BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:US/Eastern
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250324T152137Z
UID:B55E4C15-400D-4401-B8E0-E4257289DD07
DTSTART;TZID=US/Eastern:20231030T180000
DTEND;TZID=US/Eastern:20231030T190000
DESCRIPTION:The [IEEE Long Island (LI) Signal Processing Society (SPS)](htt
 ps://ieee.li/society-chapters/signal-processing-society-sp/) in collaborat
 ion with [North Jersey Social Implications of Technology Society](https://
 r1.ieee.org/northjersey/chapter/ssit/) presents the following Distinguishe
 d Lecture:\n\nVideo analytics involves processing video content in real-ti
 me\, extracting metadata\, sending out alerts\, and delivering actionable 
 intelligence insights to security staff or other systems. Video analytics 
 products apply artificial intelligence to cameras to recognize temporal an
 d spatial events. Video analytics are needed in various end applications s
 uch as quality inspection\, industrial process automation\, and workplace 
 security. It is crucial to have video analytics performed at the edge on t
 he multiple streams from on-premises cameras to make automated predictions
  with high accuracy and low latency. This talk explains the co-design of h
 ardware friendly algorithms and corresponding domain specific accelerator 
 architectures for machine learning inference at the edge for video analyti
 cs.\n\nSpeaker(s): Dr. Kiran Gunnam\, \n\nAgenda: \nTechnical support set-
 up: 5:30pm EST\nIntroductions 6pm-6:05pm EST\nTechnical Lecture: 6:05pm-6:
 50pm EST\nQ&A: 6:50pm-7pm EST\n\nVirtual: https://events.vtools.ieee.org/m
 /369906
LOCATION:Virtual: https://events.vtools.ieee.org/m/369906
ORGANIZER:Signal@ieee.li
SEQUENCE:26
SUMMARY:Co-Design of Algorithms and Architectures for Machine Learning Infe
 rence at the Edge for Video Analytics
URL;VALUE=URI:https://events.vtools.ieee.org/m/369906
X-ALT-DESC:Description: <br /><p style="font-weight: 400\;">The <a href="ht
 tps://ieee.li/society-chapters/signal-processing-society-sp/">IEEE Long Is
 land (LI) Signal Processing Society (SPS)</a> in collaboration with <a hre
 f="https://r1.ieee.org/northjersey/chapter/ssit/">North Jersey Social Impl
 ications of Technology Society</a> presents the following Distinguished Le
 cture:</p>\n<p style="font-weight: 400\;">Video analytics involves process
 ing video content in real-time\, extracting metadata\, sending out alerts\
 , and delivering actionable intelligence insights to security staff or oth
 er systems. Video analytics products apply artificial intelligence to came
 ras to recognize temporal and spatial events. Video analytics are needed i
 n various end applications such as quality inspection\, industrial process
  automation\, and workplace security. It is crucial to have video analytic
 s performed at the edge on the multiple streams from on-premises cameras t
 o make automated predictions with high accuracy and low latency. This talk
  explains the co-design of hardware friendly algorithms and corresponding 
 domain specific accelerator architectures for machine learning inference a
 t the edge for video analytics.</p><br /><br />Agenda: <br /><p>Technical 
 support set-up: 5:30pm EST<br>Introductions 6pm-6:05pm EST<br>Technical Le
 cture: 6:05pm-6:50pm EST<br>Q&amp\;A: 6:50pm-7pm EST</p>
END:VEVENT
END:VCALENDAR