Conference paper Open Access

ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO

Foteini Markatopoulou; Vasileios Mezaris; Ioannis Patras


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Concept detection</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Multi-task learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Video</subfield>
  </datafield>
  <controlfield tag="005">20190410034755.0</controlfield>
  <controlfield tag="001">159241</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">25-28 September 2016</subfield>
    <subfield code="g">ICIP 2016</subfield>
    <subfield code="a">IEEE International Conference on Image Processing</subfield>
    <subfield code="c">Phoenix Cinvention Center, Phoenix, Arizona 85004 USA</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute (ITI), CERTH</subfield>
    <subfield code="a">Vasileios Mezaris</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Queen Mary University of London</subfield>
    <subfield code="a">Ioannis Patras</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">632906</subfield>
    <subfield code="z">md5:2ea63812f644dee948985e9a549b2177</subfield>
    <subfield code="u">https://zenodo.org/record/159241/files/icip16_1_preprint.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">http://2016.ieeeicip.org/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2016-09-25</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-ecfunded</subfield>
    <subfield code="p">user-invid-h2020</subfield>
    <subfield code="o">oai:zenodo.org:159241</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute (ITI), CERTH, Queen Mary University of London</subfield>
    <subfield code="a">Foteini Markatopoulou</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ecfunded</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-invid-h2020</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">687786</subfield>
    <subfield code="a">In Video Veritas – Verification of Social Media Video Content for the News Industry</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;In this paper we propose an online multi-task learning algorithm for video concept detection. In particular, we extend the Efficient Lifelong Learning Algorithm (ELLA) in the following ways: a) we solve the objective function of ELLA using quadratic programming instead of solving the Lasso problem, b) we add a new label-based constraint that considers concept correlations, c) we use linear SVMs as base learners instead of logistic regression. Experimental results show improvement over both the single-task learning methods typically used in this problem and the original ELLA algorithm.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1109/ICIP.2016.7532344</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
39
19
views
downloads
Views 39
Downloads 19
Data volume 12.0 MB
Unique views 36
Unique downloads 19

Share

Cite as