BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20250330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250911T103028Z
UID:435FAD53-2145-4770-95CB-EFDC28F2DE95
DTSTART;TZID=Europe/Berlin:20250904T150000
DTEND;TZID=Europe/Berlin:20250904T160000
DESCRIPTION:Title: Visual Data Compression in the AI Era\n\nAbstract: This 
 talk will delve into the evolution of visual data compression in recent ye
 ars\, spotlighting how compression techniques and AI models are integrated
  together. Traditionally\, image and video codecs such as JPEG\, HEVC\, an
 d AV1 are designed primarily for accurate pixel reconstruction. However\, 
 the advancement of AI technologies has begun transforming these frameworks
  to meet modern application demands. This talk will discuss such shift thr
 ough three lenses:\n- Compression with AI: enhance the coding performance 
 of compression algorithms with AI techniques. I will discuss the use of ge
 nerative AI models\, particularly variational autoencoders in lossy image 
 compression\, and their resemblance to traditional coding concepts such as
  transform coding\, and wavelet transform.\n- Compression for AI: design c
 ompression systems for AI-based recognition and processing (as opposed to 
 human viewing only). I will showcase potential real-world applications of 
 coding for machines and present several recent methods targeting mobile-cl
 oud systems.\n- Compression of AI: efficient compression of AI models to r
 educe computational costs. I will present pruning and quantization methods
  to address the challenges of compressing neural network-based codecs.\n\n
 Bio: Fengqing Maggie Zhu is an Associate Professor of the Elmore Family Sc
 hool of Electrical and Computer Engineering at Purdue University\, West La
 fayette\, Indiana. Dr. Zhu received the B.S.E.E. (with highest distinction
 )\, M.S. and Ph.D. degrees in Electrical and Computer Engineering from Pur
 due University in 2004\, 2006 and 2011\, respectively. Prior to joining Pu
 rdue in 2015\, she was a Staff Researcher at Futurewei Technologies\, wher
 e she received a Certification of Recognition for Core Technology Contribu
 tion in 2012. She is the recipient of an NSF CISE Research Initiation Init
 iative (CRII) award\, a Google Faculty Research Award\, and an ESI and tra
 inee poster award for the NIH Precision Nutrition workshop. Her group’s 
 work on visual coding for machines has received the Best Algorithms Paper 
 Award at the Winter Conference on Applications of Computer Vision (WACV) 2
 023 and the Best Paper Finalists at the Picture Coding Symposium (PCS) 202
 2. She is currently serving as the Vice Chair of the IEEE MMSP-TC (2025-20
 26) and an Elected Member of the IVMSP-TC (2025-2027). She is also an Asso
 ciate Editor for the IEEE Transactions on Multimedia (2025-2027). She has 
 served on the organizing and program committees of major conferences in he
 r field and received recognition such as the Outstanding Area Chair for IC
 ME 2021. Dr. Zhu is a senior member of the IEEE.\n\nVirtual: https://event
 s.vtools.ieee.org/m/497738
LOCATION:Virtual: https://events.vtools.ieee.org/m/497738
ORGANIZER:Ambarish.natu@gmail.com
SEQUENCE:15
SUMMARY:Visual Data Compression in the AI Era
URL;VALUE=URI:https://events.vtools.ieee.org/m/497738
X-ALT-DESC:Description: <br /><div><strong>Title: Visual Data Compression i
 n&nbsp\;the&nbsp\;AI Era</strong></div>\n<div>&nbsp\;</div>\n<div><strong>
 Abstract</strong>:&nbsp\;This talk will delve into&nbsp\;the&nbsp\;evoluti
 on of visual data compression in recent years\, spotlighting how compressi
 on techniques and AI models are integrated together. Traditionally\, image
  and video codecs such as JPEG\, HEVC\, and AV1 are designed primarily for
  accurate pixel reconstruction. However\,&nbsp\;the&nbsp\;advancement of A
 I technologies has begun transforming these frameworks to meet modern appl
 ication demands. This talk will discuss such shift through three lenses:&n
 bsp\;</div>\n<div>- Compression with AI: enhance&nbsp\;the&nbsp\;coding pe
 rformance of compression algorithms with AI techniques. I will discuss&nbs
 p\;the&nbsp\;use of generative AI models\, particularly variational autoen
 coders in lossy image compression\, and their resemblance to traditional c
 oding concepts such as transform coding\, and wavelet transform.</div>\n<d
 iv>- Compression for AI: design compression systems for AI-based recogniti
 on and processing (as opposed to human viewing only). I will showcase pote
 ntial real-world applications of coding for machines and present several r
 ecent methods targeting mobile-cloud systems.<br>- Compression of AI: effi
 cient compression of AI models to reduce computational costs. I will prese
 nt pruning and quantization methods to address&nbsp\;the&nbsp\;challenges 
 of compressing neural network-based codecs.&nbsp\;</div>\n<div>&nbsp\;</di
 v>\n<div><strong>Bio</strong>: Fengqing&nbsp\;Maggie&nbsp\;Zhu is an Assoc
 iate Professor of&nbsp\;the&nbsp\;Elmore Family School of Electrical and C
 omputer Engineering at Purdue University\, West Lafayette\, Indiana. Dr. Z
 hu received&nbsp\;the&nbsp\;B.S.E.E. (with highest distinction)\, M.S. and
  Ph.D. degrees in Electrical and Computer Engineering from Purdue Universi
 ty in 2004\, 2006 and 2011\, respectively. Prior to joining Purdue in 2015
 \, she was&nbsp\;a&nbsp\;Staff Researcher at Futurewei Technologies\, wher
 e she received&nbsp\;a&nbsp\;Certification of Recognition for Core Technol
 ogy Contribution in 2012. She is&nbsp\;the&nbsp\;recipient of an NSF CISE 
 Research Initiation Initiative (CRII) award\,&nbsp\;a&nbsp\;Google Faculty
  Research Award\, and an ESI and trainee poster award for&nbsp\;the&nbsp\;
 NIH Precision Nutrition workshop. Her group&rsquo\;s work on visual coding
  for machines has received&nbsp\;the&nbsp\;Best Algorithms Paper Award at&
 nbsp\;the&nbsp\;Winter Conference on Applications of Computer Vision (WACV
 ) 2023 and&nbsp\;the&nbsp\;Best Paper Finalists at&nbsp\;the&nbsp\;Picture
  Coding Symposium (PCS) 2022. She is currently serving as&nbsp\;the&nbsp\;
 Vice Chair of&nbsp\;the&nbsp\;IEEE MMSP-TC (2025-2026) and an Elected Memb
 er of&nbsp\;the&nbsp\;IVMSP-TC (2025-2027). She is also an Associate Edito
 r for&nbsp\;the&nbsp\;IEEE Transactions on Multimedia (2025-2027). She has
  served on&nbsp\;the&nbsp\;organizing and program committees of major conf
 erences in her field and received recognition such as&nbsp\;the&nbsp\;Outs
 tanding Area Chair for ICME 2021. Dr. Zhu is&nbsp\;a&nbsp\;senior member o
 f&nbsp\;the&nbsp\;IEEE.&nbsp\;</div>\n<p>&nbsp\;</p>
END:VEVENT
END:VCALENDAR