BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Turkey
BEGIN:DAYLIGHT
DTSTART:20380119T061407
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1
TZNAME:+03
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20160907T000000
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=1WE;BYMONTH=9
TZNAME:+03
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190324T125819Z
UID:67B9488B-6BA2-4D48-A94D-B34046999A9C
DTSTART;TZID=Turkey:20190315T133000
DTEND;TZID=Turkey:20190315T153000
DESCRIPTION:Speaker: Assoc. Prof. Selim Aksoy\, Bilkent University\n\nTopic
 : &quot;Weakly Supervised Learning Algorithms for Medical Imaging and Remote Se
 nsing Applications&quot;\n\nLocation: Middle East Technical University\, Ankara
 \, Turkey\n\nAbstract: Learning classifiers from large image sets has been
  a popular problem in computer vision and machine learning. The commonly e
 mployed supervised learning framework typically uses manually selected ima
 ge patches with no ambiguity regarding their class labels. However\, colle
 cting sufficiently large number of examples for classes with high within-c
 lass variance and low between-class variance is not always possible. We wi
 ll present weakly supervised learning algorithms for object recognition an
 d image classification tasks in medical imaging and remote sensing applica
 tions with data sets having both localization and labeling uncertainties.\
 n\nBio: Dr. Selim Aksoy received the B.S. degree from Middle East Technica
 l University in 1996\, and the M.S. and Ph.D. degrees from the University 
 of Washington\, Seattle\, USA\, in 1998 and 2001\, respectively. Since 200
 4\, he has been with the Department of Computer Engineering\, Bilkent Univ
 ersity\, where he is currently an Associate Professor. He spent 2013 as a 
 Visiting Associate Professor at the Department of Computer Science &amp; Engin
 eering\, University of Washington. His research interests include computer
  vision\, pattern recognition\, and machine learning with applications to 
 remote sensing and medical imaging. He received the Research Incentive Awa
 rd from the Prof. Dr. Mustafa Parlar Foundation in 2016\, the BAGEP Young 
 Scientist Award from the Science Academy Association in 2016\, the GEBIP O
 utstanding Young Scientist Award from the Turkish Academy of Sciences in 2
 015\, the Distinguished Teaching Award from Bilkent University in 2014\, a
  Fulbright Scholarship in 2013\, a Marie Curie Fellowship from the Europea
 n Commission in 2005\, and the CAREER Award from the Scientific and Techno
 logical Research Council of Turkey (TUBITAK) in 2004. He served as an Asso
 ciate Editor of Pattern Recognition Letters during 2009-2013.\n\nSpeaker(s
 ): Assoc. Prof. Selim Aksoy\, \n\nAnkara\, Ankara\, Türkiye
LOCATION:Ankara\, Ankara\, Türkiye
ORGANIZER:ozergul@metu.edu.tr
SEQUENCE:0
SUMMARY:IEEE AP/MTT/EMC/ED TURKEY CHAPTER SEMINAR SERIES -- SEMINAR 46
URL;VALUE=URI:https://events.vtools.ieee.org/m/196423
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;Speaker: Assoc. Prof. Selim Aksoy\, Bilken
 t University&lt;/p&gt;\n&lt;p&gt;Topic:&amp;nbsp\;&quot;Weakly Supervised Learning Algorithms f
 or Medical Imaging and Remote Sensing Applications&quot;&lt;/p&gt;\n&lt;p&gt;Location:&amp;nbsp
 \;Middle East Technical University\, Ankara\, Turkey&lt;/p&gt;\n&lt;p&gt;Abstract: Lea
 rning classifiers from large image sets has been a popular problem in comp
 uter vision and machine learning. The commonly employed supervised learnin
 g framework typically uses manually selected image patches with no ambigui
 ty regarding their class labels. However\, collecting sufficiently large n
 umber of examples for classes with high within-class variance and low betw
 een-class variance is not always possible. We will present weakly supervis
 ed learning algorithms for object recognition and image classification tas
 ks in medical imaging and remote sensing applications with data sets havin
 g both localization and labeling uncertainties.&lt;/p&gt;\n&lt;p&gt;Bio: Dr. Selim Aks
 oy received the B.S. degree from Middle East Technical University in 1996\
 , and the M.S. and Ph.D. degrees from the University of Washington\, Seatt
 le\, USA\, in 1998 and 2001\, respectively. Since 2004\, he has been with 
 the Department of Computer Engineering\, Bilkent University\, where he is 
 currently an Associate Professor. He spent 2013 as a Visiting Associate Pr
 ofessor at the Department of Computer Science &amp;amp\; Engineering\, Univers
 ity of Washington. His research interests include computer vision\, patter
 n recognition\, and machine learning with applications to remote sensing a
 nd medical imaging. He received the Research Incentive Award from the Prof
 . Dr. Mustafa Parlar Foundation in 2016\, the BAGEP Young Scientist Award 
 from the Science Academy Association in 2016\, the GEBIP Outstanding Young
  Scientist Award from the Turkish Academy of Sciences in 2015\, the Distin
 guished Teaching Award from Bilkent University in 2014\, a Fulbright Schol
 arship in 2013\, a Marie Curie Fellowship from the European Commission in 
 2005\, and the CAREER Award from the Scientific and Technological Research
  Council of Turkey (TUBITAK) in 2004. He served as an Associate Editor of 
 Pattern Recognition Letters during 2009-2013.&lt;/p&gt;
END:VEVENT
END:VCALENDAR

