<?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-03555705</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="2026-05-17T14:23:25+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">2D Deep Video Capsule Network with Temporal Shift for Action Recognition</title>
            <author role="aut">
              <persName>
                <forename type="first">Theo</forename>
                <surname>Voillemin</surname>
              </persName>
              <idno type="halauthorid">2419645-0</idno>
              <affiliation ref="#struct-1076752"/>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hazem</forename>
                <surname>Wannous</surname>
              </persName>
              <idno type="halauthorid">409207-0</idno>
              <affiliation ref="#struct-1076752"/>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Philippe</forename>
                <surname>Vandeborre</surname>
              </persName>
              <email type="md5">22a9c906258e44dbb0b5830b22cf3450</email>
              <email type="domain">univ-lille.fr</email>
              <idno type="idhal" notation="string">vandeborre</idno>
              <idno type="idhal" notation="numeric">1166</idno>
              <idno type="halauthorid" notation="string">35611-1166</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2056-8675</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=myhkjkwAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/069896127</idno>
              <affiliation ref="#struct-1076752"/>
              <affiliation ref="#struct-410272"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Jean-Philippe</forename>
                <surname>Vandeborre</surname>
              </persName>
              <email type="md5">5a07885f5098d880beb97b6b70f860ce</email>
              <email type="domain">imt-nord-europe.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-02-03 17:31:27</date>
              <date type="whenModified">2026-02-07 05:22:43</date>
              <date type="whenReleased">2022-02-16 11:18:53</date>
              <date type="whenProduced">2021-01-10</date>
              <date type="whenEndEmbargoed">2022-02-03</date>
              <ref type="file" target="https://hal.science/hal-03555705v1/document">
                <date notBefore="2022-02-03"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03555705v1/file/ICPR2020-TVoillemin.pdf" id="file-3555707-3128354">
                <date notBefore="2022-02-03"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="148330">
                <persName>
                  <forename>Jean-Philippe</forename>
                  <surname>Vandeborre</surname>
                </persName>
                <email type="md5">5a07885f5098d880beb97b6b70f860ce</email>
                <email type="domain">imt-nord-europe.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03555705</idno>
            <idno type="halUri">https://hal.science/hal-03555705</idno>
            <idno type="halBibtex">voillemin:hal-03555705</idno>
            <idno type="halRefHtml">&lt;i&gt;25th International Conference on Pattern Recognition (ICPR 2020)&lt;/i&gt;, Jan 2021, Milan (en ligne), Italy. pp.3513-3519, &lt;a target="_blank" href="https://dx.doi.org/10.1109/ICPR48806.2021.9412983"&gt;&amp;#x27E8;10.1109/ICPR48806.2021.9412983&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">25th International Conference on Pattern Recognition (ICPR 2020), Jan 2021, Milan (en ligne), Italy. pp.3513-3519, &amp;#x27E8;10.1109/ICPR48806.2021.9412983&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3555707-3128354"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="CRISTAL-MINT" corresp="CRISTAL">CRISTAL-MINT</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="IMT-NORD-EUROPE" corresp="INSTITUT-MINES-TELECOM">IMT Nord Europe</idno>
            <idno type="stamp" n="CERI-SN" corresp="IMT-NORD-EUROPE">Centre d’Enseignement, de Recherche et d’Innovation Systèmes Numériques (CERI SN)</idno>
            <idno type="stamp" n="INSTITUT-MINES-TELECOM">Institut Mines Telecom</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">2D Deep Video Capsule Network with Temporal Shift for Action Recognition</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Theo</forename>
                    <surname>Voillemin</surname>
                  </persName>
                  <idno type="halauthorid">2419645-0</idno>
                  <affiliation ref="#struct-1076752"/>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hazem</forename>
                    <surname>Wannous</surname>
                  </persName>
                  <idno type="halauthorid">409207-0</idno>
                  <affiliation ref="#struct-1076752"/>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Philippe</forename>
                    <surname>Vandeborre</surname>
                  </persName>
                  <email type="md5">22a9c906258e44dbb0b5830b22cf3450</email>
                  <email type="domain">univ-lille.fr</email>
                  <idno type="idhal" notation="string">vandeborre</idno>
                  <idno type="idhal" notation="numeric">1166</idno>
                  <idno type="halauthorid" notation="string">35611-1166</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2056-8675</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=myhkjkwAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/069896127</idno>
                  <affiliation ref="#struct-1076752"/>
                  <affiliation ref="#struct-410272"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">CERI SN</idno>
                <meeting>
                  <title>25th International Conference on Pattern Recognition (ICPR 2020)</title>
                  <date type="start">2021-01-10</date>
                  <date type="end">2021-01-15</date>
                  <settlement>Milan (en ligne)</settlement>
                  <country key="IT">Italy</country>
                </meeting>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="pp">3513-3519</biblScope>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/ICPR48806.2021.9412983</idno>
              <ref type="publisher">https://www.micc.unifi.it/icpr2020/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-cv">Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-hc">Computer Science [cs]/Human-Computer Interaction [cs.HC]</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>Action recognition in continuous video streams is a growing field since the past few years. Deep learning techniques and in particular Convolutional Neural Networks (CNNs) achieved good results in this topic. However, intrinsic CNNs limitations begin to cap the results since 2D CNN cannot capture temporal information and 3D CNN are to much resource demanding for real-time applications. Capsule Network, evolution of CNN, already proves its interesting benefits on small and low informational datasets like MNIST but yet its true potential has not emerged. In this paper we tackle the action recognition problem by proposing a new architecture combining Temporal Shift module over deep Capsule Network. Temporal Shift module permits us to insert temporal information over 2D Capsule Network with a zero computational cost to conserve the lightness of 2D capsules and their ability to connect spatial features. Our proposed approach outperforms or brings near state-of-the-art results on color and depth information on public datasets like First Person Hand Action and DHG 14/28 with a number of parameters 10 to 40 times less than existing approaches</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-1076752" status="VALID">
          <idno type="IdRef">20073511X</idno>
          <orgName>Ecole nationale supérieure Mines-Télécom Lille Douai</orgName>
          <orgName type="acronym">IMT Nord Europe</orgName>
          <date type="start">2021-09-01</date>
          <desc>
            <address>
              <addrLine>Cité Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D’ASCQ</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://imt-nord-europe.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>