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:20260114T163732Z
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:Footstep Detection for Film Sound Production\n\nA method for f
 ootstep detection with good generalization and high accuracy is proposed i
 n this paper. Based on it, a footstep detection system was designed for fi
 lm sound production.\n\n\nXiaojuan Gu, JunLiang Chen, Bo Li, and Jun Chen 
 (Beijing Film Academy)\n---------------------\nInteractive Material Annota
 tion on 3D Scanned Models leveraging Color-Material Correlation\n\nThis pa
 per proposes an interactive system for efficient material annotation on 3D
  scanned models. Focusing on the correlation between color and material di
 stribution, we implemented a two-step annotation workflow.\n\n\nWataru Kaw
 abe (University of Tokyo), Taisuke Hashimoto and Fabrice Matulic (Preferre
 d Networks), Takeo Igarashi (University of Tokyo), and Keita Higuchi (Pref
 erred Networks)\n---------------------\nA Motion-Simulation Platform to Ge
 nerate Synthetic Motion Data for Computer Vision Tasks\n\nOur Motion-Simul
 ation Platform runs in a game engine, extracting RGB imagery and intrinsic
  motion data, benefiting motion-related computer vision tasks. Users and A
 I-bots can navigate to collect motion data.\n\n\nAndrew Chalmers (Victoria
  University of Wellington, Computational Media Innovation Centre); Junhong
  Zhao (Victoria University of Wellington); Weng Khuan Hoh, James Drown, an
 d Simon Finnie (Victoria University of Wellington, Computational Media Inn
 ovation Centre); Richard Yao, James Lin, James Wilmott, and Arindam Dey (M
 eta Platforms, Inc.); Mark Billinghurst (University of Auckland); and Taeh
 yun Rhee (Victoria University of Wellington, Computational Media Innovatio
 n Centre)\n---------------------\nWhat is the Best Automated Metric for Te
 xt to Motion Generation?\n\nThere is growing interest in generating skelet
 on-based human motions from natural language descriptions. While most effo
 rts have focused on developing better neural architectures for this task, 
 there has been no significant work on determining the proper evaluation me
 tric. Human evaluation is the ul...\n\n\nJordan Voas, Yili Wang, Qixing Hu
 ang, and Raymond Mooney (University of Texas at Austin)\n-----------------
 ----\nTraining Orchestral Conductors in Beating Time\n\nA prototype to tra
 in orchestral conductors in how to beat time. The key detection points are
  maxima in acceleration. We successfuly tested with five conductors with d
 ramatically different styles.\n\n\nNeil A. Dodgson and Kathleen Griffin (V
 ictoria University of Wellington)\n---------------------\nVR-NeRF: High-Fi
 delity 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 radiance fields. To this 
 end, we designed and built a custom multi-camera rig to densely capture wa
 lkable spaces in high fidelity with multi-...\n\n\nLinning Xu (The Chinese
  University of Hong Kong, Meta); Vasu Agrawal, William Laney, Tony Garcia,
  Aayush Bansal, Changil Kim, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontsc
 hieder, and Aljaž Božič (Meta); Dahua Lin (The Chinese University of Hong 
 Kong); and Michael Zollhoefer and Christian Richardt (Meta)\n\nRegistratio
 n Category: Full Access\n\nSession Chair: Sheng Li (Peking University)
END:VEVENT
END:VCALENDAR