{"id":"https://openalex.org/W4396843712","doi":"https://doi.org/10.1145/3589335.3651535","title":"MART: Learning Hierarchical Music Audio Representations with Part-Whole Transformer","display_name":"MART: Learning Hierarchical Music Audio Representations with Part-Whole Transformer","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843712","doi":"https://doi.org/10.1145/3589335.3651535"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3651535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651535","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651535","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651535","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090568618","display_name":"Dong Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yao","raw_affiliation_strings":["Zhejiang Unversity, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-2444-8201","affiliations":[{"raw_affiliation_string":"Zhejiang Unversity, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669373","display_name":"Jieming Zhu","orcid":"https://orcid.org/0000-0002-5666-8320"},"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's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5666-8320","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016873117","display_name":"Jiahao Xun","orcid":"https://orcid.org/0009-0000-6141-4125"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Xun","raw_affiliation_strings":["Zhejiang Unversity, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-6141-4125","affiliations":[{"raw_affiliation_string":"Zhejiang Unversity, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757087","display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0002-0030-8289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["Zhejiang Unversity, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0030-8289","affiliations":[{"raw_affiliation_string":"Zhejiang Unversity, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang Unversity, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"Zhejiang Unversity, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"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":"Liqun Deng","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-7242-0794","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082131901","display_name":"Wenqiao Zhang","orcid":"https://orcid.org/0000-0002-5988-7609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqiao Zhang","raw_affiliation_strings":["Zhejiang Unversity, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5988-7609","affiliations":[{"raw_affiliation_string":"Zhejiang Unversity, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021124418","display_name":"Zhenhua Dong","orcid":"https://orcid.org/0000-0002-2231-4663"},"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":"Zhenhua Dong","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2231-4663","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086603207","display_name":"Xin Jiang","orcid":"https://orcid.org/0000-0002-9117-8247"},"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":"Xin Jiang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9117-8247","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Hong Kong, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"967","last_page":"970"},"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":0.9990000128746033,"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":0.9922000169754028,"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":0.6866134405136108},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5415040254592896},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5246220827102661},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.49274685978889465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48630771040916443},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47823280096054077},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.439724326133728},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.43623149394989014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42666053771972656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3418114185333252},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2299022674560547},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.16956564784049988},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08148416876792908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866134405136108},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5415040254592896},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5246220827102661},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.49274685978889465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48630771040916443},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47823280096054077},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.439724326133728},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.43623149394989014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42666053771972656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3418114185333252},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2299022674560547},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.16956564784049988},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08148416876792908},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589335.3651535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651535","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651535","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651535","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651535","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843712.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2896276533","https://openalex.org/W2964218314","https://openalex.org/W2965178495","https://openalex.org/W3015666964","https://openalex.org/W3035060554","https://openalex.org/W3036517071","https://openalex.org/W3132401450","https://openalex.org/W3162391496","https://openalex.org/W3201143670","https://openalex.org/W4220931296","https://openalex.org/W4226240391","https://openalex.org/W6607167431"],"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/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W94805306"],"abstract_inverted_index":{"Recent":[0],"research":[1],"in":[2,21,29,90],"self-supervised":[3],"contrastive":[4,97],"learning":[5,60,98,122],"of":[6,51,118],"music":[7,27,58,68,88,105,120,135],"representations":[8,106],"has":[9,126],"demonstrated":[10],"remarkable":[11],"results":[12],"across":[13,130],"diverse":[14],"downstream":[15,132],"tasks.":[16],"However,":[17],"a":[18,56,78,91,95,112],"prevailing":[19],"trend":[20],"existing":[22],"methods":[23],"involves":[24],"representing":[25],"equally-sized":[26],"clips":[28,69,89],"either":[30],"waveform":[31],"or":[32],"spectrogram":[33],"formats,":[34],"often":[35],"overlooking":[36],"the":[37,48,84],"intrinsic":[38],"part-whole":[39,73,80,92,104,124],"hierarchies":[40,125],"within":[41],"music.":[42],"In":[43],"our":[44,119],"quest":[45],"to":[46,82,102],"comprehend":[47],"bottom-up":[49],"structure":[50],"music,":[52],"we":[53,76],"introduce":[54],"MART,":[55],"hierarchical":[57,79,96],"representation":[59,114,121],"approach":[61],"that":[62],"facilitates":[63],"feature":[64],"interactions":[65],"among":[66],"cropped":[67],"while":[70],"considering":[71],"their":[72],"hierarchies.":[74],"Specifically,":[75],"propose":[77],"transformer":[81],"capture":[83],"structural":[85],"relationships":[86],"between":[87],"hierarchy.":[93],"Furthermore,":[94],"objective":[99],"is":[100],"crafted":[101],"align":[103],"at":[107],"adjacent":[108],"levels,":[109],"progressively":[110],"establishing":[111],"multi-hierarchy":[113],"space.":[115],"The":[116],"effectiveness":[117],"from":[123],"been":[127],"empirically":[128],"validated":[129],"multiple":[131],"tasks,":[133],"including":[134],"classification":[136],"and":[137],"cover":[138],"song":[139],"identification.":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}