Conference
View in EDS

LADaS: A Diachronic Multi-Type Dataset for Document Layout Analysis from the 17th Century to the Present

Bibliographic Details
Title: LADaS: A Diachronic Multi-Type Dataset for Document Layout Analysis from the 17th Century to the Present
Authors: Janes, Juliette, Bénière, Sarah, Kiessling, Benjamin, Ing, Lucence, Astier, Éric, Gabay, Simon, Sagot, Benoît, Clérice, Thibault
Contributors: Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Centre Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Persée, École normale supérieure de Lyon (ENS de Lyon), Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), Université de Genève = University of Geneva (UNIGE), DEFI COLaF, European Project: 101132163,HORIZON-INFRA-2023-SERV-01,HORIZON-INFRA-2023-SERV-01,ATRIUM(2024)
Source: 8th International Workshop on Historical Document Imaging and Processing (HIP’26), The 20th International Conference on Document Analysis and Recognition (ICDAR)
https://hal.science/hal-05638101
8th International Workshop on Historical Document Imaging and Processing (HIP’26), The 20th International Conference on Document Analysis and Recognition (ICDAR), Sep 2026, Vienne, Austria
Publisher Information: CCSD
Publication Year: 2026
Collection: Université de Lyon: HAL
Subject Terms: Historical Documents, Cross-domain Transfer, Diachronic Dataset, Object Detection, Document Layout Analysis, Annotation Guidelines, Text Encoding Initiative, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [SHS.HIST]Humanities and Social Sciences/History, [SHS.LITT]Humanities and Social Sciences/Literature, [SHS.MUSEO]Humanities and Social Sciences/Cultural heritage and museology
Subject Geographic: Vienne, Austria
Description: International audience ; We introduce an open-access and openly-licensed diachronic dataset for Document Layout Analysis (DLA) targeting heterogeneous historical and contemporary materials 4 . The dataset comprises 8,287 manually annotated pages spanning 1600-2024, covering both digitised and born-digital documents across diverse genres including magazines, academic papers, monographs, plays, and administrative records. Annotations follow a two-level vocabulary derived from SegmOnto, extended to paragraph-level semantic regions consistent with the Text Encoding Initiative (TEI), and provide 45 fine-grained classes over 115,007 instances. The data is organised in modular subsets, enabling domain-specific configurations. We establish baselines using two families of object detectors (YOLOv11 and D-FINE) and study three regimes: in-domain training, label-set simplification, and large-scale pretraining (Objects365). We additionally conduct a cross-dataset transfer study against DocLayNet and M 6 Doc using a unified label mapping and a per-decade temporal evaluation. Results show that models trained on existing modern-centric DLA datasets degrade sharply on pre-20th century material (mean F1 dropping by up to 0.25), while in-domain training on our dataset preserves performance across centuries. This highlights the need for diachronic benchmarks and demonstrates the value of combining CV-based detection with DH-oriented annotation standards.
