BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250512T162847Z
UID:5963FF95-1626-441E-9346-081A81675AC5
DTSTART;TZID=America/Los_Angeles:20250509T120000
DTEND;TZID=America/Los_Angeles:20250509T130000
DESCRIPTION:Visual signal coding involves a great number of complex and com
 putationally intensive decisions\, especially in modern standards such as 
 Versatile Video Coding (VVC)\, AOMedia Video 1 (AV1)\, and Video-based Poi
 nt Cloud Compression (V-PCC). As multimedia applications increasingly targ
 et energy-constrained devices\, reducing the computational and energy dema
 nds of coding systems becomes crucial. In this talk\, we present how machi
 ne learning techniques can be applied to accelerate decision processes and
  significantly reduce complexity in these advanced coding standards. The t
 alk will present examples in which trained models are implemented into bot
 h software codecs and hardware designs\, and demonstrate how they can be c
 ombined with low-power techniques such as operand isolation\, clock gating
 \, and approximate computing. The presented approaches aim to enable effic
 ient multimedia processing even under strict energy limitations.\n\nSpeake
 r(s): Guilherme Corrêa \n\nVirtual: https://events.vtools.ieee.org/m/4830
 53
LOCATION:Virtual: https://events.vtools.ieee.org/m/483053
ORGANIZER:vickyhlu@ieee.org
SEQUENCE:55
SUMMARY:IEEE SPS SCV - Complexity-Aware Visual Signal Coding: Learning-Base
 d Approaches for Energy Efficiency
URL;VALUE=URI:https://events.vtools.ieee.org/m/483053
X-ALT-DESC:Description: <br /><p class="p1">Visual signal coding involves a
  great number of complex and computationally intensive decisions\, especia
 lly in modern standards such as Versatile Video Coding (VVC)\, AOMedia Vid
 eo 1 (AV1)\, and Video-based Point Cloud Compression (V-PCC). As multimedi
 a applications increasingly target energy-constrained devices\, reducing t
 he computational and energy demands of coding systems becomes crucial. In 
 this talk\, we present how machine learning techniques can be applied to a
 ccelerate decision processes and significantly reduce complexity in these 
 advanced coding standards. The talk will present examples in which trained
  models are implemented into both software codecs and hardware designs\, a
 nd demonstrate how they can be combined with low-power techniques such as 
 operand isolation\, clock gating\, and approximate computing. The presente
 d approaches aim to enable efficient multimedia processing even under stri
 ct energy limitations.</p>
END:VEVENT
END:VCALENDAR