BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Artificial Intelligence Research Group Talks (Comp
 uter Laboratory)
SUMMARY:When Vision Transformers Meet Cooperative Percepti
 on - Runsheng Xu\, UCLA (USA)
DTSTART;TZID=Europe/London:20230131T130000
DTEND;TZID=Europe/London:20230131T140000
UID:TALK195346AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/195346
DESCRIPTION:"Join us on Zoom":https://zoom.us/j/99166955895?pw
 d=SzI0M3pMVEkvNmw3Q0dqNDVRalZvdz09\n\nAutonomous d
 riving perception systems are faced with significa
 nt challenges\, such as occlusion and sparse senso
 r observations at a distance. Cooperative percepti
 on\, which utilizes V2X communication to enable au
 tonomous vehicles to share visual information with
  each other\, presents a promising solution to the
 se challenges. In this seminar\, we will explore t
 he use of vision transformers in cooperative perce
 ption. Runsheng Xu will present his recent researc
 h on the topic\, including two papers: "V2X-ViT: V
 ehicle-to-Everything Cooperative Perception with V
 ision Transformer" (ECCV2022) and "CoBEVT: Coopera
 tive Bird's Eye View Semantic Segmentation with Sp
 arse Transformers" (CoRL2022). These papers demons
 trate the potential of vision transformers in solv
 ing domain-specific challenges in cooperative perc
 eption. Join us to gain a deeper understanding of 
 the current state of the art and future directions
  in autonomous driving perception.
LOCATION:Online (Zoom)
CONTACT:Mateja Jamnik
END:VEVENT
END:VCALENDAR