{"id":"https://openalex.org/W4402353178","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651281","title":"CNN-Transformer Ensemble: Advancing Visual Piano Transcription with Global and Local Features","display_name":"CNN-Transformer Ensemble: Advancing Visual Piano Transcription with Global and Local Features","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353178","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651281"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651281","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109586744","display_name":"Yuqing Li","orcid":"https://orcid.org/0009-0006-9684-8867"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Li","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603607","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0001-5476-1524"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002684652","display_name":"Xianke Wang","orcid":"https://orcid.org/0000-0001-7037-9800"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianke Wang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079741694","display_name":"Ruimin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Wu","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108028872","display_name":"Wei Xu","orcid":"https://orcid.org/0009-0002-6353-9946"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications, Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.9872000217437744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.6347180008888245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6283804178237915},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.581802487373352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5279715657234192},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5201202630996704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42937377095222473},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37794798612594604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33241599798202515},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.16848692297935486},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14409145712852478},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08528187870979309},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08319202065467834},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08113384246826172}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.6347180008888245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6283804178237915},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.581802487373352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5279715657234192},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5201202630996704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42937377095222473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37794798612594604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33241599798202515},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.16848692297935486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14409145712852478},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08528187870979309},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08319202065467834},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08113384246826172},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651281","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W89231944","https://openalex.org/W129413713","https://openalex.org/W2044505737","https://openalex.org/W2105143211","https://openalex.org/W2151103935","https://openalex.org/W2163352848","https://openalex.org/W2182291269","https://openalex.org/W2194775991","https://openalex.org/W2560023338","https://openalex.org/W2788575351","https://openalex.org/W2962858109","https://openalex.org/W2982083293","https://openalex.org/W3016096605","https://openalex.org/W3035422918","https://openalex.org/W3081064203","https://openalex.org/W3094502228","https://openalex.org/W3160694286","https://openalex.org/W3209419355","https://openalex.org/W4383988462","https://openalex.org/W4385485032","https://openalex.org/W6603626069","https://openalex.org/W6729470292","https://openalex.org/W6745851314","https://openalex.org/W6798855526"],"related_works":["https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W4362512397","https://openalex.org/W587444722","https://openalex.org/W2022713566","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Piano":[0],"transcription":[1,24,53,103,138],"is":[2],"a":[3,49,109],"significant":[4],"problem":[5],"in":[6,38],"music":[7,19,140],"information":[8,141],"retrieval,":[9],"which":[10],"aims":[11],"to":[12,134],"infer":[13],"the":[14,43,72,76,83,98,101,115,127],"note":[15],"sequence":[16],"from":[17],"recorded":[18],"signals.":[20],"Recently,":[21],"visual":[22,51,102,136],"piano":[23,44,52,73,137],"heavily":[25],"relies":[26],"on":[27,114,122],"Convolutional":[28],"Neural":[29],"Networks":[30],"(CNNs)":[31],"for":[32],"local":[33,69,89],"feature":[34],"detection,":[35],"facing":[36],"challenges":[37],"capturing":[39],"global":[40,80,92],"features":[41,70,81,90,93],"of":[42,71,100,112],"keyboard.":[45,84],"Therefore,":[46],"we":[47],"propose":[48],"novel":[50],"model":[54,87,107],"that":[55],"integrates":[56,88],"CNN":[57,62],"and":[58,67,91,118,131],"transformer":[59,77],"branches.":[60],"The":[61,85],"branch":[63,78],"has":[64],"inductive":[65],"bias":[66],"extracts":[68],"key,":[74],"while":[75],"aggregates":[79],"over":[82],"proposed":[86],"at":[94],"different":[95],"resolutions,":[96],"enhancing":[97],"performance":[99],"model.":[104],"Finally,":[105],"our":[106],"achieves":[108],"remarkable":[110],"F1-score":[111],"92.35%":[113],"OMAPS2":[116],"dataset":[117],"attains":[119],"state-of-the-art":[120],"results":[121],"other":[123],"datasets.":[124],"This":[125],"substantiates":[126],"model\u2019s":[128],"innovative":[129],"approach":[130],"its":[132],"potential":[133],"advance":[135],"within":[139],"retrieval.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
