BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen - ECPv5.7.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
X-ORIGINAL-URL:https://www.greyc.fr
X-WR-CALDESC:évènements pour GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20231029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20230420T140000
DTEND;TZID=Europe/Paris:20230420T150000
DTSTAMP:20260509T135001
CREATED:20230413T065344Z
LAST-MODIFIED:20230413T065423Z
UID:11184-1681999200-1682002800@www.greyc.fr
SUMMARY:Séminaire IMAGE : « Visual attention : A tool for high-level image processing » (Alexandre Bruckert)
DESCRIPTION:Nous aurons le plaisir d’écouter Alexandre Bruckert \, post-doctorant au LS2N lab\, Nantes Université\, Polytech Nantes.\nIl donnera un séminaire IMAGE\, le jeudi 20 avril 2023\, à 14h00\, en salle de séminaire F-200.\nTitre : Visual attention : A tool for high-level image processing\nRésumé : \n\nVisual attention is the set of cognitive and biological mechanisms that we use in order to reduce the flow of visual information received and processed by our brains. More specifically\, we detect and recognize important areas of a visual stimulus\, and attend to those areas using a series of eye movements called a scanpath. Consequently\, being able to characterise the effect of a stimulus on visual attention is of great interest for high-level image processing. \nIn this presentation\, I will present several ways in which visual attention can be estimated\, with a particular focus on the deployment of attention on 3D meshes and volumetric objects. I will also present a few applications of these models\, in image compression or quality assessement for instance. \nFinally\, this cognitive mechanism is also the source of inspiration of the attention mechanisms in artificial neural networks. I will discuss the possible interactions between eye-tracking data and deep computer vision models\, with a particular interest in the Learning Using Privileged Information (LUPI) paradigm.
URL:https://www.greyc.fr/event/seminaire-image-visual-attention-a-tool-for-high-level-image-processing-alexandre-bruckert/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:Seminaire Image
END:VEVENT
END:VCALENDAR