{"id":"https://openalex.org/W4220931296","doi":"https://doi.org/10.1145/3485447.3512011","title":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","display_name":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4220931296","doi":"https://doi.org/10.1145/3485447.3512011"},"language":"en","primary_location":{"id":"doi:10.1145/3485447.3512011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3512011","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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":"Proceedings of the ACM Web Conference 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.09129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101086932","display_name":"Dong Yao","orcid":"https://orcid.org/0009-0002-0481-9454"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Yao","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757086","display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0001-7480-398X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552790","display_name":"Jieming Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Zhu","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, China","Huawei Noah's Ark Lab, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112895404","display_name":"Yudong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Zhu","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, China","Huawei Noah's Ark Lab, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421929","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0001-5230-5998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["www.ruizhang.info, China"],"affiliations":[{"raw_affiliation_string":"www.ruizhang.info, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083350101","display_name":"Xiuqiang He","orcid":"https://orcid.org/0000-0002-4115-8205"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuqiang He","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, China","Huawei Noah's Ark Lab, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101086932"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.9663,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88309637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2906","last_page":"2915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7305238246917725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5410200357437134},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5403530597686768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49280479550361633},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45893120765686035},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4553166329860687},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44997626543045044},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3951932191848755},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34247103333473206},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2086862325668335},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10522109270095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305238246917725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410200357437134},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5403530597686768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49280479550361633},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45893120765686035},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4553166329860687},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44997626543045044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3951932191848755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34247103333473206},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2086862325668335},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10522109270095825}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3485447.3512011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3512011","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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":"Proceedings of the ACM Web Conference 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.09129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.09129","pdf_url":"https://arxiv.org/pdf/2203.09129","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:2203.09129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.09129","pdf_url":"https://arxiv.org/pdf/2203.09129","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":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W1536680647","https://openalex.org/W2022479123","https://openalex.org/W2138621090","https://openalex.org/W2883725317","https://openalex.org/W2896276533","https://openalex.org/W2913939497","https://openalex.org/W2963451564","https://openalex.org/W2965178495","https://openalex.org/W2971074500","https://openalex.org/W2981952041","https://openalex.org/W2982223350","https://openalex.org/W3015666964","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3046727238","https://openalex.org/W3092850823","https://openalex.org/W3096831136","https://openalex.org/W3108655343","https://openalex.org/W3129066085","https://openalex.org/W3134652006","https://openalex.org/W3154419237","https://openalex.org/W3160719641","https://openalex.org/W3162391496","https://openalex.org/W3173187964","https://openalex.org/W3201143670","https://openalex.org/W3206191467","https://openalex.org/W4235310157","https://openalex.org/W4285345683","https://openalex.org/W4293258764","https://openalex.org/W6600710808","https://openalex.org/W6600713050","https://openalex.org/W6600763685","https://openalex.org/W6702248584","https://openalex.org/W6762931180"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W4287325290"],"abstract_inverted_index":{"Self-supervised":[0],"learning,":[1,4],"especially":[2],"contrastive":[3,32,111,156],"has":[5],"made":[6],"an":[7],"outstanding":[8],"contribution":[9],"to":[10,84,87,129,159],"the":[11,22,42,51,63,77,85,89,110,166,191],"development":[12],"of":[13,92,179,196],"many":[14],"deep":[15],"learning":[16,33,112,157],"research":[17],"fields.":[18],"Recently,":[19],"researchers":[20],"in":[21],"acoustic":[23],"signal":[24],"processing":[25],"field":[26],"noticed":[27],"its":[28],"success":[29],"and":[30,141,186,194],"leveraged":[31],"for":[34,105],"better":[35],"music":[36,64,184,197],"representation.":[37],"Typically,":[38],"existing":[39],"approaches":[40],"maximize":[41],"similarity":[43],"between":[44],"two":[45,180],"distorted":[46],"audio":[47],"segments":[48],"sampled":[49,164],"from":[50,165],"same":[52,167],"music.":[53,93,168],"In":[54],"other":[55],"words,":[56],"they":[57],"ensure":[58],"a":[59,100,120,154],"semantic":[60],"agreement":[61],"at":[62,76],"level.":[65],"However,":[66],"those":[67],"coarse-grained":[68],"methods":[69],"neglect":[70],"some":[71],"inessential":[72,149],"or":[73,148],"noisy":[74],"elements":[75],"frame":[78,103,131],"level,":[79],"which":[80,125],"may":[81],"be":[82],"detrimental":[83],"model":[86],"learn":[88],"effective":[90],"representation":[91,198],"Towards":[94],"this":[95,97],"end,":[96],"paper":[98],"proposes":[99],"novel":[101,155],"Positive-nEgative":[102],"mask":[104],"Music":[106],"Representation":[107],"based":[108],"on":[109,133,172],"framework,":[113],"abbreviated":[114],"as":[115],"PEMR.":[116,201],"Concretely,":[117],"PEMR":[118],"incorporates":[119],"Positive-Negative":[121],"Mask":[122],"Generation":[123],"module,":[124],"leverages":[126],"transformer":[127],"blocks":[128],"generate":[130,138],"masks":[132],"Log-Mel":[134],"spectrogram.":[135],"We":[136,152,169],"can":[137],"self-augmented":[139,162],"negative":[140],"positive":[142],"samples":[143],"by":[144,200],"masking":[145],"important":[146],"components":[147],"components,":[150],"respectively.":[151],"devise":[153],"objective":[158],"accommodate":[160],"both":[161],"positives/negatives":[163],"conduct":[170],"experiments":[171],"four":[173],"public":[174],"datasets.":[175],"The":[176],"experimental":[177],"results":[178],"music-related":[181],"downstream":[182],"tasks,":[183],"classification":[185],"cover":[187],"song":[188],"identification,":[189],"demonstrate":[190],"generalization":[192],"ability":[193],"transferability":[195],"learned":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}