BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190156Z
LOCATION:West Building\, Rooms 118-120
DTSTART;TZID=America/Los_Angeles:20250814T113500
DTEND;TZID=America/Los_Angeles:20250814T114500
UID:siggraph_SIGGRAPH 2025_sess141_papers_591@linklings.com
SUMMARY:Reenact Anything: Semantic Video Motion Transfer Using Motion-Text
 ual Inversion
DESCRIPTION:Manuel Kansy (ETH Zürich, Disney Research Studios); Jacek Naru
 niec and Christopher Schroers (Disney Research Studios); Markus Gross (ETH
  Zürich, Disney Research Studios); and Romann Weber (Disney Research Studi
 os)\n\nReenact Anything introduces a unified framework for semantic motion
  transfer, covering applications from full-body and face reenactment to co
 ntrolling the motion of inanimate objects and the camera. Thereby, motions
  are represented using text/image embeddings of an image-to-video diffusio
 n model and are optimized based on a given motion reference video.\n\nInte
 rest Area: Research & Education\n\nRecording: Livestreamed, Not Livestream
 ed, Recorded, Not Recorded\n\nRegistration Category: Full Conference, Virt
 ual Access, Thursday\n\nSession Chair: Nanxuan Zhao (Adobe Research)\n\n
END:VEVENT
END:VCALENDAR