{"id":"https://openalex.org/W4385471990","doi":"https://doi.org/10.1145/3604951.3605519","title":"Investigations on Self-supervised Learning for Script-, Font-type, and Location Classification on Historical Documents","display_name":"Investigations on Self-supervised Learning for Script-, Font-type, and Location Classification on Historical Documents","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385471990","doi":"https://doi.org/10.1145/3604951.3605519"},"language":"en","primary_location":{"id":"doi:10.1145/3604951.3605519","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028470223","display_name":"Johan Zenk","orcid":"https://orcid.org/0009-0002-1320-7863"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johan Zenk","raw_affiliation_strings":["Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany"],"raw_orcid":"https://orcid.org/0009-0002-1320-7863","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062481511","display_name":"Florian Kordon","orcid":"https://orcid.org/0000-0003-1240-5809"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Kordon","raw_affiliation_strings":["Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1240-5809","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063384241","display_name":"Martin Mayr","orcid":"https://orcid.org/0000-0002-3706-285X"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Mayr","raw_affiliation_strings":["Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3706-285X","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066134818","display_name":"Mathias Seuret","orcid":"https://orcid.org/0000-0001-9153-1031"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mathias Seuret","raw_affiliation_strings":["Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9153-1031","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087093169","display_name":"Vincent Christlein","orcid":"https://orcid.org/0000-0003-0455-3799"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vincent Christlein","raw_affiliation_strings":["Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0455-3799","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, Friedrich-Alexander Universit\u00e4t Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.3333,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57806984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8119614124298096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7139216661453247},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.65058434009552},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.602100670337677},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5309188961982727},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5177525877952576},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.463054895401001},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43071386218070984},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.41341888904571533},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4126240015029907},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39682644605636597},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3601455092430115},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15232321619987488},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0612865686416626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119614124298096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7139216661453247},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.65058434009552},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.602100670337677},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5309188961982727},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5177525877952576},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.463054895401001},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43071386218070984},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.41341888904571533},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4126240015029907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39682644605636597},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3601455092430115},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15232321619987488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0612865686416626},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604951.3605519","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2526985373","https://openalex.org/W2767763628","https://openalex.org/W2963272834","https://openalex.org/W2980728898","https://openalex.org/W3003735458","https://openalex.org/W3080523870","https://openalex.org/W3159481202","https://openalex.org/W3171007011","https://openalex.org/W3182680257","https://openalex.org/W3198891134","https://openalex.org/W4211192082","https://openalex.org/W4286958723","https://openalex.org/W4304014014","https://openalex.org/W4313120827","https://openalex.org/W4320169084","https://openalex.org/W4393649849"],"related_works":["https://openalex.org/W2979740303","https://openalex.org/W3176438653","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W4286910063","https://openalex.org/W2163707935","https://openalex.org/W83146503","https://openalex.org/W2169074127","https://openalex.org/W2981628807","https://openalex.org/W4379875147"],"abstract_inverted_index":{"In":[0],"the":[1,22,75,82,88,107],"context":[2],"of":[3,6,24,46,81],"automated":[4],"classification":[5,64,89,129],"historical":[7],"documents,":[8],"we":[9],"investigate":[10],"three":[11,25],"contemporary":[12],"self-supervised":[13],"learning":[14,137],"(SSL)":[15],"techniques":[16],"(SimSiam,":[17],"Dino,":[18],"and":[19,33,50,65],"VICReg)":[20],"for":[21,62,126],"pre-training":[23],"different":[26],"document":[27,128],"analysis":[28],"tasks,":[29],"namely":[30],"script-type,":[31],"font-type,":[32],"location":[34],"classification.":[35],"Our":[36],"study":[37],"draws":[38],"samples":[39],"from":[40,106],"multiple":[41],"datasets":[42],"that":[43,117],"contain":[44],"images":[45],"manuscripts,":[47],"prints,":[48],"charters,":[49],"letters.":[51],"The":[52,70,95],"representations":[53,118],"derived":[54],"via":[55,101],"pre-text":[56],"training":[57],"are":[58,122],"taken":[59],"as":[60],"inputs":[61],"k-NN":[63],"a":[66],"parametric":[67],"linear":[68],"classifier.":[69],"latter":[71],"is":[72,99],"placed":[73],"atop":[74],"pre-trained":[76],"backbones":[77],"to":[78,85],"enable":[79],"fine-tuning":[80],"entire":[83],"network":[84],"further":[86],"improve":[87],"by":[90,133],"exploiting":[91],"task-specific":[92],"label":[93],"data.":[94],"network\u2019s":[96],"final":[97],"performance":[98],"assessed":[100],"independent":[102],"test":[103],"sets":[104],"obtained":[105],"ICDAR2021":[108],"Competition":[109],"on":[110,138],"Historical":[111],"Document":[112],"Classification.":[113],"We":[114],"empirically":[115],"show":[116],"learned":[119],"with":[120],"SSL":[121],"significantly":[123],"better":[124],"suited":[125],"subsequent":[127],"than":[130],"features":[131],"generated":[132],"commonly":[134],"used":[135],"transfer":[136],"ImageNet.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}