<?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-03456989</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="2026-05-16T16:25:19+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Image Caption Combined with GAN Training Method</title>
            <author role="aut">
              <persName>
                <forename type="first">Zeqin</forename>
                <surname>Huang</surname>
              </persName>
              <email type="md5">fbeb731fdd11ebd12b57fb50fe59f8ef</email>
              <email type="domain">ict.ac.cn</email>
              <idno type="idhal" notation="numeric">1118842</idno>
              <idno type="halauthorid" notation="string">2356532-1118842</idno>
              <affiliation ref="#struct-469160"/>
              <affiliation ref="#struct-303369"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Zhongzhi</forename>
                <surname>Shi</surname>
              </persName>
              <email type="md5">3a89a71cce5165b1767dd1b31ecc66cb</email>
              <email type="domain">ict.ac.cn</email>
              <idno type="idhal" notation="numeric">1046597</idno>
              <idno type="halauthorid" notation="string">181215-1046597</idno>
              <affiliation ref="#struct-303369"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Hal</forename>
                <surname>Ifip</surname>
              </persName>
              <email type="md5">2073ac78024b6e13f2714db96e9b1e63</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-11-30 12:34:25</date>
              <date type="whenModified">2024-11-12 11:34:03</date>
              <date type="whenReleased">2021-11-30 14:07:18</date>
              <date type="whenProduced">2020-07-03</date>
              <date type="whenEndEmbargoed">2023-01-01</date>
              <ref type="file" target="https://inria.hal.science/hal-03456989v1/document">
                <date notBefore="2023-01-01"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-03456989v1/file/498234_1_En_29_Chapter.pdf" id="file-3456989-3031291">
                <date notBefore="2023-01-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="200187">
                <persName>
                  <forename>Hal</forename>
                  <surname>Ifip</surname>
                </persName>
                <email type="md5">2073ac78024b6e13f2714db96e9b1e63</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03456989</idno>
            <idno type="halUri">https://inria.hal.science/hal-03456989</idno>
            <idno type="halBibtex">huang:hal-03456989</idno>
            <idno type="halRefHtml">&lt;i&gt;11th International Conference on Intelligent Information Processing (IIP)&lt;/i&gt;, Jul 2020, Hangzhou, China. pp.310-316, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-030-46931-3_29"&gt;&amp;#x27E8;10.1007/978-3-030-46931-3_29&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">11th International Conference on Intelligent Information Processing (IIP), Jul 2020, Hangzhou, China. pp.310-316, &amp;#x27E8;10.1007/978-3-030-46931-3_29&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-3456989-3031291"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="IFIP">IFIP - International Federation for Information Processing</idno>
            <idno type="stamp" n="IFIP-AICT" corresp="IFIP">IFIP Advances in Information and Communication Technology</idno>
            <idno type="stamp" n="IFIP-TC" corresp="IFIP">IFIP Technical Committees </idno>
            <idno type="stamp" n="IFIP-TC12" corresp="IFIP-TC">TC12 - Artificial Intelligence</idno>
            <idno type="stamp" n="IFIP-IIP" corresp="IFIP-AICT">IFIP-IIP</idno>
            <idno type="stamp" n="IFIP-AICT-581" corresp="IFIP-AICT">Intelligent Information Processing X</idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">Part 7: Computer Vision and Image Understanding</note>
            <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">Image Caption Combined with GAN Training Method</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Zeqin</forename>
                    <surname>Huang</surname>
                  </persName>
                  <email type="md5">fbeb731fdd11ebd12b57fb50fe59f8ef</email>
                  <email type="domain">ict.ac.cn</email>
                  <idno type="idhal" notation="numeric">1118842</idno>
                  <idno type="halauthorid" notation="string">2356532-1118842</idno>
                  <affiliation ref="#struct-469160"/>
                  <affiliation ref="#struct-303369"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Zhongzhi</forename>
                    <surname>Shi</surname>
                  </persName>
                  <email type="md5">3a89a71cce5165b1767dd1b31ecc66cb</email>
                  <email type="domain">ict.ac.cn</email>
                  <idno type="idhal" notation="numeric">1046597</idno>
                  <idno type="halauthorid" notation="string">181215-1046597</idno>
                  <affiliation ref="#struct-303369"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">IFIP Advances in Information and Communication Technology</title>
                <meeting>
                  <title>11th International Conference on Intelligent Information Processing (IIP)</title>
                  <date type="start">2020-07-03</date>
                  <date type="end">2020-07-06</date>
                  <settlement>Hangzhou</settlement>
                  <country key="CN">China</country>
                </meeting>
                <editor>Zhongzhi Shi</editor>
                <editor>Sunil Vadera</editor>
                <editor>Elizabeth Chang</editor>
                <imprint>
                  <publisher>Springer International Publishing</publisher>
                  <biblScope unit="serie">Intelligent Information Processing X</biblScope>
                  <biblScope unit="volume">AICT-581</biblScope>
                  <biblScope unit="pp">310-316</biblScope>
                  <date type="datePub">2020</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-030-46931-3_29</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">LSTM</term>
                <term xml:lang="en">Image caption</term>
                <term xml:lang="en">Attention mechanism</term>
                <term xml:lang="en">Deep learning</term>
                <term xml:lang="en">GAN</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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 today’s world where the number of images is huge and people cannot quickly retrieve the information they need, we urgently need a simpler and more human-friendly way of understanding images, and image captions have emerged. Image caption, as its name suggests, is to analyze and understand image information to generate natural language descriptions of specific images. In recent years, it has been widely used in image-text crossover studies, early infant education, and assisted by disadvantaged groups. And the favor of industry, has produced many excellent research results. At present, the evaluation of image caption is basically based on objective evaluation indicators such as BLUE and CIDEr. It is easy to prevent the generated caption from approaching human language expression. The introduction of GAN idea allows us to use a new method of adversarial training. To evaluate the generated caption, the evaluation module is more natural and comprehensive. Considering the requirements for image fidelity, this topic proposes a GAN-based image description. The Attention mechanism is introduced to improve image fidelity, which makes the generated caption more accurate and more close to human language expression.</p>
            </abstract>
            <particDesc>
              <org type="consortium">TC 12</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="regrouplaboratory" xml:id="struct-469160" status="VALID">
          <idno type="ROR">https://ror.org/05qbk4x57</idno>
          <orgName>University of Chinese Academy of Sciences [Beijing]</orgName>
          <orgName type="acronym">UCAS</orgName>
          <date type="start">2016-10-20</date>
          <desc>
            <address>
              <addrLine>No.19(A) Yuquan Road, Shijingshan District, Beijing, P.R.China 100049</addrLine>
              <country key="CN"/>
            </address>
            <ref type="url">http://english.ucas.ac.cn/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-303369" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-303369" status="VALID">
          <idno type="ROR">https://ror.org/034t30j35</idno>
          <orgName>Chinese Academy of Sciences [Beijing]</orgName>
          <orgName type="acronym">CAS</orgName>
          <desc>
            <address>
              <addrLine>52 Sanlihe Rd., Beijing, 100864</addrLine>
              <country key="CN"/>
            </address>
            <ref type="url">http://english.cas.cn/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>