{"id":"https://openalex.org/W3163425395","doi":"https://doi.org/10.23919/eusipco54536.2021.9616287","title":"Multi-modal Conditional Bounding Box Regression for Music Score Following","display_name":"Multi-modal Conditional Bounding Box Regression for Music Score Following","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3163425395","doi":"https://doi.org/10.23919/eusipco54536.2021.9616287","mag":"3163425395"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616287","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616287","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5081334651","display_name":"Florian Henkel","orcid":null},"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":true,"raw_author_name":"Florian Henkel","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"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":"Gerhard Widmer","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081334651"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":0.6881,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71591672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"356","last_page":"360"},"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":0.9955000281333923,"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":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.6591823697090149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5518190264701843},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5250170826911926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.460636705160141},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.43526941537857056},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.43314558267593384},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41138866543769836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3575981855392456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591823697090149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5518190264701843},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5250170826911926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.460636705160141},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.43526941537857056},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.43314558267593384},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41138866543769836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3575981855392456},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616287","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616287","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6084202377","display_name":null,"funder_award_id":"670035","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W93815243","https://openalex.org/W185944909","https://openalex.org/W639708223","https://openalex.org/W1836465849","https://openalex.org/W2033918847","https://openalex.org/W2064675550","https://openalex.org/W2120202836","https://openalex.org/W2120591931","https://openalex.org/W2125930537","https://openalex.org/W2136848157","https://openalex.org/W2144234122","https://openalex.org/W2146302296","https://openalex.org/W2302548814","https://openalex.org/W2407138574","https://openalex.org/W2478051194","https://openalex.org/W2518108298","https://openalex.org/W2570343428","https://openalex.org/W2613718673","https://openalex.org/W2760103357","https://openalex.org/W2765532459","https://openalex.org/W2883727669","https://openalex.org/W2890559714","https://openalex.org/W2908510526","https://openalex.org/W2963037989","https://openalex.org/W2963116179","https://openalex.org/W2963263347","https://openalex.org/W2963285578","https://openalex.org/W2963421527","https://openalex.org/W2963855133","https://openalex.org/W2980356815","https://openalex.org/W2982297432","https://openalex.org/W3015045227","https://openalex.org/W3117303186","https://openalex.org/W3120129399","https://openalex.org/W3186213520","https://openalex.org/W4287710774","https://openalex.org/W4297824567","https://openalex.org/W6603836127","https://openalex.org/W6607608197","https://openalex.org/W6620707391","https://openalex.org/W6638667902","https://openalex.org/W6677851704","https://openalex.org/W6678818196","https://openalex.org/W6685562342","https://openalex.org/W6714201907","https://openalex.org/W6726497184","https://openalex.org/W6732196190","https://openalex.org/W6740674931","https://openalex.org/W6753035467","https://openalex.org/W6757817989","https://openalex.org/W6768985362","https://openalex.org/W6775760072","https://openalex.org/W6780226713","https://openalex.org/W6781255595"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,33,63,73,98],"problem":[4],"of":[5,32,104],"sheet-image-based":[6,76],"on-line":[7],"audio-to-score":[8],"alignment":[9,99],"also":[10],"known":[11],"as":[12,79,81,112],"score":[13,39,77],"following.":[14],"Drawing":[15],"inspiration":[16],"from":[17,72],"object":[18],"detection,":[19],"a":[20,37,48,56,102,113],"conditional":[21],"neural":[22],"network":[23],"architecture":[24],"is":[25,66],"proposed":[26,88],"that":[27],"directly":[28],"predicts":[29],"x,y":[30],"coordinates":[31],"matching":[34],"positions":[35],"in":[36,45],"complete":[38],"sheet":[40],"image":[41],"at":[42],"each":[43],"point":[44],"time":[46],"for":[47,75],"given":[49],"musical":[50],"performance.":[51],"Experiments":[52],"are":[53],"conducted":[54],"on":[55,101],"synthetic":[57],"polyphonic":[58],"piano":[59,106],"benchmark":[60],"dataset":[61],"and":[62,94],"new":[64,91],"method":[65],"compared":[67],"to":[68],"several":[69],"existing":[70],"approaches":[71],"literature":[74],"following":[78],"well":[80],"an":[82],"Optical":[83],"Music":[84],"Recognition":[85],"baseline.":[86],"The":[87],"approach":[89],"achieves":[90],"state-of-the-art":[92],"results":[93],"furthermore":[95],"significantly":[96],"improves":[97],"performance":[100],"set":[103],"real-world":[105],"recordings":[107],"by":[108],"applying":[109],"Impulse":[110],"Responses":[111],"data":[114],"augmentation":[115],"technique.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}