<?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-00872048</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="2026-05-24T12:50:18+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Time-Sensitive Topic Models for Action Recognition in Videos</title>
            <author role="aut">
              <persName>
                <forename type="first">Romain</forename>
                <surname>Tavenard</surname>
              </persName>
              <email type="md5">a0888b1a1cb237cc32f9a6925f135184</email>
              <email type="domain">univ-rennes2.fr</email>
              <idno type="idhal" notation="string">rtavenar</idno>
              <idno type="idhal" notation="numeric">5645</idno>
              <idno type="halauthorid" notation="string">19744-5645</idno>
              <idno type="IDREF">https://www.idref.fr/154729507</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1439-8465</idno>
              <affiliation ref="#struct-74654"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Rémi</forename>
                <surname>Emonet</surname>
              </persName>
              <email type="md5">5f8888ea308602ed72d8797ce9b88936</email>
              <email type="domain">univ-st-etienne.fr</email>
              <idno type="idhal" notation="string">remi-emonet</idno>
              <idno type="idhal" notation="numeric">3876</idno>
              <idno type="halauthorid" notation="string">34959-3876</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1870-1329</idno>
              <idno type="IDREF">https://www.idref.fr/139072578</idno>
              <affiliation ref="#struct-74654"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Marc</forename>
                <surname>Odobez</surname>
              </persName>
              <idno type="halauthorid">355745-0</idno>
              <affiliation ref="#struct-74654"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Rémi</forename>
                <surname>Emonet</surname>
              </persName>
              <email type="md5">5f8888ea308602ed72d8797ce9b88936</email>
              <email type="domain">univ-st-etienne.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-02-21 22:46:48</date>
              <date type="whenModified">2019-02-07 17:55:47</date>
              <date type="whenReleased">2018-02-20 08:44:34</date>
              <date type="whenProduced">2013-09-15</date>
              <date type="whenEndEmbargoed">2017-02-21</date>
              <ref type="file" target="https://inria.hal.science/hal-00872048v1/document">
                <date notBefore="2017-02-21"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-00872048v1/file/hal-00872048.pdf" id="file-1473556-1541350">
                <date notBefore="2017-02-21"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="187406">
                <persName>
                  <forename>Rémi</forename>
                  <surname>Emonet</surname>
                </persName>
                <email type="md5">5f8888ea308602ed72d8797ce9b88936</email>
                <email type="domain">univ-st-etienne.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00872048</idno>
            <idno type="halUri">https://inria.hal.science/hal-00872048</idno>
            <idno type="halBibtex">tavenard:hal-00872048</idno>
            <idno type="halRefHtml">&lt;i&gt;ICIP - International Conference on Image Processing&lt;/i&gt;, Sep 2013, Melbourne, Australia</idno>
            <idno type="halRef">ICIP - International Conference on Image Processing, Sep 2013, Melbourne, Australia</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1473556-1541350"/></licence>
            </availability>
          </publicationStmt>
          <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">Time-Sensitive Topic Models for Action Recognition in Videos</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Romain</forename>
                    <surname>Tavenard</surname>
                  </persName>
                  <email type="md5">a0888b1a1cb237cc32f9a6925f135184</email>
                  <email type="domain">univ-rennes2.fr</email>
                  <idno type="idhal" notation="string">rtavenar</idno>
                  <idno type="idhal" notation="numeric">5645</idno>
                  <idno type="halauthorid" notation="string">19744-5645</idno>
                  <idno type="IDREF">https://www.idref.fr/154729507</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1439-8465</idno>
                  <affiliation ref="#struct-74654"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Rémi</forename>
                    <surname>Emonet</surname>
                  </persName>
                  <email type="md5">5f8888ea308602ed72d8797ce9b88936</email>
                  <email type="domain">univ-st-etienne.fr</email>
                  <idno type="idhal" notation="string">remi-emonet</idno>
                  <idno type="idhal" notation="numeric">3876</idno>
                  <idno type="halauthorid" notation="string">34959-3876</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1870-1329</idno>
                  <idno type="IDREF">https://www.idref.fr/139072578</idno>
                  <affiliation ref="#struct-74654"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Marc</forename>
                    <surname>Odobez</surname>
                  </persName>
                  <idno type="halauthorid">355745-0</idno>
                  <affiliation ref="#struct-74654"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ICIP - International Conference on Image Processing</title>
                  <date type="start">2013-09-15</date>
                  <date type="end">2013-09-18</date>
                  <settlement>Melbourne</settlement>
                  <country key="AU">Australia</country>
                </meeting>
                <imprint>
                  <date type="datePub">2013</date>
                </imprint>
              </monogr>
            </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-lg">Computer Science [cs]/Machine Learning [cs.LG]</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>In this paper, we postulate that temporal information is important for action recognition in videos. Keeping temporal information, videos are represented as word time documents. We propose to use time-sensitive probabilistic topic models and we extend them for the context of supervised learning. Our time-sensitive approach is compared to both PLSA and Bag-of-Words. Our approach is shown to both capture semantics from data and yield classification performance comparable to other methods, outperforming them when the amount of training data is low.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-74654" status="VALID">
          <orgName>IDIAP Research Institute</orgName>
          <desc>
            <address>
              <addrLine>Centre du Parc Rue Marconi 19 PO Box 592 CH - 1920 Martigny Switzerland</addrLine>
              <country key="CH"/>
            </address>
            <ref type="url">http://www.idiap.ch/linstitut</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>