{"id":"https://openalex.org/W7119511988","doi":"https://doi.org/10.1007/s11263-025-02654-6","title":"End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Music","display_name":"End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Music","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7119511988","doi":"https://doi.org/10.1007/s11263-025-02654-6"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02654-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02654-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02654-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02654-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051070601","display_name":"Antonio R\u00edos-Vila","orcid":"https://orcid.org/0000-0002-7770-9726"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Antonio R\u00edos-Vila","raw_affiliation_strings":["Pattern Recognition and Artificial Intelligence Group, University of Alicante, Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Artificial Intelligence Group, University of Alicante, Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085151278","display_name":"Jorge Calvo-Zaragoza","orcid":"https://orcid.org/0000-0003-3183-2232"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jorge Calvo-Zaragoza","raw_affiliation_strings":["Pattern Recognition and Artificial Intelligence Group, University of Alicante, Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Artificial Intelligence Group, University of Alicante, Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122351937","display_name":"David Rizo","orcid":null},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Rizo","raw_affiliation_strings":["Instituto Superior de Ense\u00f1anzas Art\u00edsticas de la Comunidad Alicante, Alicante, Spain","Pattern Recognition and Artificial Intelligence Group, University of Alicante, Alicante, Spain"],"affiliations":[{"raw_affiliation_string":"Instituto Superior de Ense\u00f1anzas Art\u00edsticas de la Comunidad Alicante, Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]},{"raw_affiliation_string":"Pattern Recognition and Artificial Intelligence Group, University of Alicante, Alicante, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122354113","display_name":"Thierry Paquet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thierry Paquet","raw_affiliation_strings":["LITIS Laboratory - EA 4108, University of Rouen, Rouen, France"],"affiliations":[{"raw_affiliation_string":"LITIS Laboratory - EA 4108, University of Rouen, Rouen, France","institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051070601"],"corresponding_institution_ids":["https://openalex.org/I130194489"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05894962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0020000000949949026,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0008999999845400453,"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/limiting","display_name":"Limiting","score":0.5795000195503235},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5131000280380249},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43160000443458557},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.3783000111579895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37040001153945923},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.36800000071525574},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.33629998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398999929428101},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44670000672340393},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.33489999175071716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11263-025-02654-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02654-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02654-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05379076v1","is_oa":false,"landing_page_url":"https://normandie-univ.hal.science/hal-05379076","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Computer Vision, 2026, 134 (2), pp.49. &#x27E8;10.1007/s11263-025-02654-6&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02654-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02654-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02654-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6934186220169067}],"awards":[{"id":"https://openalex.org/G2379885196","display_name":null,"funder_award_id":"CISEJI/2023/9","funder_id":"https://openalex.org/F4320336489","funder_display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana"},{"id":"https://openalex.org/G276391773","display_name":null,"funder_award_id":"ACIF/2021","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"},{"id":"https://openalex.org/G2827925112","display_name":null,"funder_award_id":"ACIF/","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"},{"id":"https://openalex.org/G3477480002","display_name":null,"funder_award_id":"ACIF/2021/356","funder_id":"https://openalex.org/F4320336489","funder_display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana"},{"id":"https://openalex.org/G7634882126","display_name":null,"funder_award_id":"CIBEFP/2022/19","funder_id":"https://openalex.org/F4320336489","funder_display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana"}],"funders":[{"id":"https://openalex.org/F4320307502","display_name":"American Concrete Institute Foundation","ror":"https://ror.org/02a207p76"},{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"},{"id":"https://openalex.org/F4320336489","display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7119511988.pdf","grobid_xml":"https://content.openalex.org/works/W7119511988.