{"id":"https://openalex.org/W3081064203","doi":"https://doi.org/10.1145/3409501.3409540","title":"Robust Piano Music Transcription Based on Computer Vision","display_name":"Robust Piano Music Transcription Based on Computer Vision","publication_year":2020,"publication_date":"2020-07-03","ids":{"openalex":"https://openalex.org/W3081064203","doi":"https://doi.org/10.1145/3409501.3409540","mag":"3081064203"},"language":"en","primary_location":{"id":"doi:10.1145/3409501.3409540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409501.3409540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference &amp; 2020 3rd International Conference on Big Data and Artificial Intelligence","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/A5100691319","display_name":"Jun Li","orcid":"https://orcid.org/0000-0002-6239-2922"},"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":true,"raw_author_name":"Jun Li","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080649483","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-6616-3633"},"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, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207935","display_name":"Yong Cao","orcid":"https://orcid.org/0000-0002-3889-0382"},"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":"Yong Cao","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431757","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-2187-8125"},"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 Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056643192","display_name":"Wenqing Cheng","orcid":"https://orcid.org/0000-0001-7840-1195"},"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":"Wenqing Cheng","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100691319"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61125741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.9951000213623047,"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/piano","display_name":"Piano","score":0.8472648859024048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6901172995567322},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5754776000976562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5492300391197205},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46416595578193665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3864303231239319},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1227739155292511}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8472648859024048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901172995567322},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5754776000976562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5492300391197205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46416595578193665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3864303231239319},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1227739155292511},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3409501.3409540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409501.3409540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference &amp; 2020 3rd International Conference on Big Data and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W173399573","https://openalex.org/W1975962343","https://openalex.org/W2105143211","https://openalex.org/W2182291269","https://openalex.org/W2183341477","https://openalex.org/W2229159429","https://openalex.org/W2247760547","https://openalex.org/W2299180476","https://openalex.org/W2560023338","https://openalex.org/W2788575351","https://openalex.org/W2790768712","https://openalex.org/W2921484047","https://openalex.org/W6600224776","https://openalex.org/W6661645069","https://openalex.org/W6682193241","https://openalex.org/W6728773792","https://openalex.org/W6729470292","https://openalex.org/W6730342312"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2755342338","https://openalex.org/W2021592657","https://openalex.org/W2229312674","https://openalex.org/W3116076068","https://openalex.org/W2160136308","https://openalex.org/W2168822216"],"abstract_inverted_index":{"Recently,":[0],"automatic":[1,24],"music":[2,8,25],"transcription":[3,26,73,96],"aiming":[4],"to":[5,18,36,45,87],"convert":[6],"acoustic":[7,29],"signals":[9],"into":[10],"symbolic":[11],"notations":[12],"attracts":[13],"increasing":[14],"attention.":[15],"In":[16,64,98],"order":[17],"deal":[19],"with":[20],"the":[21,38,50,61,79,89,94,107,125,135,146],"challenges":[22],"of":[23,102,109,127],"based":[27],"on":[28,133],"information,":[30],"traditional":[31],"approaches":[32],"adopt":[33],"hough":[34,51],"transform":[35,52],"locate":[37],"piano":[39,72,80,111,121],"keyboard":[40,81],"and":[41,53,83,138,141],"a":[42,69,84,116],"weak":[43,54],"classifier":[44,55,86],"detect":[46,88],"pressed":[47,90],"keys.":[48],"However,":[49],"show":[56],"insufficient":[57],"detection":[58,82],"ability":[59],"in":[60,100,106],"changing":[62],"environment.":[63],"this":[65],"paper,":[66],"we":[67,113,130,139],"devise":[68],"robust":[70],"visual":[71,110,120],"system":[74,143],"using":[75],"semantic":[76],"segmentation":[77],"for":[78,119],"CNN-based":[85],"keys,":[91],"which":[92],"improves":[93],"frame-level":[95],"results.":[97],"addition,":[99],"view":[101],"lacking":[103],"public":[104],"datasets":[105],"field":[108],"transcription,":[112],"further":[114],"propose":[115],"new":[117],"dataset":[118,137],"transcription.":[122],"To":[123],"demonstrate":[124],"effectiveness":[126],"our":[128,142],"system,":[129],"evaluate":[131],"it":[132],"both":[134],"published":[136],"proposed,":[140],"significantly":[144],"outperforms":[145],"state-of-the-art":[147],"approaches.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
