BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Recent advances in data compression
DTSTART:20190506T103000
DTEND:20190506T113000
DTSTAMP:20260407T120149Z
UID:7bbc42b7302425c7fab4953814c5d9334458c4db64ecbb65ef4c1665
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Touradj Ebrahimi\nEPFL-STI-IEL\, Multimedia Signal Proce
 ssing Group\nImage and image sequence contents often represent a substanti
 al volume of data. In most cases\, there is a statistical redundancy among
  samples of such data that if appropriately modeled\, can reduce their vol
 ume. Also\, as the vast majority of image content is destined to be consum
 ed by human subjects\, further compression can be obtained by taking into 
 account the properties of the human visual system.  Practical considerati
 ons such as complexity\, memory requirements\, delay\, progressiveness\, b
 ackward compatibility\, lossy or lossless transcoding\, error resiliency\,
  etc. often play an important role when designing and deploying useful ima
 ge and video compression technologies. \nIn this presentation\, we start 
 with an overview of the design choices that led to the popular JPEG image 
 compression format with emphasis on its advantages and drawbacks. We then 
 discuss more recent image compression formats such as JPEG 2000\, JPEG XR\
 , JPEG XS\, JPEG XT\, and JPEG XL\, along with motivations that led to the
 ir design and the added values they bring. The recent JPEG Pleno compressi
 on standard that allows efficient compression of new imaging modalities su
 ch as lightfield\, point cloud\, and holography is then discussed. Last bu
 t not least\, the role of machine learning and in particular the impact of
  the paradigm shift from humans as consumers of images and video\, to mach
 ines and computer vision systems\, will be discussed\, and emerging ideas 
 on how to design image compression based on deep learning will be presente
 d.
LOCATION:PPB 019
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR