<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-02903209</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-10T14:29:44+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Multi-modal Transformer for Video Retrieval</title>
            <author role="aut">
              <persName>
                <forename type="first">Valentin</forename>
                <surname>Gabeur</surname>
              </persName>
              <idno type="halauthorid">1633145-0</idno>
              <affiliation ref="#struct-1067171"/>
              <affiliation ref="#struct-1043084"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Chen</forename>
                <surname>Sun</surname>
              </persName>
              <idno type="halauthorid">1149611-0</idno>
              <affiliation ref="#struct-1067171"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Karteek</forename>
                <surname>Alahari</surname>
              </persName>
              <email type="md5">8b5821932295a105b3d46a223982bb86</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">karteek</idno>
              <idno type="idhal" notation="numeric">19670</idno>
              <idno type="halauthorid" notation="string">27319-19670</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1838-5936</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=qcyG7rwAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/196283892</idno>
              <affiliation ref="#struct-1043084"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cordelia</forename>
                <surname>Schmid</surname>
              </persName>
              <email type="md5">2d066eaf116a4f83d50c1c2f6cc1b77c</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">831154</idno>
              <idno type="halauthorid" notation="string">119565-831154</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-1067171"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>THOTH</forename>
                <surname>Team</surname>
              </persName>
              <email type="md5">413829dab28a0224ec5dc6d17391bece</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-47752"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-07-20 17:55:19</date>
              <date type="whenModified">2025-10-27 11:00:01</date>
              <date type="whenReleased">2020-07-21 08:47:21</date>
              <date type="whenProduced">2020-08-23</date>
              <date type="whenEndEmbargoed">2020-07-20</date>
              <ref type="file" target="https://inria.hal.science/hal-02903209v1/document">
                <date notBefore="2020-07-20"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-02903209v1/file/main.pdf" id="file-2903209-2554165">
                <date notBefore="2020-07-20"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2007.10639"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="156804">
                <persName>
                  <forename>THOTH</forename>
                  <surname>Team</surname>
                </persName>
                <email type="md5">413829dab28a0224ec5dc6d17391bece</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02903209</idno>
            <idno type="halUri">https://inria.hal.science/hal-02903209</idno>
            <idno type="halBibtex">gabeur:hal-02903209</idno>
            <idno type="halRefHtml">&lt;i&gt;ECCV 2020 - European Conference on Computer Vision&lt;/i&gt;, Aug 2020, Glasgow, United Kingdom. pp.214-229, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-030-58548-8_13"&gt;&amp;#x27E8;10.1007/978-3-030-58548-8_13&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">ECCV 2020 - European Conference on Computer Vision, Aug 2020, Glasgow, United Kingdom. pp.214-229, &amp;#x27E8;10.1007/978-3-030-58548-8_13&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2903209-2554165"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="INRIA-RHA">INRIA Grenoble - Rhône-Alpes</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LJK">Laboratoire Jean Kuntzmann</idno>
            <idno type="stamp" n="LJK_GI" corresp="LJK">Département Géométrie et Images</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LJK-GI-THOTH" corresp="LJK_GI">Apprentissage de modèles visuels à partir de données massives</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ANR-IA-18" corresp="ANR-IA">ANR-IA-18</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Multi-modal Transformer for Video Retrieval</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Valentin</forename>
                    <surname>Gabeur</surname>
                  </persName>
                  <idno type="halauthorid">1633145-0</idno>
                  <affiliation ref="#struct-1067171"/>
                  <affiliation ref="#struct-1043084"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Chen</forename>
                    <surname>Sun</surname>
                  </persName>
                  <idno type="halauthorid">1149611-0</idno>
                  <affiliation ref="#struct-1067171"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Karteek</forename>
                    <surname>Alahari</surname>
                  </persName>
                  <email type="md5">8b5821932295a105b3d46a223982bb86</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">karteek</idno>
                  <idno type="idhal" notation="numeric">19670</idno>
                  <idno type="halauthorid" notation="string">27319-19670</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1838-5936</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=qcyG7rwAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/196283892</idno>
