BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ITSERR - ECPv6.2.8.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.itserr.it
X-WR-CALDESC:Events for ITSERR
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Brussels
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20241125
DTEND;VALUE=DATE:20241129
DTSTAMP:20260428T073202
CREATED:20250327T075828Z
LAST-MODIFIED:20250327T075828Z
UID:1415-1732492800-1732838399@www.itserr.it
SUMMARY:BMVC 2024_The 35th British Machine Vision Conference
DESCRIPTION:Davide Caffagni (University of Modena and Reggio Emilia) participated in the 35th British Machine Vision Conference (BMVC)\, presenting the paper “Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization”\, co-authored with Nicholas Moratelli\, Marcella Cornia\, Lorenzo Baraldi\, and Rita Cucchiara (University of Modena and Reggio Emilia). \nThe paper introduces Direct CLIP-Based Optimization (DiCO)\, a novel training paradigm for image captioning that improves stability and enhances caption quality by optimizing modern metrics like CLIP-Score while maintaining fluency. The proposed approach outperforms existing methods in aligning with human preferences and generates more informative captions.
URL:https://www.itserr.it/event/bmvc-2024_the-35th-british-machine-vision-conference/
LOCATION:Glasgow\, United Kingdom
END:VEVENT
END:VCALENDAR