<?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-01216103</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="2026-05-03T07:33:00+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Fast-Learning Adaptive-Subspace Self-Organizing Map: An Application to Saliency-Based Invariant Image Feature Construction</title>
            <author role="aut">
              <persName>
                <forename type="first">Huicheng</forename>
                <surname>Zheng</surname>
              </persName>
              <idno type="halauthorid">958938-0</idno>
              <orgName ref="#struct-365900"/>
              <affiliation ref="#struct-351709"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Grégoire</forename>
                <surname>Lefebvre</surname>
              </persName>
              <email type="md5">cb6fe14daa3d4fcb17173259091d28d4</email>
              <email type="domain">orange.com</email>
              <idno type="idhal" notation="string">gregoire-lefebvre</idno>
              <idno type="idhal" notation="numeric">5481</idno>
              <idno type="halauthorid" notation="string">26401-5481</idno>
              <idno type="IDREF">https://www.idref.fr/121808807</idno>
              <orgName ref="#struct-242003"/>
              <affiliation ref="#struct-305447"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christophe</forename>
                <surname>Laurent</surname>
              </persName>
              <idno type="halauthorid">100635-0</idno>
              <orgName ref="#struct-365900"/>
              <affiliation ref="#struct-305447"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Grégoire</forename>
                <surname>Lefebvre</surname>
              </persName>
              <email type="md5">cb6fe14daa3d4fcb17173259091d28d4</email>
              <email type="domain">orange.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-10-21 16:26:12</date>
              <date type="whenModified">2025-05-13 11:42:04</date>
              <date type="whenReleased">2015-10-23 08:59:13</date>
              <date type="whenProduced">2008-06-01</date>
              <date type="whenEndEmbargoed">2015-10-21</date>
              <ref type="file" target="https://hal.science/hal-01216103v1/document">
                <date notBefore="2015-10-21"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01216103v1/file/TNN2008.pdf" id="file-1216103-1297162">
                <date notBefore="2015-10-21"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-01216103/file/TNN2008.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="323389">
                <persName>
                  <forename>Grégoire</forename>
                  <surname>Lefebvre</surname>
                </persName>
                <email type="md5">cb6fe14daa3d4fcb17173259091d28d4</email>
                <email type="domain">orange.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01216103</idno>
            <idno type="halUri">https://hal.science/hal-01216103</idno>
            <idno type="halBibtex">zheng:hal-01216103</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE Transactions on Neural Networks&lt;/i&gt;, 2008, &lt;a target="_blank" href="https://dx.doi.org/10.1109/TNN.2007.911741"&gt;&amp;#x27E8;10.1109/TNN.2007.911741&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE Transactions on Neural Networks, 2008, &amp;#x27E8;10.1109/TNN.2007.911741&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1216103-1297162"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Fast-Learning Adaptive-Subspace Self-Organizing Map: An Application to Saliency-Based Invariant Image Feature Construction</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Huicheng</forename>
                    <surname>Zheng</surname>
                  </persName>
                  <idno type="halauthorid">958938-0</idno>
                  <orgName ref="#struct-365900"/>
                  <affiliation ref="#struct-351709"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Grégoire</forename>
                    <surname>Lefebvre</surname>
                  </persName>
                  <email type="md5">cb6fe14daa3d4fcb17173259091d28d4</email>
                  <email type="domain">orange.com</email>
                  <idno type="idhal" notation="string">gregoire-lefebvre</idno>
                  <idno type="idhal" notation="numeric">5481</idno>
                  <idno type="halauthorid" notation="string">26401-5481</idno>
                  <idno type="IDREF">https://www.idref.fr/121808807</idno>
                  <orgName ref="#struct-242003"/>
                  <affiliation ref="#struct-305447"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christophe</forename>
                    <surname>Laurent</surname>
                  </persName>
                  <idno type="halauthorid">100635-0</idno>
                  <orgName ref="#struct-365900"/>
                  <affiliation ref="#struct-305447"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">5386</idno>
                <idno type="issn">1045-9227</idno>
                <title level="j">IEEE Transactions on Neural Networks</title>
                <imprint>
                  <publisher>Institute of Electrical and Electronics Engineers</publisher>
                  <date type="datePub">2008-06-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/TNN.2007.911741</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Adaptive-Subspace Self-Organizing Map</term>
                <term xml:lang="en">feature construction</term>
                <term xml:lang="en">adult image filtering</term>
                <term xml:lang="en">image classification</term>
              </keywords>
              <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-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-ts">Computer Science [cs]/Signal and Image Processing</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The Adaptive-Subspace Self-Organizing Map (AS-SOM) is useful for invariant feature generation and visualization. However, the learning procedure of the ASSOM is slow. In this paper, two fast implementations of the ASSOM are proposed to boost ASSOM learning based on insightful discussions of the basis rotation operator of ASSOM. We reveal the objective function approximately maximized by the classical rotation operator. We then explore a sequence of two schemes to apply the proposed ASSOM implementations to saliency-based invariant feature construction for image classification. In the first scheme, a cumulative activity map computed from a single ASSOM is used as descriptor of the input image. In the second scheme, we use one ASSOM for each image category and a joint cumulative activity map is calculated as the descriptor. Both schemes are evaluated on a subset of the Corel photo base with 10 classes. The multi-ASSOM scheme is favored. It is also applied to adult image filtering and shows promising results.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-351709" status="VALID">
          <idno type="IdRef">149100981</idno>
          <idno type="ISNI">000000012360039X</idno>
          <idno type="ROR">https://ror.org/0064kty71</idno>
          <idno type="Wikidata">Q178972</idno>
          <orgName>Sun Yat-sen University [Guangzhou]</orgName>
          <orgName type="acronym">SYSU</orgName>
          <date type="start">1924-01-01</date>
          <desc>
            <address>
              <addrLine>135 Xingang W Rd, Haizhu, Guangzhou, Guangdong, China</addrLine>
              <country key="CN"/>
            </address>
            <ref type="url">http://www.sysu.edu.cn/2012/en/index.htm</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-305447" status="INCOMING">
          <orgName>France Telecom Division R&amp;D</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>