Document Type: conference object
Language: English
Relation: info:eu-repo/grantAgreement//101132163/EU/Advancing FronTier Research In the Arts and hUManities/ATRIUM
Availability: https://hal.science/hal-05638101
https://hal.science/hal-05638101v1/document
https://hal.science/hal-05638101v1/file/HIP-4.pdf
Rights: https://creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/OpenAccess
Accession Number: edsbas.4DD5571B
Database: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://hal.science/hal-05638101#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.4DD5571B
RelevancyScore: 1026
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 1025.63562011719
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: LADaS: A Diachronic Multi-Type Dataset for Document Layout Analysis from the 17th Century to the Present
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Janes%2C+Juliette%22">Janes, Juliette</searchLink><br /><searchLink fieldCode="AR" term="%22Bénière%2C+Sarah%22">Bénière, Sarah</searchLink><br /><searchLink fieldCode="AR" term="%22Kiessling%2C+Benjamin%22">Kiessling, Benjamin</searchLink><br /><searchLink fieldCode="AR" term="%22Ing%2C+Lucence%22">Ing, Lucence</searchLink><br /><searchLink fieldCode="AR" term="%22Astier%2C+Éric%22">Astier, Éric</searchLink><br /><searchLink fieldCode="AR" term="%22Gabay%2C+Simon%22">Gabay, Simon</searchLink><br /><searchLink fieldCode="AR" term="%22Sagot%2C+Benoît%22">Sagot, Benoît</searchLink><br /><searchLink fieldCode="AR" term="%22Clérice%2C+Thibault%22">Clérice, Thibault</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH)<br />Centre Inria de Paris<br />Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)<br />Persée<br />École normale supérieure de Lyon (ENS de Lyon)<br />Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS)<br />Université de Genève = University of Geneva (UNIGE)<br />DEFI COLaF<br />European Project: 101132163,HORIZON-INFRA-2023-SERV-01,HORIZON-INFRA-2023-SERV-01,ATRIUM(2024)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: 8th International Workshop on Historical Document Imaging and Processing (HIP’26), The 20th International Conference on Document Analysis and Recognition (ICDAR)<br />https://hal.science/hal-05638101<br />8th International Workshop on Historical Document Imaging and Processing (HIP’26), The 20th International Conference on Document Analysis and Recognition (ICDAR), Sep 2026, Vienne, Austria
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: CCSD
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2026
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Université de Lyon: HAL
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Historical+Documents%22">Historical Documents</searchLink><br /><searchLink fieldCode="DE" term="%22Cross-domain+Transfer%22">Cross-domain Transfer</searchLink><br /><searchLink fieldCode="DE" term="%22Diachronic+Dataset%22">Diachronic Dataset</searchLink><br /><searchLink fieldCode="DE" term="%22Object+Detection%22">Object Detection</searchLink><br /><searchLink fieldCode="DE" term="%22Document+Layout+Analysis%22">Document Layout Analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Annotation+Guidelines%22">Annotation Guidelines</searchLink><br /><searchLink fieldCode="DE" term="%22Text+Encoding+Initiative%22">Text Encoding Initiative</searchLink><br /><searchLink fieldCode="DE" term="%22[INFO%2EINFO-CV]Computer+Science+[cs]%2FComputer+Vision+and+Pattern+Recognition+[cs%2ECV]%22">[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]</searchLink><br /><searchLink fieldCode="DE" term="%22[SHS%2EHIST]Humanities+and+Social+Sciences%2FHistory%22">[SHS.HIST]Humanities and Social Sciences/History</searchLink><br /><searchLink fieldCode="DE" term="%22[SHS%2ELITT]Humanities+and+Social+Sciences%2FLiterature%22">[SHS.LITT]Humanities and Social Sciences/Literature</searchLink><br /><searchLink fieldCode="DE" term="%22[SHS%2EMUSEO]Humanities+and+Social+Sciences%2FCultural+heritage+and+museology%22">[SHS.MUSEO]Humanities and Social Sciences/Cultural heritage and museology</searchLink>
– Name: Subject
  Label: Subject Geographic
