BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.adass.org//adass2026//talk//Y8MJEQ
BEGIN:VTIMEZONE
TZID:AWST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20051231T160000Z
TZNAME:AWST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20070325T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:AWST
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20071028T030000
RRULE:FREQ=YEARLY;BYDAY=4SU;BYMONTH=10;UNTIL=20081025T190000Z
TZNAME:AWDT
TZOFFSETFROM:+0800
TZOFFSETTO:+0900
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-adass2026-Y8MJEQ@pretalx.adass.org
DTSTART;TZID=AWST:20261103T104800
DTEND;TZID=AWST:20261103T110000
DESCRIPTION:The next generation of radio astronomy telescopes\, including t
 he Square Kilometre Array (SKA)\, will generate unprecedented data volumes
 \, requiring highly automated and reliable approaches for source finding a
 nd catalogue construction. Existing neutral hydrogen (HI) source-finding m
 ethods\, including numerical algorithms and machine-learning approaches\, 
 have demonstrated strong performance but often rely on survey-specific pre
 processing\, parameter tuning\, or architectures that do not fully exploit
  the three-dimensional structure of spectral-line data. We present the HI 
 Segment Anything Model (HISAM)\, an automated image-to-catalogue pipeline 
 for HI source finding based on a pretrained three-dimensional large vision
  model. HISAM adapts a volumetric segmentation architecture to HI spectral
 -line cubes through domain-specific modifications and fine-tuning\, and in
 tegrates source segmentation with catalogue construction and false-positiv
 e rejection to transform input image cubes into science-ready source catal
 ogues. We evaluate HISAM on the SKA Science Data Challenge 2 simulation. H
 ISAM achieves competitive completeness and reliability for sources with su
 fficiently strong signals\, while its overall completeness decreases when 
 evaluated across the full source population.
DTSTAMP:20261116T154911Z
LOCATION:Seminar Room 2
SUMMARY:Image-to-Catalogue: End-to-End Source Finding with a 3D large visio
 n model - Li Wang
URL:https://pretalx.adass.org/adass2026/talk/Y8MJEQ/
END:VEVENT
END:VCALENDAR
