{"id":"https://openalex.org/W3193915386","doi":"https://doi.org/10.1145/3463945.3469056","title":"Residual Recurrent CRNN for End-to-End Optical Music Recognition on Monophonic Scores","display_name":"Residual Recurrent CRNN for End-to-End Optical Music Recognition on Monophonic Scores","publication_year":2021,"publication_date":"2021-08-21","ids":{"openalex":"https://openalex.org/W3193915386","doi":"https://doi.org/10.1145/3463945.3469056","mag":"3193915386"},"language":"en","primary_location":{"id":"doi:10.1145/3463945.3469056","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3463945.3469056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding","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/A5072352550","display_name":"Aozhi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Aozhi Liu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030047091","display_name":"Lipei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lipei Zhang","raw_affiliation_strings":["University of London, London, China"],"affiliations":[{"raw_affiliation_string":"University of London, London, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065700757","display_name":"Yaqi Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqi Mei","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017301310","display_name":"Baoqiang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoqiang Han","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021081741","display_name":"Zifeng Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zifeng Cai","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058852815","display_name":"Zhaohua Zhu","orcid":"https://orcid.org/0000-0003-2883-0252"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohua Zhu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070173803","display_name":"Jing Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072352550"],"corresponding_institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":1.2189,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79175118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9876000285148621,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.816912055015564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720293998718262},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.767927348613739},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6990646123886108},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6174522638320923},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6047331094741821},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5962871313095093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.543531060218811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5324906706809998},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46733319759368896},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4664067327976227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42571526765823364},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2619473934173584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14092206954956055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06830048561096191}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.816912055015564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720293998718262},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.767927348613739},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6990646123886108},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6174522638320923},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6047331094741821},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5962871313095093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.543531060218811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5324906706809998},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46733319759368896},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4664067327976227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42571526765823364},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2619473934173584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14092206954956055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06830048561096191},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3463945.3469056","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3463945.3469056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W1934184906","https://openalex.org/W2045220951","https://openalex.org/W2098152393","https://openalex.org/W2127141656","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2406188329","https://openalex.org/W2604021907","https://openalex.org/W2738024508","https://openalex.org/W2787229240","https://openalex.org/W2796517058","https://openalex.org/W2902632486"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W2790400419"],"abstract_inverted_index":{"One":[0],"of":[1,4,15,62,77,98],"the":[2,5,13,16,83,87,96,99,103,124],"challenges":[3],"Optical":[6],"Music":[7],"Recognition":[8],"task":[9],"is":[10,46],"to":[11,73,82,101],"transcript":[12],"symbols":[14,80],"camera-captured":[17],"images":[18],"into":[19],"digital":[20],"music":[21,79],"notations.":[22],"Previous":[23],"end-to-end":[24,126],"model":[25,100],"which":[26,118],"was":[27],"developed":[28],"as":[29],"a":[30,48,60,69,75,112],"Convolutional":[31,65,92,129],"Recurrent":[32,64,91,130],"Neural":[33,66,131],"Network":[34,67],"does":[35],"not":[36],"explore":[37],"sufficient":[38],"contextual":[39],"information":[40],"from":[41],"full":[42],"scales":[43],"and":[44],"there":[45],"still":[47],"large":[49],"room":[50],"for":[51],"improvement.":[52],"We":[53],"propose":[54],"an":[55],"innovative":[56],"framework":[57],"that":[58,120],"combines":[59],"block":[61,93],"Residual":[63,90],"with":[68],"recurrent":[70],"Encoder-Decoder":[71],"network":[72],"map":[74],"sequence":[76],"monophonic":[78],"corresponding":[81],"notations":[84],"present":[85],"in":[86],"image.":[88],"The":[89,106],"can":[94],"improve":[95],"ability":[97],"enrich":[102],"context":[104],"information.":[105],"experiment":[107],"results":[108],"are":[109],"benchmarked":[110],"against":[111],"publicly":[113],"available":[114],"dataset":[115],"called":[116],"CAMERA-PRIMUS,":[117],"demonstrates":[119],"our":[121],"approach":[122],"surpass":[123],"state-of-the-art":[125],"method":[127],"using":[128],"Network.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}