{"id":"https://openalex.org/W3006654639","doi":"https://doi.org/10.1109/tmm.2020.2973831","title":"Using Cell Phone Pictures of Sheet Music To Retrieve MIDI Passages","display_name":"Using Cell Phone Pictures of Sheet Music To Retrieve MIDI Passages","publication_year":2020,"publication_date":"2020-02-14","ids":{"openalex":"https://openalex.org/W3006654639","doi":"https://doi.org/10.1109/tmm.2020.2973831","mag":"3006654639"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2020.2973831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2973831","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.11724","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"T.J. Tsai","orcid":"https://orcid.org/0000-0002-0879-5931"},"institutions":[{"id":"https://openalex.org/I133543626","display_name":"Harvey Mudd College","ror":"https://ror.org/025ecfn45","country_code":"US","type":"education","lineage":["https://openalex.org/I133543626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"T.J. Tsai","raw_affiliation_strings":["Harvey Mudd College, Claremont, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0879-5931","affiliations":[{"raw_affiliation_string":"Harvey Mudd College, Claremont, CA, USA","institution_ids":["https://openalex.org/I133543626"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel Yang","orcid":"https://orcid.org/0000-0002-7684-9057"},"institutions":[{"id":"https://openalex.org/I133543626","display_name":"Harvey Mudd College","ror":"https://ror.org/025ecfn45","country_code":"US","type":"education","lineage":["https://openalex.org/I133543626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Yang","raw_affiliation_strings":["Harvey Mudd College, Claremont, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7684-9057","affiliations":[{"raw_affiliation_string":"Harvey Mudd College, Claremont, CA, USA","institution_ids":["https://openalex.org/I133543626"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengyi Shan","orcid":"https://orcid.org/0000-0002-1520-5979"},"institutions":[{"id":"https://openalex.org/I133543626","display_name":"Harvey Mudd College","ror":"https://ror.org/025ecfn45","country_code":"US","type":"education","lineage":["https://openalex.org/I133543626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengyi Shan","raw_affiliation_strings":["Harvey Mudd College, Claremont, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1520-5979","affiliations":[{"raw_affiliation_string":"Harvey Mudd College, Claremont, CA, USA","institution_ids":["https://openalex.org/I133543626"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thitaree Tanprasert","orcid":"https://orcid.org/0000-0002-5606-2433"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Thitaree Tanprasert","raw_affiliation_strings":["The University of British Columbia, Vancouver, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5606-2433","affiliations":[{"raw_affiliation_string":"The University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":null,"display_name":"Teerapat Jenrungrot","orcid":"https://orcid.org/0000-0002-8562-7210"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teerapat Jenrungrot","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8562-7210","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133543626"],"apc_list":null,"apc_paid":null,"fwci":1.0635,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.76062961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"22","issue":"12","first_page":"3115","last_page":"3127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8903999924659729,"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":0.8903999924659729,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.02850000001490116,"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":0.010599999688565731,"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/midi","display_name":"MIDI","score":0.8021000027656555},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5716000199317932},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.570900022983551},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5443999767303467},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4185999929904938},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4020000100135803},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38679999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295999765396118},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.8021000027656555},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5716000199317932},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5171999931335449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47110000252723694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C147942929","wikidata":"https://www.wikidata.org/wiki/Q210820","display_name":"Camera