BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20151025T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20161030T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20160327T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.7296.field_data.0@oba.diag.uniroma1.it
DTSTAMP:20260405T004646Z
CREATED:20160503T152358Z
DESCRIPTION:While vital for handling most multimedia and computer vision pr
 oblems\, collecting large scale fully annotated data sets is a resource-co
 nsuming\, often unaffordable task.  In this context\, developing methodolo
 gical approaches able to deal with noisy and incomplete data sets is highl
 y desirable. Matrix completion is a generic framework aiming to recover a 
 matrix from a limited number of (noisy) entries. In this talk I will prese
 nt three recent approaches derived from the matrix completion paradigm to 
 address different visual tasks in the area of human behaviour understandin
 g.  First\, coupled matrix completion for the analysis of complex social s
 cenes. Second\, non-linear matrix completion to recognize emotions elicite
 d from  paintings. Third\, self-adaptive matrix completion for remote hear
 t-rate estimation from videos. 
DTSTART;TZID=Europe/Paris:20160509T110000
DTEND;TZID=Europe/Paris:20160509T110000
LAST-MODIFIED:20190805T155749Z
LOCATION:Room B203
SUMMARY:Elisa Ricci - Learning from noisy and missing data: introducing mat
 rix completion for human behaviour analysis from visual inputs - Dr. Elisa
  Ricci\, FBK Trento
URL;TYPE=URI:http://oba.diag.uniroma1.it/node/7296
END:VEVENT
END:VCALENDAR