{"id":"https://openalex.org/W7204011900","doi":"https://doi.org/10.1007/978-3-032-36033-5_41","title":"Specialized HTR vs Vision-Language Models: Evaluating DANIEL and Fine-Tuned Qwen on Historical Documents","display_name":"Specialized HTR vs Vision-Language Models: Evaluating DANIEL and Fine-Tuned Qwen on Historical Documents","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204011900","doi":"https://doi.org/10.1007/978-3-032-36033-5_41"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-36033-5_41","doi":"https://doi.org/10.1007/978-3-032-36033-5_41","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-36033-5_41","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"parent_works":[{"id":"https://openalex.org/W7203972584","display_name":"Document Analysis and Recognition \u2013 ICDAR 2026: 20th International Conference, Vienna, Austria, August 31 \u2013 September 2, 2026, Proceedings, Part II","relationship":"volume"}],"lineage":["https://openalex.org/W7204011900","https://openalex.org/W7203972584"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5035521679","display_name":"Gabriel Frossard","orcid":"https://orcid.org/0009-0004-6655-7028","observed_orcids":["https://orcid.org/0009-0004-6655-7028"]},"institutions":[{"id":"https://openalex.org/I37553959","display_name":"Universit\u00e9 de technologie de belfort-montb\u00e9liard","ror":"https://ror.org/05bn3m307","country_code":"FR","type":"education","lineage":["https://openalex.org/I37553959"]},{"id":"https://openalex.org/I4387153146","display_name":"Connaissance & Intelligence Artificielle Distribu\u00e9es","ror":"https://ror.org/01ch21j41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I37553959","https://openalex.org/I4387153146","https://openalex.org/I4405253280"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Gabriel Frossard","raw_affiliation_strings":["CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France"],"raw_orcid":"https://orcid.org/0009-0004-6655-7028","affiliations":[{"raw_affiliation_string":"CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France","institution_ids":["https://openalex.org/I37553959","https://openalex.org/I4387153146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135203827","display_name":"Flavian Theurel","orcid":"https://orcid.org/0009-0002-0337-3753","observed_orcids":["https://orcid.org/0009-0002-0337-3753"]},"institutions":[{"id":"https://openalex.org/I37553959","display_name":"Universit\u00e9 de technologie de belfort-montb\u00e9liard","ror":"https://ror.org/05bn3m307","country_code":"FR","type":"education","lineage":["https://openalex.org/I37553959"]},{"id":"https://openalex.org/I4387153146","display_name":"Connaissance & Intelligence Artificielle Distribu\u00e9es","ror":"https://ror.org/01ch21j41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I37553959","https://openalex.org/I4387153146","https://openalex.org/I4405253280"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Flavian Theurel","raw_affiliation_strings":["CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France"],"raw_orcid":"https://orcid.org/0009-0002-0337-3753","affiliations":[{"raw_affiliation_string":"CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France","institution_ids":["https://openalex.org/I37553959","https://openalex.org/I4387153146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079633095","display_name":"Wissam AlKendi","orcid":"https://orcid.org/0000-0003-4239-9964","observed_orcids":["https://orcid.org/0000-0003-4239-9964"]},"institutions":[{"id":"https://openalex.org/I37553959","display_name":"Universit\u00e9 de technologie de belfort-montb\u00e9liard","ror":"https://ror.org/05bn3m307","country_code":"FR","type":"education","lineage":["https://openalex.org/I37553959"]},{"id":"https://openalex.org/I4387153146","display_name":"Connaissance & Intelligence Artificielle Distribu\u00e9es","ror":"https://ror.org/01ch21j41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I37553959","https://openalex.org/I4387153146","https://openalex.org/I4405253280"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wissam Al-Kendi","raw_affiliation_strings":["CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France"],"raw_orcid":"https://orcid.org/0000-0003-4239-9964","affiliations":[{"raw_affiliation_string":"CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France","institution_ids":["https://openalex.org/I37553959","https://openalex.org/I4387153146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039132202","display_name":"Franck Gechter","orcid":"https://orcid.org/0000-0002-1172-603X","observed_orcids":["https://orcid.org/0000-0002-1172-603X"]},"institutions":[{"id":"https://openalex.org/I37553959","display_name":"Universit\u00e9 de technologie de belfort-montb\u00e9liard","ror":"https://ror.org/05bn3m307","country_code":"FR","type":"education","lineage":["https://openalex.org/I37553959"]},{"id":"https://openalex.org/I4387153146","display_name":"Connaissance & Intelligence Artificielle Distribu\u00e9es","ror":"https://ror.org/01ch21j41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I37553959","https://openalex.org/I4387153146","https://openalex.org/I4405253280"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Franck Gechter","raw_affiliation_strings":["CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France"],"raw_orcid":"https://orcid.org/0000-0002-1172-603X","affiliations":[{"raw_affiliation_string":"CIAD UR 7533, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard, 90010, Belfort cedex, France","institution_ids":["https://openalex.org/I37553959","https://openalex.org/I4387153146"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035521679"],"corresponding_institution_ids":["https://openalex.org/I37553959","https://openalex.org/I4387153146"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16973","issue":null,"first_page":"695","last_page":"711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0,"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/T10028","display_name":"Topic Modeling","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"handwriting recognition","score":0.8740000128746033},{"id":"https://openalex.org/keywords/transcription-of-historical-documents","display_name":"transcription of historical documents","score":0.8679999709129333},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8130000233650208},{"id":"https://openalex.org/keywords/qwen","display_name":"Qwen","score":0.7910000085830688},{"id":"https://openalex.org/keywords/daniel","display_name":"Daniel","score":0.9580000042915344},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.9369999766349792},{"id":"https://openalex.org/keywords/layout-segmentation","display_name":"layout segmentation","score":0.8220000267028809},{"id":"https://openalex.org/keywords/yolo","display_name":"YOLO","score":0.8289999961853027},{"id":"https://openalex.org/keywords/character-error-rate","display_name":"character error rate","score":0.7059999704360962},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.7360000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590999841690063},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6711999773979187},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6632999777793884},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5418999791145325},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510200023651123},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.41339999437332153},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.25040000677108765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-032-36033-5_41","doi":"https://doi.org/10.1007/978-3-032-36033-5_41","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-36033-5_41","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-05724725v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-05724725","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"20th International Conference on Document Analysis and Recognition : ICDAR 2026, Aug 2026, Vienne, Austria. pp.695-711, ⟨10.1007/978-3-032-36033-5_41⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1995929454","https://openalex.org/W2013962506","https://openalex.org/W2020407556","https://openalex.org/W2101105183","https://openalex.org/W2576852589","https://openalex.org/W2786974559","https://openalex.org/W2946759265","https://openalex.org/W2997154779","https://openalex.org/W4304013646","https://openalex.org/W4312263373","https://openalex.org/W4327810158","https://openalex.org/W4382202677","https://openalex.org/W4386185600","https://openalex.org/W4396665642","https://openalex.org/W4402671775","https://openalex.org/W4404840084","https://openalex.org/W4406196974","https://openalex.org/W4411348589","https://openalex.org/W6930707219"],"related_works":["https://openalex.org/W7160091047","https://openalex.org/W4410761886","https://openalex.org/W7221541577","https://openalex.org/W7140068890","https://openalex.org/W4406735876","https://openalex.org/W3002692706","https://openalex.org/W6911003973","https://openalex.org/W4394803700","https://openalex.org/W7203828598","https://openalex.org/W6885138107"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2026-08-23T00:00:00"}