{"id":"https://openalex.org/W6968686483","doi":"https://doi.org/10.5281/zenodo.14877483","title":"Toward a More Complete OMR Solution","display_name":"Toward a More Complete OMR Solution","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968686483","doi":"https://doi.org/10.5281/zenodo.14877483"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877483","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877483","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Guang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Muru Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muru Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yanming Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanming Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Noah A. Smith","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noah A. Smith","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9545999765396118,"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":0.9545999765396118,"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":0.01759999990463257,"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":0.0032999999821186066,"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/notation","display_name":"Notation","score":0.8949000239372253},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.7398999929428101},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6879000067710876},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5838000178337097},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5792999863624573},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4713999927043915}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.8949000239372253},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.7398999929428101},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6879000067710876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502000093460083},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5838000178337097},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5792999863624573},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4185999929904938},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3921999931335449},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.34869998693466187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877483","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877483","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Optical":[0],"music":[1,7,28,42,79,91],"recognition":[2],"(OMR)":[3],"aims":[4],"to":[5,14,125],"convert":[6],"notation":[8,29,43,50,70,111],"into":[9,40],"digital":[10],"formats.":[11],"One":[12],"approach":[13],"tackle":[15],"OMR":[16,164],"is":[17,123],"through":[18],"a":[19,41,72,90,104,145,161],"multi-stage":[20],"pipeline,":[21],"where":[22],"the":[23,32,63,110,135,139],"system":[24],"first":[25],"detects":[26],"visual":[27],"elements":[30],"in":[31,144],"image":[33],"(object":[34],"detection)":[35],"and":[36,81,141],"then":[37],"assembles":[38],"them":[39],"(notation":[44],"assembly).":[45],"Most":[46],"previous":[47],"work":[48],"on":[49,62,95,115,130],"assembly":[51,112,142],"unrealistically":[52],"assumes":[53],"perfect":[54,131],"object":[55,92],"detection.":[56],"In":[57],"this":[58,121],"study,":[59],"we":[60,82,88,102],"focus":[61],"MUSCIMA++":[64],"v2.0":[65],"dataset,":[66],"which":[67,97],"represents":[68],"musical":[69],"as":[71],"graph":[73],"with":[74,152],"pairwise":[75],"relationships":[76],"among":[77],"detected":[78],"objects,":[80],"consider":[83],"both":[84],"stages":[85,143],"together.":[86],"First,":[87],"introduce":[89,103],"detector":[93],"based":[94,114],"YOLOv8,":[96],"improves":[98],"detection":[99,116,132,140],"performance.":[100],"Second,":[101],"supervised":[105],"training":[106],"pipeline":[107],"that":[108,120],"completes":[109],"stage":[113],"output.":[117],"We":[118],"find":[119],"model":[122],"able":[124],"outperform":[126],"existing":[127],"models":[128],"trained":[129],"output,":[133],"showing":[134],"benefit":[136],"of":[137],"considering":[138],"more":[146,162],"holistic":[147],"way.":[148],"These":[149],"findings,":[150],"together":[151],"our":[153],"novel":[154],"evaluation":[155],"metric,":[156],"are":[157],"important":[158],"steps":[159],"toward":[160],"complete":[163],"solution.":[165]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}