BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//INFN-LNF - ECPv5.14.2.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:INFN-LNF
X-ORIGINAL-URL:/?lang=en
X-WR-CALDESC:Events for INFN-LNF
BEGIN:VTIMEZONE
TZID:Europe/Rome
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Rome:20250528T143000
DTEND;TZID=Europe/Rome:20250528T160000
DTSTAMP:20260422T041616
CREATED:20250313T091707Z
LAST-MODIFIED:20250313T091707Z
UID:39065-1748442600-1748448000@w3.lnf.infn.it
SUMMARY:Learning with uncertainty for computer vision
DESCRIPTION:Speaker: Fabio Galasso (Roma La Sapienza Univ.) \nRepresentation learning is an important part of modern computer vision. Literature assumes a default Euclidean space\, thus a manifold based on regular grids. Only most recently\, hyperbolic spaces have enabled techniques to reach and surpass the state-of-the-art\, supporting learning with hierarchical structures and uncertainty\, also a by-product of hyperbolic representation learning. I will introduce our most recent work that leverages Hyperbolic Neural Networks for anomaly detection\, self-supervised learning of actions\, active learning of semantic segmentation\, and reinforcement learning of robot navigation in social environments.
URL:https://w3.lnf.infn.it/event/learning-with-uncertainty-for-computer-vision/?lang=en
LOCATION:Aula Salvini
CATEGORIES:Seminari generali
END:VEVENT
END:VCALENDAR