{"id":"https://openalex.org/W4379805453","doi":"https://doi.org/10.1145/3587819.3590968","title":"Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems","display_name":"Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379805453","doi":"https://doi.org/10.1145/3587819.3590968"},"language":"en","primary_location":{"id":"doi:10.1145/3587819.3590968","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3587819.3590968","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587819.3590968","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM Multimedia Systems Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3587819.3590968","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046035965","display_name":"Luis Carvalho","orcid":"https://orcid.org/0000-0002-1344-3463"},"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":"Luis Carvalho","raw_affiliation_strings":["Johannes Kepler University, Linz, Austria"],"raw_orcid":"https://orcid.org/0000-0002-1344-3463","affiliations":[{"raw_affiliation_string":"Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092114801","display_name":"Tobias Wash\u00fcttl","orcid":"https://orcid.org/0009-0001-9947-6783"},"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":"Tobias Wash\u00fcttl","raw_affiliation_strings":["Johannes Kepler University, Linz, Austria"],"raw_orcid":"https://orcid.org/0009-0001-9947-6783","affiliations":[{"raw_affiliation_string":"Johannes Kepler University, Linz, Austria","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":["Johannes Kepler University, Linz, Austria"],"raw_orcid":"https://orcid.org/0000-0003-3531-1282","affiliations":[{"raw_affiliation_string":"Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":0.9667,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75257732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9983999729156494,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8610235452651978},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5499812364578247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5484796166419983},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5160884261131287},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.466217577457428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44532835483551025},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43561968207359314},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43253710865974426},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37957510352134705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37727850675582886},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3751174807548523},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.09946960210800171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610235452651978},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5499812364578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5484796166419983},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5160884261131287},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.466217577457428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44532835483551025},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43561968207359314},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43253710865974426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37957510352134705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37727850675582886},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3751174807548523},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.09946960210800171},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3587819.3590968","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3587819.3590968","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587819.3590968","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM Multimedia Systems Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.12134","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.12134","pdf_url":"https://arxiv.org/pdf/2309.12134","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:epub.jku.at/:8852293","is_oa":true,"landing_page_url":"https://epub.jku.at/doi/10.1145/3587819.3590968","pdf_url":"https://epub.jku.at/obvulioa/content/titleinfo/8852293/full.pdf","source":{"id":"https://openalex.org/S4306401788","display_name":"University Library Linz repository (Johannes Kepler Universitat Linz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121883995","host_organization_name":"Johannes Kepler University of Linz","host_organization_lineage":["https://openalex.org/I121883995"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3587819.3590968","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3587819.3590968","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587819.3590968","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM Multimedia Systems Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G987399148","display_name":null,"funder_award_id":"101019375","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379805453.pdf","grobid_xml":"https://content.openalex.org/works/W4379805453.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2152937398","https://openalex.org/W2157364932","https://openalex.org/W2198584637","https://openalex.org/W2346933546","https://openalex.org/W2407410673","https://openalex.org/W2509065397","https://openalex.org/W2592549691","https://openalex.org/W2620341577","https://openalex.org/W2792643794","https://openalex.org/W2890559714","https://openalex.org/W2906259846","https://openalex.org/W2938353296","https://openalex.org/W2954996726","https://openalex.org/W2963543871","https://openalex.org/W3015879946","https://openalex.org/W3098357269","https://openalex.org/W3102718214","https://openalex.org/W3197345328","https://openalex.org/W4205501836","https://openalex.org/W4239515185"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W4230611425","https://openalex.org/W2731899572","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W4383066092","https://openalex.org/W3215138031","https://openalex.org/W2379392295","https://openalex.org/W3160965418"],"abstract_inverted_index":{"Linking":[0],"sheet":[1,49,117],"music":[2,17,98,191,215],"images":[3],"to":[4,29,42,67,69,92,137,187],"audio":[5,47,115],"recordings":[6],"remains":[7],"a":[8,31,90,93,101,120],"key":[9],"problem":[10],"for":[11,200,207],"the":[12,22,52,62,155,159,180,201,209],"development":[13],"of":[14,21,46,54,64,96,109,111,122,162,203],"efficient":[15],"cross-modal":[16,32,163],"retrieval":[18,71,172,181,216],"systems.":[19],"One":[20],"fundamental":[23],"approaches":[24],"toward":[25],"this":[26,74,82,175],"task":[27,161],"is":[28,40,193],"learn":[30],"embedding":[33],"space":[34],"via":[35],"deep":[36],"neural":[37],"networks":[38],"that":[39,132,179],"able":[41,136],"connect":[43],"short":[44],"snippets":[45,110,139],"and":[48,116,126,146,166,219],"music.":[50],"However,":[51],"scarcity":[53,212],"annotated":[55,210],"data":[56,99,192,211],"from":[57,184],"real":[58,70,97,127,190],"musical":[59],"content":[60],"affects":[61],"capability":[63],"such":[65],"methods":[66],"generalize":[68],"scenarios.":[72],"In":[73,174],"work,":[75],"we":[76,79,130,153,177],"investigate":[77],"whether":[78],"can":[80],"mitigate":[81],"limitation":[83],"with":[84,140],"self-supervised":[85,204],"contrastive":[86,205],"learning,":[87],"by":[88,104,150,198],"exposing":[89],"network":[91],"large":[94],"amount":[95],"as":[100],"pre-training":[102,147],"step,":[103],"contrasting":[105],"randomly":[106],"augmented":[107],"views":[108],"both":[112],"modalities,":[113],"namely":[114],"images.":[118],"Through":[119],"number":[121],"experiments":[123,169],"on":[124,170],"synthetic":[125],"piano":[128],"data,":[129],"show":[131],"pretrained":[133],"models":[134,221],"are":[135,222],"retrieve":[138],"better":[141],"precision":[142],"in":[143,158,213],"all":[144],"scenarios":[145],"configurations.":[148,173],"Encouraged":[149],"these":[151],"results,":[152],"employ":[154],"snippet":[156],"embeddings":[157],"higher-level":[160],"piece":[164],"identification":[165],"conduct":[167],"more":[168],"several":[171],"task,":[176],"observe":[178],"quality":[182],"improves":[183],"30%":[185],"up":[186],"100%":[188],"when":[189],"present.":[194],"We":[195],"then":[196],"conclude":[197],"arguing":[199],"potential":[202],"learning":[206],"alleviating":[208],"multi-modal":[214],"models.":[217],"Code":[218],"trained":[220],"accessible":[223],"at":[224],"https://github.com/luisfvc/ucasr.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}