<?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-05120511</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="2026-05-19T16:17:02+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">WildKhmerST: A Comprehensive Dataset and Benchmark for Khmer Scene Text Detection and Recognition in the Wild</title>
            <author role="aut">
              <persName>
                <forename type="first">Vannkinh</forename>
                <surname>Nom</surname>
              </persName>
              <email type="md5">b111e9e2d0d082128ed2121a3b824f06</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">vannkinh-nom</idno>
              <idno type="idhal" notation="numeric">1532948</idno>
              <idno type="halauthorid" notation="string">3483667-1532948</idno>
              <idno type="ORCID">https://orcid.org/0009-0004-4684-0416</idno>
              <affiliation ref="#struct-1145672"/>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-300311"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Saly</forename>
                <surname>Keo</surname>
              </persName>
              <email type="md5">b989f1b78fae4430c0d754e26770e993</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">salykeo</idno>
              <idno type="idhal" notation="numeric">1532951</idno>
              <idno type="halauthorid" notation="string">3483673-1532951</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=78TuKksAAAAJ</idno>
              <idno type="ORCID">https://orcid.org/0009-0000-9878-4015</idno>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-300311"/>
              <affiliation ref="#struct-1145672"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Souhail</forename>
                <surname>Bakkali</surname>
              </persName>
              <email type="md5">f774952658bba621f870d23eda1a5b76</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">souhail-bakkali</idno>
              <idno type="idhal" notation="numeric">1252080</idno>
              <idno type="halauthorid" notation="string">1996573-1252080</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9383-3842</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gO_Q48IAAAAJ</idno>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-300311"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Muhammad</forename>
                <forename type="middle">Muzzamil</forename>
                <surname>Luqman</surname>
              </persName>
              <email type="md5">88b3cc3407d8cd58bfcbcff8592003d8</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">muhammad-muzzamil-luqman</idno>
              <idno type="idhal" notation="numeric">3218</idno>
              <idno type="halauthorid" notation="string">1996510-3218</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9658-0833</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=ACfqR3UAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/163827265</idno>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-300311"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mickaël</forename>
                <surname>Coustaty</surname>
              </persName>
              <email type="md5">f9ce53d60edb2cd05a382789958ad267</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">mickael-coustaty</idno>
              <idno type="idhal" notation="numeric">2462</idno>
              <idno type="halauthorid" notation="string">8192-2462</idno>
              <idno type="IDREF">https://www.idref.fr/160560268</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0123-439X</idno>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-300311"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marçal</forename>
                <surname>Rossinyol</surname>
              </persName>
              <idno type="idhal" notation="numeric">1553424</idno>
              <idno type="halauthorid" notation="string">3591576-1553424</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1734-2205</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Marc</forename>
                <surname>Ogier</surname>
              </persName>
              <email type="md5">a339d6fb3cccbb765373cffb3e1c31c1</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="numeric">833747</idno>
              <idno type="halauthorid" notation="string">133814-833747</idno>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-300311"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Vannkinh</forename>
                <surname>Nom</surname>
              </persName>
              <email type="md5">b111e9e2d0d082128ed2121a3b824f06</email>
              <email type="domain">univ-lr.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-06-19 11:16:11</date>
              <date type="whenModified">2026-02-11 11:32:02</date>
              <date type="whenReleased">2025-06-25 16:15:51</date>
              <date type="whenProduced">2025-09-16</date>
              <date type="whenEndEmbargoed">2025-06-19</date>
              <ref type="file" target="https://hal.science/hal-05120511v1/document">
                <date notBefore="2025-06-19"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05120511v1/file/WildKhmerST_A_Comprehensive_Dataset_and_Benchmark.pdf" id="file-5120511-4426287">
                <date notBefore="2025-06-19"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1663595">
                <persName>
                  <forename>Vannkinh</forename>
                  <surname>Nom</surname>
                </persName>
                <email type="md5">b111e9e2d0d082128ed2121a3b824f06</email>
                <email type="domain">univ-lr.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05120511</idno>
            <idno type="halUri">https://hal.science/hal-05120511</idno>
            <idno type="halBibtex">nom:hal-05120511</idno>
            <idno type="halRefHtml">&lt;i&gt;The 19th International Conference on Document Analysis and Recognition&lt;/i&gt;, Sep 2025, Wuhan, Hubei, China</idno>
            <idno type="halRef">The 19th International Conference on Document Analysis and Recognition, Sep 2025, Wuhan, Hubei, China</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc-nd/4.0/">CC BY-NC-ND 4.0 - Attribution - Non-commercial use - No Derivative Works<ref corresp="#file-5120511-4426287"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-ROCHELLE">Université de La Rochelle</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">WildKhmerST: A Comprehensive Dataset and Benchmark for Khmer Scene Text Detection and Recognition in the Wild</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Vannkinh</forename>
                    <surname>Nom</surname>
                  </persName>
                  <email type="md5">b111e9e2d0d082128ed2121a3b824f06</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">vannkinh-nom</idno>
                  <idno type="idhal" notation="numeric">1532948</idno>
                  <idno type="halauthorid" notation="string">3483667-1532948</idno>
                  <idno type="ORCID">https://orcid.org/0009-0004-4684-0416</idno>
                  <affiliation ref="#struct-1145672"/>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-300311"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Saly</forename>
                    <surname>Keo</surname>
                  </persName>
