BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:CIS - "Get to know your neighbors" Seminar series - Prof. Touradj 
 Ebrahimi
DTSTART:20220207T151500
DTEND:20220207T161500
DTSTAMP:20260917T081923Z
UID:576c5758e82e1767a3ba5b4f6e395f252ca84070c8ad8e3c5e00af77
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Touradj Ebrahimi\nTitle: JPEG AI: The text generation of
  learning based image compression\n\nAbstract:\nArtificial Intelligence (A
 I) has emerged as a key technology in a wide range of applications\, inclu
 ding those in visual information processing. \nComputer vision based on A
 I has shown outstanding results in pattern recognition and content underst
 anding and AI-based image processing has demonstrated unparalleled perfor
 mance in cognitive enhancement of visual content as witnessed by advances 
 in super-resolution and denoising operations taking advantage of deep lea
 rning techniques. More recent efforts in AI-based compression have shown s
 uperior performance when compared to the most advanced to state of the ar
 t in image coding.\nBased on the above observations\, the JPEG standardiza
 tion committee has started a new project in AI-based image compression for
  next generation applications where visual content should be efficiently 
 represented to be used for both human and machine consumption. The scope o
 f JPEG AI is defined as a learning-based image coding standard that offer
 s a single-stream\, compact and compressed domain representation\, targeti
 ng both human visualization\, with significant compression efficiency imp
 rovement over current image coding standards\, as well as effective perfor
 mance for image processing and computer vision tasks.\nIn this talk we wi
 ll provide an overview of JPEG AI activities\, its current status and its 
 roadmap. Doing so\, we will discuss potential applications that can be en
 abled thanks to JPEG AI\, and examine potential technologies which can bec
 ome the backbone of such a standard. \n\nBio:\nTouradj Ebrahimi is profes
 sor of image processing at Ecole Polytechnique Fédérale de Lausanne (EPF
 L). He is active in teaching and research in multimedia signal processing
  and heads the Multimedia Signal Processing Group at EPFL. \nSince 2014\,
  he has been the Convenor (Chairman) of the JPEG standardization Committee
  which has produced a family of standards that have revolutionised the wo
 rld of imaging. He represents Switzerland as the head of its delegation to
  JTC1 (in charge of standardization of information technology in ISO and 
 IEC)\, SC29 (the body overseeing MPEG and JPEG standardization) and is a m
 ember of ITU representing EPFL. He was previously the chairman of the SC2
 9 Advisory Group on Management until 2014. Prof. Ebrahimi is involved in E
 cma International as a member of its ExeCom since 2020 and serves as cons
 ultant\, evaluator and expert for European Commission and other government
 al funding agencies in Europe and advises a number of Venture Capital com
 panies in Switzerland in their scientific and technical audits. He has fou
 nded several startup and spinoff companies in the past two decades\, incl
 uding the most recent RayShaper SA\, a research company based in Switzerla
 nd involved in AI powered multimedia. Prof. Ebrahimi is author or co-auth
 or of over 300 scientific publications and hold a dozen invention patents.
  His areas of interest include image and video compression\, media securi
 ty\, quality of experience in multimedia and AI based image and video proc
 essing and analysis. Prof. Ebrahimi is a Fellow of the IEEE and SPIE and 
 has been recipient of several awards and distinctions\, including an IEEE 
 Star Innovator Award in Multimedia.\n\n\nThe CIS seminar will take place l
 ive on Zoom: https://epfl.zoom.us/j/63510408613\n\nPlease connect to your 
 zoom account using your "@epfl.ch" address\, as this live event is only op
 en to the EPFL community\nMonday\, February 7th\, 2022 from 3:15 to 4:15 p
 m\nNB: Video recordings of the seminars will be made available on our webs
 ite and published on our social media pages
LOCATION:Hybride TBD https://epfl.zoom.us/j/63510408613
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR