{"id":"https://openalex.org/W4414359198","doi":"https://doi.org/10.24963/ijcai.2025/1138","title":"Pay Attention to the Keys: Visual Piano Transcription Using Transformers","display_name":"Pay Attention to the Keys: Visual Piano Transcription Using Transformers","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359198","doi":"https://doi.org/10.24963/ijcai.2025/1138"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1138","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5114674286","display_name":"Uros Zivanovic","orcid":null},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Uros Zivanovic","raw_affiliation_strings":["University of Trieste"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trieste","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094196177","display_name":"Ivan Pilkov","orcid":"https://orcid.org/0009-0002-7881-8139"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ivan Pilkov","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University Linz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University Linz","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062774572","display_name":"Carlos Cancino-Chac\u00f3n","orcid":"https://orcid.org/0000-0001-5770-7005"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Carlos Cancino-Chac\u00f3n","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University Linz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University Linz","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"10243","last_page":"10251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9940000176429749,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9657999873161316,"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":0.8608999848365784},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.7864000201225281},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6794000267982483},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5264000296592712},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3628000020980835}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8608999848365784},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.7864000201225281},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6794000267982483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585999727249146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5939000248908997},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4595000147819519},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1138","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on 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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"piano":[1,14,27,74],"transcription":[2],"(VPT)":[3],"is":[4,55],"the":[5,26,39,58,100,103,111],"task":[6],"of":[7,12,25,64,67,73],"obtaining":[8],"a":[9,13,22,34],"symbolic":[10],"representation":[11],"performance":[15],"from":[16,21],"visual":[17],"information":[18],"alone":[19],"(e.g.,":[20],"top-down":[23],"video":[24,69],"keyboard).":[28],"In":[29],"this":[30,92],"work":[31],"we":[32],"propose":[33],"VPT":[35],"system":[36,54,98],"based":[37,47],"on":[38,48,57,102,110],"vision":[40],"transformer":[41],"(ViT),":[42],"which":[43,85],"surpasses":[44],"previous":[45],"methods":[46],"convolutional":[49],"neural":[50],"networks":[51],"(CNNs).":[52],"Our":[53],"trained":[56],"newly":[59],"introduced":[60],"R3":[61,112],"dataset,":[62],"consisting":[63],"ca.~31":[65],"hours":[66],"synchronized":[68],"and":[70,109,117],"MIDI":[71],"recordings":[72],"performances.":[75],"We":[76,94],"additionally":[77],"introduce":[78],"an":[79],"approach":[80],"to":[81],"predict":[82],"note":[83],"offsets,":[84],"has":[86],"not":[87],"been":[88],"previously":[89],"explored":[90],"in":[91],"context.":[93],"show":[95],"that":[96],"our":[97],"outperforms":[99],"state-of-the-art":[101],"PianoYT":[104],"dataset":[105,113],"for":[106,114],"onset":[107],"prediction":[108],"both":[115],"onsets":[116],"offsets.":[118]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}