Conference paper Open Access

Attention Mechanisms, Signal Encodings and Fusion Strategies for Improved Ad-hoc Video Search with Dual Encoding Networks

Galanopoulos, Damianos; Mezaris, Vasileios


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/4244549</identifier>
  <creators>
    <creator>
      <creatorName>Galanopoulos, Damianos</creatorName>
      <givenName>Damianos</givenName>
      <familyName>Galanopoulos</familyName>
      <affiliation>CERTH-ITI</affiliation>
    </creator>
    <creator>
      <creatorName>Mezaris, Vasileios</creatorName>
      <givenName>Vasileios</givenName>
      <familyName>Mezaris</familyName>
      <affiliation>CERTH-ITI</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Attention Mechanisms, Signal Encodings and Fusion Strategies for Improved Ad-hoc Video Search with Dual Encoding Networks</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>Video search</subject>
    <subject>Video retrieval</subject>
    <subject>Ad-hoc video search</subject>
    <subject>Deep learning</subject>
    <subject>Dual encoding network</subject>
    <subject>Attention mechanism</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-06-07</date>
  </dates>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4244549</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1145/3372278.3390737</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/retv-h2020</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://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 paper, the problem of unlabeled video retrieval using textual queries is addressed. We present an extended dual encoding network which makes use of more than one encodings of the visual and textual content, as well as two different attention mechanisms. The latter serve the purpose of highlighting temporal locations in every modality that can contribute more to effective retrieval. The different encodings of the visual and textual inputs, along with early/late fusion strategies, are examined for further improving performance. Experimental evaluations and comparisons with state-of-the-art methods document the merit of the proposed network.&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/H2020/780656/">780656</awardNumber>
      <awardTitle>Enhancing and Re-Purposing TV Content for Trans-Vector Engagement</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
148
51
views
downloads
Views 148
Downloads 51
Data volume 159.4 MB
Unique views 147
Unique downloads 50

Share

Cite as