{"id":"https://openalex.org/W4416251578","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228034","title":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata","display_name":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251578","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228034"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5101683598","display_name":"Abhinaba Roy","orcid":"https://orcid.org/0000-0002-3290-3322"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Abhinaba Roy","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049466548","display_name":"Renhang Liu","orcid":"https://orcid.org/0009-0004-4752-4116"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Renhang Liu","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020867211","display_name":"Toh\u2010Ming Lu","orcid":"https://orcid.org/0000-0003-3600-9798"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tongyu Lu","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069548004","display_name":"Dorien Herremans","orcid":"https://orcid.org/0000-0001-8607-1640"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dorien Herremans","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101683598"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":1.6611,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88337795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9828000068664551,"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":0.9828000068664551,"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":0.0017000000225380063,"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/T13996","display_name":"Diverse Musicological Studies","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.881600022315979},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6226000189781189},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4348999857902527},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.42320001125335693},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3937999904155731},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.38580000400543213}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.881600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224999904632568},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6226000189781189},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5566999912261963},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4348999857902527},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.42320001125335693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3939000070095062},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.3224000036716461},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C196070930","wikidata":"https://www.wikidata.org/wiki/Q598190","display_name":"Correlogram","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2023701920","https://openalex.org/W2101105183","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4392647990","https://openalex.org/W4400033239","https://openalex.org/W4400768137","https://openalex.org/W4401043564","https://openalex.org/W4403757590","https://openalex.org/W4404782964","https://openalex.org/W4409362600"],"related_works":[],"abstract_inverted_index":{"We":[0,33,85],"introduce":[1,35],"JamendoMaxCaps,":[2],"a":[3,25,36,60,72,103],"large-scale":[4],"music-caption":[5],"dataset":[6,20,77,98],"featuring":[7],"over":[8],"362,000":[9],"freely":[10],"licensed":[11],"instrumental":[12],"tracks":[13],"from":[14],"the":[15,96],"renowned":[16],"Jamendo":[17],"platform.":[18],"The":[19],"includes":[21],"captions":[22],"generated":[23],"by":[24],"state-of-the-art":[26],"captioning":[27],"model,":[28],"enhanced":[29],"with":[30,90],"imputed":[31],"metadata.":[32],"also":[34],"retrieval":[37],"system":[38],"that":[39],"leverages":[40],"both":[41],"musical":[42],"features":[43],"and":[44,75,120],"metadata":[45,58],"to":[46,54,70,106],"identify":[47],"similar":[48],"songs,":[49],"which":[50],"are":[51],"then":[52],"used":[53],"fill":[55],"in":[56,109],"missing":[57],"using":[59],"local":[61],"large":[62],"language":[63],"model":[64],"(LLLM).":[65],"This":[66],"approach":[67,88],"allows":[68],"us":[69],"provide":[71,102],"more":[73],"comprehensive":[74],"informative":[76],"for":[78],"researchers":[79],"working":[80],"on":[81],"music-language":[82,110],"understanding":[83,111],"tasks.":[84],"validate":[86],"this":[87],"quantitatively":[89],"five":[91],"different":[92],"measurements.":[93],"By":[94],"making":[95],"JamendoMaxCaps":[97],"publicly":[99],"available,":[100],"we":[101],"high-quality":[104],"resource":[105],"advance":[107],"research":[108],"tasks":[112],"such":[113],"as":[114],"music":[115,122],"retrieval,":[116],"multimodal":[117],"representation":[118],"learning,":[119],"generative":[121],"models.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}
