<?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-01317558v2</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="2026-05-14T01:20:21+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Human Action Localization with Sparse Spatial Supervision</title>
            <author role="aut">
              <persName>
                <forename type="first">Philippe</forename>
                <surname>Weinzaepfel</surname>
              </persName>
              <idno type="halauthorid">534585-0</idno>
              <affiliation ref="#struct-23641"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Xavier</forename>
                <surname>Martin</surname>
              </persName>
              <idno type="halauthorid">25986-0</idno>
              <affiliation ref="#struct-445108"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cordelia</forename>
                <surname>Schmid</surname>
              </persName>
              <idno type="halauthorid">119565-0</idno>
              <affiliation ref="#struct-445108"/>
            </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-38053"/>
            <funder ref="#projeurop-98942"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2016-05-18 15:18:44</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2017-05-24 10:41:40</date>
              <date type="whenModified">2025-10-27 11:00:05</date>
              <date type="whenReleased">2017-05-24 11:58:16</date>
              <date type="whenProduced">2017-05-24</date>
              <date type="whenEndEmbargoed">2017-05-23</date>
              <ref type="file" target="https://inria.hal.science/hal-01317558v2/document">
                <date notBefore="2017-05-23"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01317558v2/file/ActionLocSparse.pdf" id="file-1527084-1588654">
                <date notBefore="2017-05-23"/>
              </ref>
              <ref type="annex" subtype="figure" n="1" target="https://inria.hal.science/hal-01317558v2/file/brushing_B3-ywpMj4Jk.jpg" id="file-1527084-1588653">
                <date notBefore="2017-05-23"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1605.05197"/>
            </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-01317558</idno>
            <idno type="halUri">https://inria.hal.science/hal-01317558</idno>
            <idno type="halBibtex">weinzaepfel:hal-01317558</idno>
            <idno type="halRefHtml">2017</idno>
            <idno type="halRef">2017</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1527084-1588654"/><ref corresp="#file-1527084-1588653"/></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="OPENAIRE">OpenAIRE</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="PERSYVAL-LAB">[Labex] PERSYVAL-lab</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="INRIA2017">INRIA2017</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="INRIA2017-PREPRINT">INRIA2017-PREPRINT</idno>
            <idno type="stamp" n="UGA-COMUE">Université Grenoble Alpes [2016-2019]</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="INRIA-ETATSUNIS">Copublications Inria-Etats-Unis</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Human Action Localization with Sparse Spatial Supervision</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Philippe</forename>
                    <surname>Weinzaepfel</surname>
                  </persName>
                  <idno type="halauthorid">534585-0</idno>
                  <affiliation ref="#struct-23641"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Xavier</forename>
                    <surname>Martin</surname>
                  </persName>
                  <idno type="halauthorid">25986-0</idno>
                  <affiliation ref="#struct-445108"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cordelia</forename>
                    <surname>Schmid</surname>
                  </persName>
                  <idno type="halauthorid">119565-0</idno>
                  <affiliation ref="#struct-445108"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
              <idno type="arxiv">1605.05197</idno>
            </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="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>We introduce an approach for spatio-temporal human action localization using sparse spatial supervision. Our method leverages the large amount of annotated humans available today and extracts human tubes by combining a state-of-the-art human detector with a tracking-by-detection approach. Given these high-quality human tubes and temporal supervision, we select positive and negative tubes with very sparse spatial supervision, i.e., only one spatially annotated frame per instance. The selected tubes allow us to effectively learn a spatio-temporal action detector based on dense trajectories or CNNs. We conduct experiments on existing action localization benchmarks: UCF-Sports, J-HMDB and UCF-101. Our results show that our approach, despite using sparse spatial supervision, performs on par with methods using full supervision, i.e., one bounding box annotation per frame. To further validate our method, we introduce DALY (Daily Action Localization in YouTube), a dataset for realistic action localization in space and time. It contains high quality temporal and spatial annotations for 3.6k instances of 10 actions in 31 hours of videos (3.3M frames). It is an order of magnitude larger than existing datasets, with more diversity in appearance and long untrimmed videos.</p>
            </abstract>
            <particDesc>
              <org type="consortium">ERC_Allegro</org>
              <org type="consortium">MSR-Inria</org>
              <org type="consortium">Google_Research_Award</org>
              <org type="consortium">Facebook_Research_Award</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-23641" status="VALID">
          <orgName>Xerox Research Centre Europe [Meylan]</orgName>
          <desc>
            <address>
              <addrLine>Xerox Research Centre Europe 6 Chemin de Maupertuis 38240 Meylan, FRANCE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.xrce.xerox.com</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301733" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-445108" status="OLD">
          <idno type="IdRef">242196691</idno>
          <idno type="RNSR">201622034K</idno>
          <orgName>Apprentissage de modèles à partir de données massives</orgName>
          <orgName type="acronym">Thoth</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</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-1042161" type="direct"/>
            <relation active="#struct-89889" type="indirect"/>
            <relation name="UMR5224" active="#struct-441569" type="indirect"/>
            <relation active="#struct-445543" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301733" status="VALID">
          <orgName>Xerox Company</orgName>
          <desc>
            <address>
              <country key="US"/>
            </address>
          </desc>
        </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-1042161" status="OLD">
          <idno type="IdRef">184945011</idno>
          <idno type="ISNI">000000040383676X</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">2016-01-01</date>
          <date type="end">2019-12-31</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-89889" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="direct"/>
            <relation active="#struct-445543" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-89889" status="OLD">
          <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">2007-01-01</date>
          <date type="end">2019-12-31</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>
        </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="institution" xml:id="struct-445543" status="OLD">
          <idno type="IdRef">188399275</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes [2016-2019]</orgName>
          <orgName type="acronym">UGA [2016-2019]</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-38053" status="VALID">
          <idno type="anr">ANR-11-LABX-0025</idno>
          <idno type="program">Laboratoires d'excellence</idno>
          <orgName>PERSYVAL-lab</orgName>
          <desc>Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique</desc>
          <date type="start">2011</date>
        </org>
        <org type="europeanProject" xml:id="projeurop-98942" status="VALID">
          <idno type="number">320559</idno>
          <idno type="program">ERC-2012-ADG_20120216</idno>
          <idno type="call">ERC-2012-ADG_20120216</idno>
          <orgName>ALLEGRO</orgName>
          <desc>Active large-scale learning for visual recognition</desc>
          <date type="start">2013-01-04</date>
          <date type="end">2019-03-31</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>