                  <email type="md5">b989f1b78fae4430c0d754e26770e993</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">salykeo</idno>
                  <idno type="idhal" notation="numeric">1532951</idno>
                  <idno type="halauthorid" notation="string">3483673-1532951</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=78TuKksAAAAJ</idno>
                  <idno type="ORCID">https://orcid.org/0009-0000-9878-4015</idno>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-300311"/>
                  <affiliation ref="#struct-1145672"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Souhail</forename>
                    <surname>Bakkali</surname>
                  </persName>
                  <email type="md5">f774952658bba621f870d23eda1a5b76</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">souhail-bakkali</idno>
                  <idno type="idhal" notation="numeric">1252080</idno>
                  <idno type="halauthorid" notation="string">1996573-1252080</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9383-3842</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gO_Q48IAAAAJ</idno>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-300311"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Muhammad</forename>
                    <forename type="middle">Muzzamil</forename>
                    <surname>Luqman</surname>
                  </persName>
                  <email type="md5">88b3cc3407d8cd58bfcbcff8592003d8</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">muhammad-muzzamil-luqman</idno>
                  <idno type="idhal" notation="numeric">3218</idno>
                  <idno type="halauthorid" notation="string">1996510-3218</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9658-0833</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=ACfqR3UAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/163827265</idno>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-300311"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mickaël</forename>
                    <surname>Coustaty</surname>
                  </persName>
                  <email type="md5">f9ce53d60edb2cd05a382789958ad267</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">mickael-coustaty</idno>
                  <idno type="idhal" notation="numeric">2462</idno>
                  <idno type="halauthorid" notation="string">8192-2462</idno>
                  <idno type="IDREF">https://www.idref.fr/160560268</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0123-439X</idno>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-300311"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marçal</forename>
                    <surname>Rossinyol</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1553424</idno>
                  <idno type="halauthorid" notation="string">3591576-1553424</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1734-2205</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Marc</forename>
                    <surname>Ogier</surname>
                  </persName>
                  <email type="md5">a339d6fb3cccbb765373cffb3e1c31c1</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="numeric">833747</idno>
                  <idno type="halauthorid" notation="string">133814-833747</idno>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-300311"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>The 19th International Conference on Document Analysis and Recognition</title>
                  <date type="start">2025-09-16</date>
                  <date type="end">2025-09-21</date>
                  <settlement>Wuhan, Hubei</settlement>
                  <country key="CN">China</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Scene-Text Detection and Recognition</term>
                <term xml:lang="en">Low-resource languages</term>
                <term xml:lang="en">Khmer Script</term>
                <term xml:lang="en">WildKhmerST Dataset</term>
                <term xml:lang="en">WildKhmerST Dataset Khmer Script Low-resource languages Scene-Text Detection and Recognition</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>&lt;div&gt;&lt;p&gt;This study presents a large-scale dataset of Khmer scene text images captured in real-world environments. Khmer, the official language of Cambodia, is spoken by approximately 17 million people. While Optical Character Recognition (OCR) systems have achieved remarkable success in Roman (Latin) script languages such as English, Khmer script poses unique challenges due to its intricate structure, absence of clear word boundaries, and highly diverse character shapes and sizes. A significant limitation in Khmer OCR research has been the scarcity of highquality training data, particularly for deep learning-based models, which require extensive datasets to achieve robust performance. To address these challenges, we introduce a newly constructed dataset of Khmer scene text, comprising 29,601 annotated text lines from 10,000 unique images. This dataset is highly diverse and challenging, encompassing artistic text, blurred text, low-light conditions, curved text, text in complex backgrounds, and occluded text. Each text line is annotated with polygonal bounding box coordinates and line-level transcriptions, alongside attributes describing background complexity, character appearance, and text style. To establish a foundational benchmark for future research in Khmer OCR, we provide baseline results for Khmer text detection and recognition. Additionally, we propose a robust evaluation metric tailored for Khmer OCR, enabling precise assessment of CER and WER while accounting for the unique characteristics of the Khmer script.&lt;/p&gt;&lt;/div&gt;</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-1145672" status="VALID">
          <idno type="ROR">https://ror.org/05fj1je62</idno>
          <orgName>Cambodia Academy of Digital Technology</orgName>
          <orgName type="acronym">CADT</orgName>
          <desc>
            <address>
              <addrLine>2nd Bridge Prek Leap, National Road Number 6, Phnom Penh 12252</addrLine>
              <country key="KH"/>
            </address>
            <ref type="url">https://www.cadt.edu.kh</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-40831" status="VALID">
          <idno type="IdRef">183449045</idno>
          <idno type="RNSR">199613735B</idno>
          <idno type="ROR">https://ror.org/03r7r0k94</idno>
          <orgName>Laboratoire Informatique, Image et Interaction - EA 2118</orgName>
          <orgName type="acronym">L3I</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://l3i.univ-larochelle.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA2118" active="#struct-300311" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300311" status="VALID">
          <idno type="IdRef">035375043</idno>
          <idno type="ISNI">0000 0001 2169 7335</idno>
          <idno type="ROR">https://ror.org/04mv1z119</idno>
          <orgName>La Rochelle Université</orgName>
          <orgName type="acronym">ULR</orgName>
          <desc>
            <address>
              <addrLine>Technoforum - 23 avenue Albert Einstein - BP 33060 - 17031 La Rochelle - France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-larochelle.fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>