{"id":"https://openalex.org/W4415707689","doi":"https://doi.org/10.1109/icme59968.2025.11210123","title":"CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining","display_name":"CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707689","doi":"https://doi.org/10.1109/icme59968.2025.11210123"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5120192654","display_name":"Tristan Tsoi","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":true,"raw_author_name":"Tristan Tsoi","raw_affiliation_strings":["Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406454","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-8874-4167"},"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":"Jiajun Deng","raw_affiliation_strings":["Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063427144","display_name":"Yaolong Ju","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":"Yaolong Ju","raw_affiliation_strings":["Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038446032","display_name":"Benno Weck","orcid":"https://orcid.org/0000-0002-5760-6922"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Benno Weck","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074883610","display_name":"Holger Kirchhoff","orcid":"https://orcid.org/0009-0008-4655-729X"},"institutions":[{"id":"https://openalex.org/I4210129353","display_name":"Huawei Technologies (Germany)","ror":"https://ror.org/038cdme44","country_code":"DE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Kirchhoff","raw_affiliation_strings":["Huawei Technologies,Munich Research Center,Munich,Germany"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Munich Research Center,Munich,Germany","institution_ids":["https://openalex.org/I4210129353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103134236","display_name":"Simon Lui","orcid":"https://orcid.org/0000-0002-0829-2867"},"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":"Simon Lui","raw_affiliation_strings":["Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5120192654"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42318795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9717000126838684,"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":0.9717000126838684,"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/T10028","display_name":"Topic Modeling","score":0.0026000000070780516,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.002400000113993883,"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/leverage","display_name":"Leverage (statistics)","score":0.66839998960495},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6322000026702881},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6227999925613403},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3440999984741211},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.3377000093460083},{"id":"https://openalex.org/keywords/serendipity","display_name":"Serendipity","score":0.326200008392334},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.3059999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645999789237976},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.66839998960495},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6322000026702881},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6227999925613403},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5284000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.3377000093460083},{"id":"https://openalex.org/C2779119418","wikidata":"https://www.wikidata.org/wiki/Q166039","display_name":"Serendipity","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32019999623298645},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2533999979496002},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1979955134","https://openalex.org/W2080391922","https://openalex.org/W2110851725","https://openalex.org/W2116373735","https://openalex.org/W2126410803","https://openalex.org/W2165071375","https://openalex.org/W2487137543","https://openalex.org/W2591719913","https://openalex.org/W3015829441","https://openalex.org/W3100806282","https://openalex.org/W3160506022","https://openalex.org/W3199787416","https://openalex.org/W4225314222","https://openalex.org/W4372259760","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4392963916","https://openalex.org/W4411112969"],"related_works":[],"abstract_inverted_index":{"Music":[0,114],"similarity":[1,37],"retrieval":[2],"is":[3],"fundamental":[4],"for":[5],"managing":[6],"and":[7,71,107],"exploring":[8],"relevant":[9],"content":[10],"from":[11],"large":[12],"collections":[13],"in":[14,46],"streaming":[15,115],"platforms.":[16],"This":[17],"paper":[18,61],"presents":[19],"a":[20,63],"novel":[21],"cross-modal":[22],"contrastive":[23],"learning":[24],"framework":[25,94],"that":[26,91],"leverages":[27],"the":[28,40,53,92,112],"open-ended":[29],"nature":[30],"of":[31,42,55],"text":[32],"descriptions":[33],"to":[34,83],"guide":[35],"music":[36,81],"modeling,":[38],"addressing":[39],"limitations":[41],"traditional":[43],"uni-modal":[44],"approaches":[45],"capturing":[47],"complex":[48],"musical":[49],"relationships.":[50],"To":[51],"overcome":[52],"scarcity":[54],"high-quality":[56],"text-music":[57],"paired":[58],"data,":[59],"this":[60],"introduces":[62],"dual-source":[64],"data":[65],"acquisition":[66],"approach":[67],"combining":[68],"online":[69],"scraping":[70],"LLM-based":[72],"prompting,":[73],"where":[74],"carefully":[75],"designed":[76],"prompts":[77],"leverage":[78],"LLMs\u2019":[79],"comprehensive":[80],"knowledge":[82],"generate":[84],"contextually":[85],"rich":[86],"descriptions.":[87],"Extensive":[88],"experiments":[89],"demonstrate":[90],"proposed":[93],"achieves":[95],"significant":[96],"performance":[97],"improvements":[98],"over":[99],"existing":[100],"benchmarks":[101],"through":[102],"objective":[103],"metrics,":[104],"subjective":[105],"evaluations,":[106],"real-world":[108],"A/B":[109],"testing":[110],"on":[111],"Huawei":[113],"platform.":[116]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}