phone","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2020.2973831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2973831","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2004.11724","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.11724","pdf_url":"https://arxiv.org/pdf/2004.11724","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.11724","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.11724","pdf_url":"https://arxiv.org/pdf/2004.11724","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1986823487","https://openalex.org/W2000304248","https://openalex.org/W2007972815","https://openalex.org/W2031787046","https://openalex.org/W2038510921","https://openalex.org/W2106277773","https://openalex.org/W2119605622","https://openalex.org/W2124386111","https://openalex.org/W2133059825","https://openalex.org/W2155803963","https://openalex.org/W2172987025","https://openalex.org/W2194187530","https://openalex.org/W2340600463","https://openalex.org/W2562417371","https://openalex.org/W2600067905","https://openalex.org/W2725249286","https://openalex.org/W2739344165","https://openalex.org/W2785680402","https://openalex.org/W2787426902","https://openalex.org/W2795705148","https://openalex.org/W2811221988","https://openalex.org/W2887755027","https://openalex.org/W2888313892","https://openalex.org/W2889024947","https://openalex.org/W2889118961","https://openalex.org/W2890559714","https://openalex.org/W2897135094","https://openalex.org/W2898403805","https://openalex.org/W2902071833","https://openalex.org/W2902632486","https://openalex.org/W2904263947","https://openalex.org/W2906259846","https://openalex.org/W2921147815","https://openalex.org/W2954161205","https://openalex.org/W2963351448","https://openalex.org/W2963801643","https://openalex.org/W2964172523","https://openalex.org/W2969230409","https://openalex.org/W2972750926","https://openalex.org/W6608257652","https://openalex.org/W6630444114","https://openalex.org/W6639102338","https://openalex.org/W6639824700","https://openalex.org/W6677994088","https://openalex.org/W6712658070","https://openalex.org/W6714054724","https://openalex.org/W6732196190","https://openalex.org/W6733312593","https://openalex.org/W6742368143","https://openalex.org/W6750227808","https://openalex.org/W6752214466","https://openalex.org/W6753035467","https://openalex.org/W6757091677","https://openalex.org/W6770058728","https://openalex.org/W6770152511"],"related_works":[],"abstract_inverted_index":{"This":[0,35],"article":[1],"investigates":[2],"a":[3,9,15,20,25,44,51,75,80,103,122,174,181,196,212],"cross-modal":[4],"retrieval":[5],"problem":[6,36],"in":[7,93],"which":[8,83],"user":[10],"would":[11],"like":[12],"to":[13,90,195],"retrieve":[14],"passage":[16],"of":[17,29,32,66,87,109,160,176,184,200,217,223,245],"music":[18,116,232],"from":[19,204],"MIDI":[21,97,137],"file":[22],"by":[23],"taking":[24],"cell":[26,63,139],"phone":[27,64,140],"picture":[28],"several":[30],"lines":[31,92],"sheet":[33,67,94,115],"music.":[34,68,95],"is":[37,50,56,163],"challenging":[38],"for":[39,130],"two":[40],"reasons:":[41],"it":[42,49,165],"has":[43,166,219],"significant":[45],"runtime":[46,222],"constraint":[47],"since":[48],"user-facing":[52],"application,":[53],"and":[54,113,138,226,235,243],"there":[55],"very":[57],"little":[58],"relevant":[59],"training":[60,182],"data":[61],"containing":[62],"images":[65,203],"To":[69],"solve":[70],"this":[71],"problem,":[72],"we":[73,148,188],"introduce":[74],"novel":[76],"feature":[77],"representation":[78,98],"called":[79],"bootleg":[81,104,123,146],"score":[82,105,124,216],"encodes":[84],"the":[85,114,136,151],"position":[86],"noteheads":[88],"relative":[89],"staff":[91],"The":[96,156],"can":[99,118,149],"be":[100,119],"converted":[101,120,144],"into":[102,121,145],"using":[106,125,153],"deterministic":[107],"rules":[108],"Western":[110],"musical":[111,207],"notation,":[112],"image":[117,141],"classical":[126],"computer":[127],"vision":[128],"techniques":[129],"detecting":[131],"simple":[132],"geometrical":[133],"shapes.":[134],"Once":[135],"have":[142],"been":[143],"scores,":[147],"estimate":[150],"alignment":[152],"dynamic":[154],"programming.":[155],"most":[157],"notable":[158],"characteristic":[159],"our":[161,191,246],"system":[162,192,210],"that":[164,190],"no":[167],"trainable":[168],"weights":[169],"at":[170],"all":[171],"-":[172],"only":[173],"set":[175,183,199],"about":[177],"40":[178],"hyperparameters.":[179],"With":[180],"just":[185],"400":[186],"images,":[187],"show":[189],"generalizes":[193],"well":[194],"much":[197],"larger":[198],"1600":[201],"test":[202,213],"160":[205],"unseen":[206],"scores.":[208],"Our":[209],"achieves":[211],"F":[214],"measure":[215],"0.89,":[218],"an":[220],"average":[221],"0.90":[224],"seconds,":[225],"outperforms":[227],"baseline":[228],"systems":[229],"based":[230],"on":[231],"object":[233],"detection":[234],"sheet-audio":[236],"alignment.":[237],"We":[238],"provide":[239],"extensive":[240],"experimental":[241],"validation":[242],"analysis":[244],"system.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2020-02-24T00:00:00"}