{"id":"https://openalex.org/W4385470899","doi":"https://doi.org/10.1145/3604951.3605511","title":"DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis","display_name":"DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385470899","doi":"https://doi.org/10.1145/3604951.3605511"},"language":"en","primary_location":{"id":"doi:10.1145/3604951.3605511","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604951.3605511","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604951.3605511","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of the 7th International Workshop on Historical Document Imaging and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":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3604951.3605511","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016271960","display_name":"Lars V\u00f6gtlin","orcid":"https://orcid.org/0000-0002-2543-9074"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Lars V\u00f6gtlin","raw_affiliation_strings":["University of Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018871260","display_name":"Anna Scius-Bertrand","orcid":null},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anna Scius-Bertrand","raw_affiliation_strings":["University of Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066161932","display_name":"Paul Maergner","orcid":"https://orcid.org/0000-0002-9270-9986"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paul Maergner","raw_affiliation_strings":["University of Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019597653","display_name":"Andreas Fischer","orcid":"https://orcid.org/0000-0003-0069-3436"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Fischer","raw_affiliation_strings":["University of Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018014670","display_name":"Rolf Ingold","orcid":"https://orcid.org/0000-0001-7738-133X"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rolf Ingold","raw_affiliation_strings":["University of Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016271960"],"corresponding_institution_ids":["https://openalex.org/I154338468"],"apc_list":null,"apc_paid":null,"fwci":0.3611,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59181138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9973000288009644,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.989300012588501,"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/diva","display_name":"Diva","score":0.852928638458252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6118175983428955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4891076683998108},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46833348274230957},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.4373820424079895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3794286847114563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3791976571083069},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.1377672553062439},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.12714076042175293}],"concepts":[{"id":"https://openalex.org/C2781092335","wikidata":"https://www.wikidata.org/wiki/Q867132","display_name":"Diva","level":2,"score":0.852928638458252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118175983428955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4891076683998108},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46833348274230957},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.4373820424079895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3794286847114563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3791976571083069},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.1377672553062439},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.12714076042175293}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3604951.3605511","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604951.3605511","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604951.3605511","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"},{"id":"pmh:oai:hesso.tind.io:13143","is_oa":false,"landing_page_url":"http://arodes.hes-so.ch/record/13143","pdf_url":null,"source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/13143","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3604951.3605511","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604951.3605511","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604951.3605511","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385470899.pdf","grobid_xml":"https://content.openalex.org/works/W4385470899.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2951882630","https://openalex.org/W2963881378","https://openalex.org/W2984055017","https://openalex.org/W3000820403","https://openalex.org/W3045582458","https://openalex.org/W3118281477","https://openalex.org/W6788270868","https://openalex.org/W6912515347"],"related_works":["https://openalex.org/W4256010879","https://openalex.org/W4223522741","https://openalex.org/W4322587066","https://openalex.org/W3216653757","https://openalex.org/W3088360568","https://openalex.org/W4322586679","https://openalex.org/W2030658481","https://openalex.org/W3128670447","https://openalex.org/W4247460045","https://openalex.org/W3043369706"],"abstract_inverted_index":{"Deep":[0],"learning":[1,43],"methods":[2],"have":[3,103],"shown":[4],"strong":[5],"performance":[6],"in":[7],"solving":[8],"tasks":[9,60,80],"for":[10,55,87,107,118],"historical":[11,56],"document":[12,57,112],"image":[13],"analysis.":[14,58],"However,":[15],"despite":[16],"current":[17],"libraries":[18],"and":[19,29,52,64,94],"frameworks,":[20],"programming":[21,109],"an":[22,40],"experiment":[23],"or":[24,70,124],"a":[25,111],"set":[26],"of":[27,84,97,110,141],"experiments":[28],"executing":[30],"them":[31],"can":[32,66],"be":[33,67],"time-consuming.":[34],"This":[35],"is":[36,47,73],"why":[37],"we":[38],"propose":[39],"open-source":[41],"deep":[42],"framework,":[44],"DIVA-DAF,":[45],"which":[46],"based":[48],"on":[49],"PyTorch":[50],"Lightning":[51],"specifically":[53],"designed":[54],"Pre-implemented":[59],"such":[61,121],"as":[62,115,117,122],"segmentation":[63],"classification":[65],"easily":[68],"used":[69],"customized.":[71],"It":[72],"also":[74,135],"easy":[75],"to":[76,129,137],"create":[77],"one\u2019s":[78],"own":[79],"with":[81],"the":[82,108,126,133,139],"benefit":[83],"powerful":[85],"modules":[86],"loading":[88],"data,":[89],"even":[90],"large":[91],"data":[92,131],"sets,":[93],"different":[95,119],"forms":[96],"ground":[98],"truth.":[99],"The":[100],"applications":[101],"conducted":[102],"demonstrated":[104],"time":[105,140],"savings":[106],"analysis":[113],"task,":[114],"well":[116],"scenarios":[120],"pre-training":[123],"changing":[125],"architecture.":[127],"Thanks":[128],"its":[130],"module,":[132],"framework":[134],"allows":[136],"reduce":[138],"model":[142],"training":[143],"significantly.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-08-02T00:00:00"}