BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260310T071436Z
UID:https://www.biblhertz.it/events/31160/2648208
DTSTART:20220511T140000Z
DTEND:20220511T153000Z
CLASS:PUBLIC
CREATED:20220429T102022Z
DESCRIPTION:Recent progress in the Computer Vision and Natural Language Pro
 cessing communities have made it possible to connect Vision and Language t
 ogether in a variety of different tasks which lie at the intersection of V
 ision\, Language\, and Embodied AI. Those tasks range from retrieving imag
 es or part of images given textual queries\, to generating meaningful desc
 riptions of images\, answering questions and navigating agents in unseen e
 nvironments via natural language instructions.\nVortragender: Lorenzo Bara
 ldi
LAST-MODIFIED:20250113T112719Z
LOCATION:Villino Stroganoff\, Via Gregoriana 22\, 00187 Rom
SUMMARY:Research Seminar: Multimodal and Embodied AI for Digital Humanities
URL;VALUE=URI:https://www.biblhertz.it/events/31160/2648208
END:VEVENT
END:VCALENDAR