BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030311Z
LOCATION:Chancellor 1+2\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251218T090000
DTEND;TZID=Asia/Hong_Kong:20251218T180000
UID:siggraphasia_SIGGRAPH Asia 2025_sess320_ipos_130@linklings.com
SUMMARY:IntentMotion: Learning Intent-Aware Human Motion from Language in 
 3D Scene
DESCRIPTION:Wenfeng Song and Shi Zheng (Computer School, Beijing Informati
 on Science and Technology University); Xinyu Zhang (State Key Laboratory o
 f Virtual Reality Technology and Systems, Beihang University); Xingliang J
 in (School of Computer Science and Technology, East China Normal Universit
 y); Aimin Hao (State Key Laboratory of Virtual Reality Technology and Syst
 ems, Beihang University); Fei Hou (Key Laboratory of System Software (CAS)
 , State Key Laboratory of Computer Science, Institute of Software, Chinese
  Academy of Sciences, China; University of Chinese Academy of Sciences, Ch
 ina); Xia Hou (Computer School, Beijing Information Science and Technology
  University); and Shuai Li (State Key Laboratory of Virtual Reality Techno
 logy and Systems, Beihang University; Zhongguancun Laboratory)\n\nIntentMo
 tion is a novel framework that generates human motion in 3D scenes from in
 structions. We first introduce the Intention-Guided Contact Field (IGCF), 
 which explicitly aligns parsed language roles with spatial contact regions
  through a hierarchical attention mechanism. IGCF is jointly trained with 
 a diffusion-based motion generator, allowing contact predictions to adapt 
 dynamically through gradient feedback. To improve the controllability and 
 physics-aware motion, we further propose an Intention-Aware Diffusion Mode
 l, which decouples the high-level semantic planning from the low-level con
 tact refinement. Contact cues are utilized to guide the synthesis of coars
 e trajectory, followed by refining detailed pose sequences under IGCF supe
 rvision.\n\nRegistration Category: Enhanced Access, Exhibit & Experience A
 ccess, Experience Hall Exhibitor, Full Access, Full Access Supporter, Trad
 e Exhibitor\n\n
END:VEVENT
END:VCALENDAR