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Vienne%22">Vienne</searchLink><br /><searchLink fieldCode="DE" term="%22Austria%22">Austria</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: International audience ; We introduce an open-access and openly-licensed diachronic dataset for Document Layout Analysis (DLA) targeting heterogeneous historical and contemporary materials 4 . The dataset comprises 8,287 manually annotated pages spanning 1600-2024, covering both digitised and born-digital documents across diverse genres including magazines, academic papers, monographs, plays, and administrative records. Annotations follow a two-level vocabulary derived from SegmOnto, extended to paragraph-level semantic regions consistent with the Text Encoding Initiative (TEI), and provide 45 fine-grained classes over 115,007 instances. The data is organised in modular subsets, enabling domain-specific configurations. We establish baselines using two families of object detectors (YOLOv11 and D-FINE) and study three regimes: in-domain training, label-set simplification, and large-scale pretraining (Objects365). We additionally conduct a cross-dataset transfer study against DocLayNet and M 6 Doc using a unified label mapping and a per-decade temporal evaluation. Results show that models trained on existing modern-centric DLA datasets degrade sharply on pre-20th century material (mean F1 dropping by up to 0.25), while in-domain training on our dataset preserves performance across centuries. This highlights the need for diachronic benchmarks and demonstrates the value of combining CV-based detection with DH-oriented annotation standards.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: conference object
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: info:eu-repo/grantAgreement//101132163/EU/Advancing FronTier Research In the Arts and hUManities/ATRIUM
– Name: URL
  Label: Availability
  Group: URL
  Data: https://hal.science/hal-05638101<br />https://hal.science/hal-05638101v1/document<br />https://hal.science/hal-05638101v1/file/HIP-4.pdf
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: https://creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/OpenAccess
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.4DD5571B
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.4DD5571B
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Vienne
        Type: general
      – SubjectFull: Austria
        Type: general
      – SubjectFull: Historical Documents
        Type: general
      – SubjectFull: Cross-domain Transfer
        Type: general
      – SubjectFull: Diachronic Dataset
        Type: general
      – SubjectFull: Object Detection
        Type: general
      – SubjectFull: Document Layout Analysis
        Type: general
      – SubjectFull: Annotation Guidelines
        Type: general
      – SubjectFull: Text Encoding Initiative
        Type: general
      – SubjectFull: [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
        Type: general
      – SubjectFull: [SHS.HIST]Humanities and Social Sciences/History
        Type: general
      – SubjectFull: [SHS.LITT]Humanities and Social Sciences/Literature
        Type: general
      – SubjectFull: [SHS.MUSEO]Humanities and Social Sciences/Cultural heritage and museology
        Type: general
    Titles:
      – TitleFull: LADaS: A Diachronic Multi-Type Dataset for Document Layout Analysis from the 17th Century to the Present
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Janes, Juliette
      – PersonEntity:
          Name:
            NameFull: Bénière, Sarah
      – PersonEntity:
          Name:
            NameFull: Kiessling, Benjamin
      – PersonEntity:
          Name:
            NameFull: Ing, Lucence
      – PersonEntity:
          Name:
            NameFull: Astier, Éric
      – PersonEntity:
          Name:
            NameFull: Gabay, Simon
      – PersonEntity:
          Name:
            NameFull: Sagot, Benoît
      – PersonEntity:
          Name:
            NameFull: Clérice, Thibault
      – PersonEntity:
          Name:
            NameFull: Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH)
      – PersonEntity:
          Name:
            NameFull: Centre Inria de Paris
      – PersonEntity:
          Name:
            NameFull: Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
      – PersonEntity:
          Name:
            NameFull: Persée
      – PersonEntity:
          Name:
            NameFull: École normale supérieure de Lyon (ENS de Lyon)
      – PersonEntity:
          Name:
            NameFull: Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS)
      – PersonEntity:
          Name:
            NameFull: Université de Genève = University of Geneva (UNIGE)
      – PersonEntity:
          Name:
            NameFull: DEFI COLaF
      – PersonEntity:
          Name:
            NameFull: European Project: 101132163,HORIZON-INFRA-2023-SERV-01,HORIZON-INFRA-2023-SERV-01,ATRIUM(2024)
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
          Titles:
            – TitleFull: 8th International Workshop on Historical Document Imaging and Processing (HIP’26), The 20th International Conference on Document Analysis and Recognition (ICDAR) ; https://hal.science/hal-05638101 ; 8th International Workshop on Historical Document Imaging and Processing (HIP’26), The 20th International Conference on Document Analysis and Recognition (ICDAR), Sep 2026, Vienne, Austria
              Type: main
ResultId 1