BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.coscup.org//coscup-2026//speaker//KRN3BV
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-coscup-2026-7JPPXJ@pretalx.coscup.org
DTSTART;TZID=CST:20260809T133500
DTEND;TZID=CST:20260809T140500
DESCRIPTION:In practical artificial intelligence development\, while model 
 design is important\, project success often depends more on data annotatio
 n workflows\, toolchain integration\, and engineering deployment. This tal
 k draws on my real-world contributions to the open-source annotation tool 
 Labelme\, showing how practical user needs led to multilingual localizatio
 n and feature improvements\, as well as the technical trade-offs involved 
 in collaborating with upstream maintainers and the community. Building on 
 this experience\, the session explores how open-source tools help bridge A
 I research and real-world applications\, highlighting challenges such as d
 ata quality and privacy in medical image segmentation and data distributio
 n shifts and real-time requirements in multi-site industrial vision deploy
 ment. Through cross-domain case studies\, it emphasizes the critical role 
 of open-source tooling in modern AI workflows and demonstrates how address
 ing real problems through community collaboration can effectively support 
 engineering practice in medical and industrial AI systems.
DTSTAMP:20260713T132624Z
LOCATION:RB105
SUMMARY:From Annotation Tools to Real-World AI: My Open-Source Journey with
  Labelme\, Medical Imaging\, and Industrial Vision - Kan (Koala)
URL:https://pretalx.coscup.org/coscup-2026/talk/7JPPXJ/
END:VEVENT
END:VCALENDAR