BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T135600
DTEND;TZID=Asia/Tokyo:20241205T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess132_papers_725@linklings.com
SUMMARY:Body Gesture Generation for Multimodal Conversational Agents
DESCRIPTION:Technical Papers\n\nSunwoo Kim, Minwook Chang, and Yoonhee Kim
  (NCSOFT) and Jehee Lee (Seoul National University)\n\nCreating intelligen
 t virtual agents with realistic conversational abilities necessitates a mu
 ltimodal communication approach extending beyond text. Body gestures, in p
 articular, play a pivotal role in delivering a lifelike user experience by
  providing additional context, such as agreement, confusion, and emotional
  states. This paper introduces an\nintegration of motion matching framewor
 k with a learning-based approach for generating gestures, suitable for mul
 timodal, real-time, interactive conversational agents mimicking natural hu
 man discourse. Our gesture generation framework enables accurate synchroni
 zation with both the rhythm and semantics of spoken language accompanied b
 y multimodal perceptual cues. It also incorporates gesture phasing theory 
 from social studies to maintain critical gesture features while ensuring a
 gile responses to unexpected interruptions and barging-in situations. Our 
 system demonstrates responsiveness, fluidity, and quality beyond tradition
 al turn-based gesture-generation methods.\n\nRegistration Category: Full A
 ccess, Full Access Supporter\n\nLanguage Format: English Language\n\nSessi
 on Chair: Yi Zhou (Adobe)
URL:https://asia.siggraph.org/2024/program/?id=papers_725&sess=sess132
END:VEVENT
END:VCALENDAR