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W166419126","https://openalex.org/W2030863126","https://openalex.org/W2045220951","https://openalex.org/W2131604793","https://openalex.org/W2141507078","https://openalex.org/W2157590796","https://openalex.org/W2576000810","https://openalex.org/W2785680402","https://openalex.org/W2785881071","https://openalex.org/W2796517058","https://openalex.org/W2900768105","https://openalex.org/W2917211058","https://openalex.org/W2968036310","https://openalex.org/W2969230409","https://openalex.org/W2983390797","https://openalex.org/W2995210048","https://openalex.org/W2995301500","https://openalex.org/W3091861134","https://openalex.org/W3115736077","https://openalex.org/W3138516171","https://openalex.org/W3159443578","https://openalex.org/W3197999066","https://openalex.org/W3198091796","https://openalex.org/W3201139606","https://openalex.org/W4224434037","https://openalex.org/W4283276297","https://openalex.org/W4283332714","https://openalex.org/W4286266857","https://openalex.org/W4294811919","https://openalex.org/W4312233877","https://openalex.org/W4312443924","https://openalex.org/W4313051467","https://openalex.org/W4313065545","https://openalex.org/W4327974172","https://openalex.org/W4360841345","https://openalex.org/W4372260009","https://openalex.org/W4378472468","https://openalex.org/W4382602926","https://openalex.org/W4385990962","https://openalex.org/W4402343076","https://openalex.org/W4402397206","https://openalex.org/W4402418891","https://openalex.org/W4402423721"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Optical":[1],"Music":[2],"Recognition":[3],"(OMR)":[4],"has":[5],"made":[6,110],"significant":[7,211],"progress":[8],"since":[9],"its":[10],"inception,":[11],"with":[12,89,158,174,205],"various":[13],"approaches":[14,32],"now":[15],"capable":[16],"of":[17,64,140,167,216],"accurately":[18],"transcribing":[19,40],"music":[20,95,105,190],"scores":[21,191],"into":[22],"digital":[23],"formats.":[24],"Despite":[25],"these":[26],"advancements,":[27],"most":[28,142],"so-called":[29],"end-to-end":[30,75],"OMR":[31,79,147,177],"still":[33],"rely":[34],"on":[35],"multi-stage":[36],"processing":[37],"pipelines":[38],"for":[39,51,77],"full-page":[41,189],"score":[42,96],"images,":[43],"which":[44,85,120,137],"entails":[45],"challenges":[46],"such":[47,65],"as":[48],"the":[49,61,72,114,117,131,141,146,195,206,214],"need":[50],"dedicated":[52],"layout":[53],"analysis":[54],"and":[55,98,116,161,202],"specific":[56],"annotated":[57],"data,":[58,160],"thereby":[59],"limiting":[60],"general":[62],"applicability":[63],"methods.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"present":[71],"first":[73,153],"truly":[74],"approach":[76,171],"page-level":[78],"in":[80,103,145,154,198],"complex":[81,143],"layouts.":[82],"Our":[83,170],"system,":[84],"combines":[86],"convolutional":[87],"layers":[88],"autoregressive":[90],"Transformers,":[91],"processes":[92],"an":[93],"entire":[94],"page":[97],"outputs":[99],"a":[100,104,155,210],"complete":[101],"transcription":[102],"encoding":[106],"format.":[107],"This":[108,149],"is":[109,138,151,172],"possible":[111],"by":[112],"both":[113,199],"architecture":[115],"training":[118],"procedure,":[119],"utilizes":[121],"curriculum":[122],"learning":[123],"through":[124],"incremental":[125],"synthetic":[126,159],"data":[127],"generation.":[128],"We":[129],"evaluate":[130],"proposed":[132],"system":[133,184],"using":[134],"pianoform":[135],"corpora,":[136],"one":[139],"sources":[144],"literature.":[148],"evaluation":[150],"conducted":[152],"controlled":[156],"scenario":[157],"subsequently":[162],"against":[163],"two":[164],"real-world":[165],"corpora":[166],"varying":[168],"conditions.":[169],"compared":[173],"leading":[175],"commercial":[176,196],"software.":[178],"The":[179],"results":[180],"demonstrate":[181],"that":[182],"our":[183],"not":[185],"only":[186],"successfully":[187],"transcribes":[188],"but":[192],"also":[193],"outperforms":[194],"tool":[197],"zero-shot":[200],"settings":[201],"after":[203],"fine-tuning":[204],"target":[207],"domain,":[208],"representing":[209],"contribution":[212],"to":[213],"field":[215],"OMR.":[217]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2026-01-09T00:00:00"}
