Conference paper Open Access

Deep Multi-task Learning with Label Correlation Constraint for Video Concept Detection

Markatopoulou, Foteini; Mezaris, Vasileios; Patras, Ioannis


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; deep learning; video analysis</subfield>
  </datafield>
  <controlfield tag="005">20200120165925.0</controlfield>
  <controlfield tag="001">162404</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">October 2016</subfield>
    <subfield code="a">ACM Multimedia</subfield>
    <subfield code="c">Amsterdam</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CERTH</subfield>
    <subfield code="a">Mezaris, Vasileios</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">QMUL</subfield>
    <subfield code="a">Patras, Ioannis</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">433735</subfield>
    <subfield code="z">md5:a715e3e8d926a165019b1b350465caa1</subfield>
    <subfield code="u">https://zenodo.org/record/162404/files/mm16_1_preprint.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2016-10-17</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="p">user-moving-h2020</subfield>
    <subfield code="o">oai:zenodo.org:162404</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">CERTH</subfield>
    <subfield code="a">Markatopoulou, Foteini</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Deep Multi-task Learning with Label Correlation Constraint for Video Concept Detection</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="980" ind1=" " ind2=" ">
    <subfield code="a">user-moving-h2020</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">693092</subfield>
    <subfield code="a">Training towards a society of data-savvy information professionals to enable open leadership innovation</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">https://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 work we propose a method that integrates multi-task learning (MTL) and deep learning. Our method appends a MTL-like loss to a deep convolutional neural network, in order to learn the relations between tasks together at the same time, and also incorporates the label correlations between pairs of tasks. We apply the proposed method on a transfer learning scenario, where our objective is to fine-tune the parameters of a network that has been originally trained on a large-scale image dataset for concept detection, so that it be applied on a target video dataset and a corresponding new set of target concepts. We evaluate the proposed method for the video concept detection problem on the TRECVID 2013 Semantic Indexing dataset. Our results show that the proposed algorithm leads to better concept-based video annotation than existing state-of-the-art methods.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1145/2964284.2967271</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
123
59
views
downloads
Views 123
Downloads 59
Data volume 25.6 MB
Unique views 116
Unique downloads 58

Share

Cite as