, in the Amir & Zaib Husain Auditorium (GDC 2.216) on The University of Texas at Austin main campus, A reception with refreshments will follow the talk.
Every day, hundreds of millions of photos and videos are captured by and streamed and shared online. Numerous distortions can affect these visual signals: blurs, compression, jitter, shake, noise, judder, over/under-exposure, etc., often combining to create multitudes of composite impairments impossible to model analvtically The problem is made harder because the way that humans perceive distortions depends on the content being viewed: for example different videos on which identical distortions occur can lie at opposite ends of the perceptual quality scale, because of neurophysiological masking processes.
To explain modern methods of measuring perceptual visual quality, Bovik will explain why video signals are "special," having internal statistical structures that visual systems have optimally evolved to optimally encode and process what we see. These special attributes have been used to create statistical picture and video qualitv models that now monitor and control much of all Internet traffic. The talk will cover the need for very large-scale psychometric databases of human judgments of video quality, and modern picture and video quality prediction engines that are deployed at global scales, monitoring and controlling the perceptual quality of most streaming and social visual media.
Refreshments will be provided in the atrium following the talk
Register to Attend
