{"id":"https://openalex.org/W4411635678","doi":"https://doi.org/10.1145/3731715.3733471","title":"Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning","display_name":"Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635678","doi":"https://doi.org/10.1145/3731715.3733471"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.23298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102489274","display_name":"Xiaofeng Pan","orcid":"https://orcid.org/0009-0007-0719-3780"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Pan","raw_affiliation_strings":["NetEase Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-0719-3780","affiliations":[{"raw_affiliation_string":"NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Chen","orcid":"https://orcid.org/0009-0000-9583-0637"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["NetEase Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-9583-0637","affiliations":[{"raw_affiliation_string":"NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040570251","display_name":"Haitong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitong Zhang","raw_affiliation_strings":["NetEase Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-1283-3788","affiliations":[{"raw_affiliation_string":"NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073845581","display_name":"Menglin Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menglin Xing","raw_affiliation_strings":["NetEase Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-3613-094X","affiliations":[{"raw_affiliation_string":"NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiayi Wei","orcid":"https://orcid.org/0009-0002-6693-6293"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Wei","raw_affiliation_strings":["NetEase Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-6693-6293","affiliations":[{"raw_affiliation_string":"NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuefeng Mu","orcid":"https://orcid.org/0009-0009-3919-298X"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Mu","raw_affiliation_strings":["NetEase Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-3919-298X","affiliations":[{"raw_affiliation_string":"NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102563452","display_name":"Zhongqian Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqian Xie","raw_affiliation_strings":["NetEase Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-0528-8982","affiliations":[{"raw_affiliation_string":"NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":1.4852,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78628272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2018","last_page":"2022"},"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":0.9984999895095825,"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":0.998199999332428,"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/bridging","display_name":"Bridging (networking)","score":0.8083829879760742},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7153427600860596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.696430504322052},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.6023789048194885},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4723540246486664},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4289413094520569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4119778871536255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4091295003890991},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3342961072921753},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16001319885253906}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8083829879760742},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7153427600860596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696430504322052},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.6023789048194885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4723540246486664},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4289413094520569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4119778871536255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4091295003890991},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3342961072921753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16001319885253906},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731715.3733471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.23298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23298","pdf_url":"https://arxiv.org/pdf/2505.23298","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":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:2505.23298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23298","pdf_url":"https://arxiv.org/pdf/2505.23298","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411635678.pdf","grobid_xml":"https://content.openalex.org/works/W4411635678.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2723293840","https://openalex.org/W3143852976","https://openalex.org/W3162391496","https://openalex.org/W3168997536","https://openalex.org/W4285483774","https://openalex.org/W4372266552","https://openalex.org/W4379806198","https://openalex.org/W4379806206","https://openalex.org/W4399418346","https://openalex.org/W6840200333"],"related_works":["https://openalex.org/W4408719353","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2128807628","https://openalex.org/W4234264766","https://openalex.org/W2415426693"],"abstract_inverted_index":{"Recent":[0],"works":[1,167],"of":[2,172,205,221],"music":[3,11,22,60,99,149,213],"representation":[4,100],"learning":[5,9],"mainly":[6],"focus":[7],"on":[8,37,59,211],"acoustic":[10],"representations":[12,23],"with":[13,24,202],"unlabeled":[14],"audios":[15],"or":[16,35],"further":[17],"attempt":[18],"to":[19,46,55,90,95,126,142,151,156],"acquire":[20],"multi-modal":[21],"scarce":[25],"annotated":[26],"audio-text":[27,128],"pairs.":[28],"They":[29],"either":[30],"ignore":[31],"the":[32,64,87,91,102,123,153,170,191,203,219],"language":[33,188],"semantics":[34,129,189],"rely":[36],"labeled":[38],"audio":[39,114,182],"datasets":[40],"that":[41,83,168,184],"are":[42],"difficult":[43],"and":[44,106,116,215],"expensive":[45],"create.":[47],"Moreover,":[48],"merely":[49],"modeling":[50],"semantic":[51,88,105,154,206,214],"space":[52,67,155,159,201,207],"usually":[53],"fails":[54],"achieve":[56],"satisfactory":[57],"performance":[58],"recommendation":[61,216],"tasks":[62,217],"since":[63],"user":[65,92,107,157,199],"preference":[66,108,158,200],"is":[68],"ignored.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,135,178],"propose":[74],"a":[75,97,112,118,137,176,180],"novel":[76],"Hierarchical":[77],"Two-stage":[78],"Contrastive":[79],"Learning":[80],"(HTCL)":[81],"method":[82],"models":[84,196],"similarity":[85,197],"from":[86,146,165,190],"perspective":[89,93],"hierarchically":[94],"learn":[96,127],"comprehensive":[98],"bridging":[101],"gap":[103],"between":[104],"spaces.":[109],"We":[110],"devise":[111],"scalable":[113],"encoder":[115,125,183,193],"leverage":[117],"pre-trained":[119],"BERT":[120],"model":[121],"as":[122],"text":[124,192],"via":[130,160],"large-scale":[131],"contrastive":[132,161],"pre-training.":[133],"Further,":[134],"explore":[136],"simple":[138],"yet":[139],"effective":[140],"way":[141],"exploit":[143],"interaction":[144],"data":[145],"our":[147,222],"online":[148],"platform":[150],"adapt":[152],"fine-tuning,":[162],"which":[163],"differs":[164],"previous":[166],"follow":[169],"idea":[171],"collaborative":[173],"filtering.":[174],"As":[175],"result,":[177],"obtain":[179],"powerful":[181],"not":[185],"only":[186],"distills":[187],"but":[194],"also":[195],"in":[198],"integrity":[204],"preserved.":[208],"Experimental":[209],"results":[210],"both":[212],"confirm":[218],"effectiveness":[220],"method.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}