BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Brown Bag,Colloquium/Seminar
DESCRIPTION:Abstract:  Predicting the perceptual quality of pictures and vi
 deos is a hard problem that has been successfully addressed in many scenari
 os\, such as quality control of streaming videos and sharing of social medi
 a pictures. In this talk I will address how visual quality perception can b
 e understood using principles of neuroscience and neuro-statistical models 
 of distortion. In particular I will review some basic vision science that m
 akes accurate perceptual visual quality prediction possible\, and how algor
 ithms are designed that are now used worldwide. However\, generated content
  like gaming videos and GenAI pictures are fundamentally different from opt
 ical pictures\, and those differences may be statistically testable. I will
  discuss a recent approach to gaming content quality prediction called GAMI
 VAL that combines neuro-statistical models adapted to gaming distortions wi
 th deep features that capture gaming semantics. I will also discuss an earl
 y exploration into the perceptual statistics of GenAI pictures\, and how th
 ese might be used to gauge GenAI visual quality and detectability.\n \n\nBi
 o: Al Bovik is the Cockrell Family Regents Endowed Chair Professor at The U
 niversity of Texas at Austin. His research interests land at the nexus of v
 isual neuroscience and digital pictures and videos\, and how their capture\
 , processing\, transmission\, and display can be perceptually optimized. An
  elected member of the U.S. National Academy of Engineering\, the Indian Na
 tional Academy of Engineering\, the National Academy of Inventors\, and Aca
 demia Europaea\, his many honors include the IEEE Edison Medal\, a Primetim
 e Emmy Award\, a Technology & Engineering Emmy Award\, the RPS Progress Med
 al\, and the Edwin H. Land Medal.\nhttp://utw10503.utweb.utexas.edu/bovik.p
 hp\, and https://www.colorado.edu/ecee/al-bovik
DTEND:20241112T193000Z
DTSTAMP:20260311T012130Z
DTSTART:20241112T183000Z
GEO:40.007435;-105.269921
LOCATION:Roser ATLAS Center\, ATLS 208
SEQUENCE:0
SUMMARY:ATLAS Colloquium: Al Bovik  on Statistical Predictions of the Visua
 l Quality of Pictures\, Games\, and GenAI
UID:tag:localist.com\,2008:EventInstance_47721005970563
URL:https://calendar.colorado.edu/event/atlas-colloquium-al-bovik-on-statis
 tical-predictions-of-the-visual-quality-of-pictures-games-and-genai
END:VEVENT
END:VCALENDAR