BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070241Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_486@linklings.com
SUMMARY:Neural Motion Graph
DESCRIPTION:Technical Papers\n\nHongyu Tao, Shuaiying Hou, Changqing Zou, 
 Hujun Bao, and Weiwei Xu (Zhejiang University)\n\nDeep learning techniques
  have been employed to design a controllable human motion synthesizer. Des
 pite their potential, however, designing a neural network-based motion syn
 thesis that enables flexible user interaction, fine-grained controllabilit
 y, and the support of new types of motions at reduced time and space consu
 mption costs remains a challenge. In this paper, we propose a novel approa
 ch, a neural motion graph, that addresses the challenge by enabling scalab
 ility to new motions while using compact neural networks. Our approach rep
 resents each type of motion with a separate neural node to reduce the cost
  of adding new motion types. In addition, designing a separate neural node
  for each motion type enables task-specific control strategies and has gre
 ater potential to achieve a high-quality synthesis of complex motions, suc
 h as the Mongolian dance. Furthermore, a single transition network, which 
 acts as neural edges, is used to model the transition between two motion n
 odes. The transition network is designed with a lightweight control module
  to achieve a fine-grained response to user control signals. Overall, the 
 design choice makes the neural motion graph highly controllable and scalab
 le. In addition to being fully flexible to user interaction through high-l
 evel and fine-grained user-control signals, our experimental and subjectiv
 e evaluation results demonstrate that our proposed approach, neural motion
  graph, outperforms state-of-the-art human motion synthesis methods in ter
 ms of the quality of controlled motion generation.\n\nRegistration Categor
 y: Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Exhibito
 r
URL:https://asia.siggraph.org/2023/full-program?id=papers_486&sess=sess209
END:VEVENT
END:VCALENDAR