BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20180325T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20171029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260407T163922Z
UID:5a61fee06cf92935166800@ist.ac.at
DTSTART:20180125T100000
DTEND:20180125T110000
DESCRIPTION:Speaker: Viktoriia Sharmanska\nhosted by Christoph Lampert\nAbs
 tract: Can we incorporate annotation disagreements of the crowdsourced dat
 a collection process?Can we make use of discarded features from filter/wra
 pper feature selection methods? Can we build an image classifier that can 
 incorporate knowledge from video data?Can we unify all the previous questi
 ons in a single joint learning framework?Yes\, we can\, the framework is c
 alled a Learning using Priviledged Information (LUPI).LUPI provides a mech
 anism to incorporate additional information that is only available at trai
 ning time\, annotation disagreements--discarded features--video dataset\, 
 into the learning process of a classifier. In this talk\, I will summarize
  our contributions to LUPI paradigm including a Bayesian and non-Bayesian 
 perspective of the LUPI  and its variety of applications in computer visio
 n and feature selection.
LOCATION:Mondi Seminar Room 3\, Central Building\, ISTA
ORGANIZER:abonvent@ist.ac.at
SUMMARY:Viktoriia Sharmanska: Learning beyond Label Annotations
URL:https://talks-calendar.ista.ac.at/events/1067
END:VEVENT
END:VCALENDAR