BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212945Z
LOCATION:Mile High 4
DTSTART;TZID=America/Denver:20240731T111500
DTEND;TZID=America/Denver:20240731T112500
UID:siggraph_SIGGRAPH 2024_sess129_papers_323@linklings.com
SUMMARY:Flexible Motion In-betweening With Diffusion Models
DESCRIPTION:Setareh Cohan (University of British Columbia); Guy Tevet (Tel
  Aviv University); Daniele Reda (University of British Columbia); Xue Bin 
 Peng (Simon Fraser University, NVIDIA Research); and Michiel van de Panne 
 (University of British Columbia)\n\nWe introduce CondMDI, a simple and uni
 fied diffusion-based approach for text and keyframe guided motion in-betwe
 ening. CondMDI accommodates flexible keyframe placements and partial keyfr
 ames, generating high-quality and diverse motions coherent with the input 
 constraints. Evaluation on the HumanML3D dataset showcases CondMDI's effec
 tiveness on a diverse set of motion in-betweening tasks.\n\nInterest Area:
  Research & Education\n\nRecording: Livestreamed, Recorded\n\nKeyword: Ani
 mation\n\nRegistration Category: Full Conference, Full Conference Supporte
 r, Virtual Access, Exhibitor Full Conference, Wednesday\n\nSession Chair: 
 Libin Liu (Peking University)\n\n
END:VEVENT
END:VCALENDAR