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:20250110T023314Z
LOCATION:G409\, G Block\, Level 4
DTSTART;TZID=Asia/Tokyo:20241206T140000
DTEND;TZID=Asia/Tokyo:20241206T160000
UID:siggraphasia_SIGGRAPH Asia 2024_sess320_ET105@linklings.com
SUMMARY:[IMAGICA GROUP] Real-time sensor analysis with Machine Learning , 
 AI and Computer Vision
DESCRIPTION:Exhibitor Talks\n\nSuki Samra and Mehar Samra (Photron USA Inc
 .); Jun Kubota (IMAGICA GROUP Inc., Photron Ltd.); Ippei Otake (Nara Insti
 tute of Science and Technology (NAIST)); and Akinobu Maejima (OLM Digital,
  Inc.; IMAGICA GROUP Inc.)\n\nPresentation 1:\nPresentation Title: Infiniw
 orkflow: AI Vision Powered Imaging Platform\nPresentation Description:\nIn
 troduction and live demo of Infiniworkflow showing rapid prototyping of wo
 rkflows for building machine learning model, performing real-time inferenc
 e and combining with image processing and computer vision algorithms - all
  with no coding and done with high performance GPU/Cloud backend.\n\nPrese
 ntation 2:\nPresentation Title: Low latency pose estimation with event cam
 era for interactive VFX\nPresentation Description:\nWhen human pose estima
 tion using a frame-based camera is performed in an online process during a
 ctual human motion, the latency of the estimation process causes a decreas
 e in pose accuracy with real-time pose and estimation's runtime and camera
  framerate limit the time resolution of pose output. We will introduce pos
 e updating using an event-based camera that can solve this latency and fra
 me rate problem in the same workflow. This method computes differences seq
 uentially as needed by computing sequential update vectors adapted to the 
 motion magnitude, and achieves framerate improvement by immediate update o
 f the estimated pose using the computed differences, and latency compensat
 ion by multi-step immediate update. We will also introduce our experiment 
 in a real live scene. Our method was performed in a real live scene with d
 ancers, and it shows that real-time display of visual effect is possible. 
 Also showed that the proposed method compensates latency and improves fram
 erate via pose evaluation.\n\nRegistration Category: Enhanced Access, Exhi
 bit & Experience Access, Experience Hall Exhibitor, Full Access, Full Acce
 ss Supporter, Trade Exhibitor\n\nLanguage Format: English Language, AI Tra
 nslation Multi-Language
URL:https://asia.siggraph.org/2024/program/?id=ET105&sess=sess320
END:VEVENT
END:VCALENDAR