                  <affiliation ref="#struct-1043084"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cordelia</forename>
                    <surname>Schmid</surname>
                  </persName>
                  <email type="md5">2d066eaf116a4f83d50c1c2f6cc1b77c</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">831154</idno>
                  <idno type="halauthorid" notation="string">119565-831154</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-1067171"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ECCV 2020 - European Conference on Computer Vision</title>
                  <date type="start">2020-08-23</date>
                  <date type="end">2020-08-28</date>
                  <settlement>Glasgow</settlement>
                  <country key="GB">United Kingdom</country>
                </meeting>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="serie">Lecture Notes in Computer Science</biblScope>
                  <biblScope unit="volume">12349</biblScope>
                  <biblScope unit="pp">214-229</biblScope>
                  <date type="datePub">2020-10-29</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-030-58548-8_13</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">attention</term>
                <term xml:lang="en">transformer</term>
                <term xml:lang="en">temporality</term>
                <term xml:lang="en">cross-modal</term>
                <term xml:lang="en">multi-modal</term>
                <term xml:lang="en">retrieval</term>
                <term xml:lang="en">language</term>
                <term xml:lang="en">video</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cv">Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The task of retrieving video content relevant to natural language queries plays a critical role in effectively handling internet-scale datasets. Most of the existing methods for this caption-to-video retrieval problem do not fully exploit cross-modal cues present in video. Furthermore, they aggregate per-frame visual features with limited or no temporal information. In this paper, we present a multi-modal transformer to jointly encode the different modalities in video, which allows each of them to attend to the others. The transformer architecture is also leveraged to encode and model the temporal information. On the natural language side, we investigate the best practices to jointly optimize the language embedding together with the multi-modal transformer. This novel framework allows us to establish state-of-the-art results for video retrieval on three datasets. More details are available at http://thoth.inrialpes.fr/research/MMT.</p>
            </abstract>
            <particDesc>
              <org type="consortium">ANR-18-CE23-0011</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-1067171" status="VALID">
          <orgName>Google France</orgName>
          <desc>
            <address>
              <addrLine>8 Rue de Londres, 75009 Paris</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1043084" status="VALID">
          <idno type="IdRef">242196691</idno>
          <idno type="RNSR">201622034K</idno>
          <idno type="ROR">https://ror.org/02a2awp29</idno>
          <orgName>Apprentissage de modèles à partir de données massives</orgName>
          <orgName type="acronym">Thoth</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/thoth</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2497" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-1043077" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2497" status="VALID">
          <idno type="RNSR">199218244V</idno>
          <idno type="ROR">https://ror.org/00n8d6z93</idno>
          <orgName>Centre Inria de l'Université Grenoble Alpes</orgName>
          <desc>
            <address>
              <addrLine>Inovallée655 avenue de l'Europe38330 Montbonnot</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/grenoble</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1043077" status="VALID">
          <idno type="IdRef">184945011</idno>
          <idno type="ISNI">0000 0004 0383 676X</idno>
          <idno type="RNSR">200711891Z</idno>
          <idno type="ROR">https://ror.org/04ett5b41</idno>
          <orgName>Laboratoire Jean Kuntzmann</orgName>
          <orgName type="acronym">LJK</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment IMAG, CS 40700, F-38058 Grenoble Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://ljk.imag.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="direct"/>
            <relation active="#struct-1042703" type="direct"/>
            <relation active="#struct-1043329" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-1042703" status="VALID">
          <idno type="IdRef">240648315</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes</orgName>
          <orgName type="acronym">UGA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse CS 40700 - 38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-grenoble-alpes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1043329" status="VALID">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042703" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-47752" status="VALID">
          <idno type="anr">ANR-18-CE23-0011</idno>
          <orgName>AVENUE</orgName>
          <desc>Réseau de mémoire visuelle pour l'interprétation de scènes</desc>
          <date type="start">2018</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>