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:20240214T070311Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T174500
DTEND;TZID=Australia/Melbourne:20231213T183700
UID:siggraphasia_SIGGRAPH Asia 2023_sess147@linklings.com
SUMMARY:Technoscape
DESCRIPTION:Technical Communications, Technical Papers\n\nWhat is the Best
  Automated Metric for Text to Motion Generation?\n\nThere is growing inter
 est in generating skeleton-based human motions from natural language descr
 iptions. While most efforts have focused on developing better neural archi
 tectures for this task, there has been no significant work on determining 
 the proper evaluation metric. Human evaluation is the ul...\n\n\nJordan Vo
 as, Yili Wang, Qixing Huang, and Raymond Mooney (University of Texas at Au
 stin)\n---------------------\nTraining Orchestral Conductors in Beating Ti
 me\n\nA prototype to train orchestral conductors in how to beat time. The 
 key detection points are maxima in acceleration. We successfuly tested wit
 h five conductors with dramatically different styles.\n\n\nNeil A. Dodgson
  and Kathleen Griffin (Victoria University of Wellington)\n---------------
 ------\nA Motion-Simulation Platform to Generate Synthetic Motion Data for
  Computer Vision Tasks\n\nOur Motion-Simulation Platform runs in a game en
 gine, extracting RGB imagery and intrinsic motion data, benefiting motion-
 related computer vision tasks. Users and AI-bots can navigate to collect m
 otion data.\n\n\nAndrew Chalmers (Victoria University of Wellington, Compu
 tational Media Innovation Centre); Junhong Zhao (Victoria University of We
 llington); Weng Khuan Hoh, James Drown, and Simon Finnie (Victoria Univers
 ity of Wellington, Computational Media Innovation Centre); Richard Yao, Ja
 mes Lin, James Wilmott, and Arindam Dey (Meta Platforms, Inc.); Mark Billi
 nghurst (University of Auckland); and Taehyun Rhee (Victoria University of
  Wellington, Computational Media Innovation Centre)\n---------------------
 \nVR-NeRF: High-Fidelity Virtualized Walkable Spaces\n\nWe present an end-
 to-end system for the high-fidelity capture, model reconstruction and real
 -time rendering of walkable spaces in virtual reality using neural radianc
 e fields. To this end, we designed and built a custom multi-camera rig to 
 densely capture walkable spaces in high fidelity with multi-...\n\n\nLinni
 ng Xu (The Chinese University of Hong Kong, Meta); Vasu Agrawal, William L
 aney, Tony Garcia, Aayush Bansal, Changil Kim, Samuel Rota Bulň, Lorenzo P
 orzi, Peter Kontschieder, and Aljaž Božič (Meta); Dahua Lin (The Chinese U
 niversity of Hong Kong); and Michael Zollhoefer and Christian Richardt (Me
 ta)\n---------------------\nInteractive Material Annotation on 3D Scanned 
 Models leveraging Color-Material Correlation\n\nThis paper proposes an int
 eractive system for efficient material annotation on 3D scanned models. Fo
 cusing on the correlation between color and material distribution, we impl
 emented a two-step annotation workflow.\n\n\nWataru Kawabe (University of 
 Tokyo), Taisuke Hashimoto and Fabrice Matulic (Preferred Networks), Takeo 
 Igarashi (University of Tokyo), and Keita Higuchi (Preferred Networks)\n--
 -------------------\nFootstep Detection for Film Sound Production\n\nA met
 hod for footstep detection with good generalization and high accuracy is p
 roposed in this paper. Based on it, a footstep detection system was design
 ed for film sound production.\n\n\nXiaojuan Gu, JunLiang Chen, Bo Li, and 
 Jun Chen (Beijing Film Academy)\n\nRegistration Category: Full Access\n\nS
 ession Chair: Sheng Li (Peking University)
END:VEVENT
END:VCALENDAR