Conference paper Open Access

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

Markatopoulou, Foteini; Mezaris, Vasileios; Patras, Ioannis


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://zenodo.org/record/162404</identifier>
  <creators>
    <creator>
      <creatorName>Markatopoulou, Foteini</creatorName>
      <givenName>Foteini</givenName>
      <familyName>Markatopoulou</familyName>
      <affiliation>CERTH</affiliation>
    </creator>
    <creator>
      <creatorName>Mezaris, Vasileios</creatorName>
      <givenName>Vasileios</givenName>
      <familyName>Mezaris</familyName>
      <affiliation>CERTH</affiliation>
    </creator>
    <creator>
      <creatorName>Patras, Ioannis</creatorName>
      <givenName>Ioannis</givenName>
      <familyName>Patras</familyName>
      <affiliation>QMUL</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Deep Multi-task Learning with Label Correlation Constraint for Video Concept Detection</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2016</publicationYear>
  <subjects>
    <subject>Concept detection; deep learning; video analysis</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2016-10-17</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/162404</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1145/2964284.2967271</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/ecfunded</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/invid-h2020</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/moving-h2020</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="http://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/693092/">693092</awardNumber>
      <awardTitle>Training towards a society of data-savvy information professionals to enable open leadership innovation</awardTitle>
    </fundingReference>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/687786/">687786</awardNumber>
      <awardTitle>In Video Veritas – Verification of Social Media Video Content for the News Industry</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
83
46
views
downloads
Views 83
Downloads 46
Data volume 20.0 MB
Unique views 80
Unique downloads 45

Share

Cite as