BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:64663337-6438-4365-b462-393162386566
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Learning to Anticipate - Alex Schwing\, Assistant Professor\, 
 University of Illinois
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20211107T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20191103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20201101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20190310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20200308T020000
RDATE:20210314T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:5b8f8326-6ea1-40be-b018-ed63fc8f6f3b
DTSTAMP:20260426T011521Z
CLASS:PUBLIC
CREATED:20191212T182630Z
DESCRIPTION:Abstract: Despite significant progress in recent years\, autono
 mous agents like speakers or cars are far from participating robustly and 
 safely in our environment\, largely because they lack an ability to antici
 pate. We argue that this is due to four reasons: (1) holistic object reaso
 ning is still at its infancy\, e.g.\, because of occlusions\; (2) inferrin
 g of interactions between observed objects is hard because little data is 
 available\; (3) capturing of revealing real-world priors is challenging be
 cause of a high-dimensional setting\; and (4) understanding ambiguity is t
 ough due to an exponential…
DTSTART;TZID=America/Vancouver:20191216T150000
DTEND;TZID=America/Vancouver:20191216T160000
LAST-MODIFIED:20210611T165706Z
LOCATION:ICCS - X836\, ICICS Computer Science\, 2366 Main Mall\, Vancouver\
 , BC
SUMMARY:Learning to Anticipate - Alex Schwing\, Assistant Professor\, Unive
 rsity of Illinois
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/learning-anticipate-alex-schwing-assistant-p
 rofessor-university-illinois
END:VEVENT
END:VCALENDAR