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:20260817T171534Z
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:Sunwoo Kim, Minwook Chang, and Yoonhee Kim (NCSOFT) and Jehee 
 Lee (Seoul National University)\n\nCreating intelligent virtual agents wit
 h realistic conversational abilities necessitates a multimodal communicati
 on approach extending beyond text. Body gestures, in particular, play a pi
 votal role in delivering a lifelike user experience by providing additiona
 l context, such as agreement, confusion, and emotional states. This paper 
 introduces an\nintegration of motion matching framework with a learning-ba
 sed approach for generating gestures, suitable for multimodal, real-time, 
 interactive conversational agents mimicking natural human discourse. Our g
 esture generation framework enables accurate synchronization with both the
  rhythm and semantics of spoken language accompanied by multimodal percept
 ual cues. It also incorporates gesture phasing theory from social studies 
 to maintain critical gesture features while ensuring agile responses to un
 expected interruptions and barging-in situations. Our system demonstrates 
 responsiveness, fluidity, and quality beyond traditional turn-based gestur
 e-generation methods.\n\nRegistration Category: Full Access, Full Access S
 upporter\n\nLanguage Format: English Language\n\nSession Chair: Yi Zhou (R
 oblox)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_725&sess=sess132
END:VEVENT
END:VCALENDAR