{"id":"https://openalex.org/W7166847535","doi":"https://doi.org/10.18653/v1/2026.acl-long.2197","title":"FIGMA: Towards FIne-Grained Music retrievAl","display_name":"FIGMA: Towards FIne-Grained Music retrievAl","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166847535","doi":"https://doi.org/10.18653/v1/2026.acl-long.2197"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2197","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2197","pdf_url":"https://aclanthology.org/2026.acl-long.2197.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2197.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076391965","display_name":"Nishit Anand","orcid":"https://orcid.org/0000-0001-9391-1871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishit Anand","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139748485","display_name":"Ashish Seth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Seth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784465","display_name":"Sreyan Ghosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139751556","display_name":"Dinesh Manocha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramani Duraiswami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86373838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47559","last_page":"47572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9613000154495239,"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":0.9613000154495239,"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":0.009200000204145908,"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"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.002899999963119626,"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/music-information-retrieval","display_name":"Music information retrieval","score":0.7105000019073486},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6837000250816345},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3935000002384186},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3781000077724457},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.37439998984336853},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3249000012874603},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.30790001153945923},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.30160000920295715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220999836921692},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.7105000019073486},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6837000250816345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.597599983215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5561000108718872},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4138000011444092},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.2743000090122223},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2197","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2197","pdf_url":"https://aclanthology.org/2026.acl-long.2197.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2197","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2197","pdf_url":"https://aclanthology.org/2026.acl-long.2197.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166847535.pdf","grobid_xml":"https://content.openalex.org/works/W7166847535.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieving":[0],"music":[1,177,182],"using":[2],"natural":[3],"language":[4],"descriptions":[5,24],"has":[6],"improved":[7],"with":[8,149,156,188],"contrastive":[9,54,90],"audio-text":[10,100],"models":[11,39,65,179],"such":[12,29],"as":[13,30,163,165],"CLAP,":[14],"but":[15],"current":[16],"systems":[17],"remain":[18],"limited":[19],"to":[20,42,109,193],"coarse":[21],"semantic":[22,113],"queries.When":[23],"specify":[25],"fine-grained":[26],"musical":[27,117],"attributes":[28,118],"tempo,":[31,157],"key,":[32,158],"chord":[33,159],"progression,":[34,160],"or":[35],"rhythmic":[36],"structure,":[37],"existing":[38,175],"often":[40],"fail":[41],"retrieve":[43],"the":[44,53,69,76,126],"correct":[45],"audio.We":[46],"show":[47],"that":[48,92,171],"this":[49,94],"limitation":[50,95],"stems":[51],"from":[52],"learning":[55],"objective":[56],"itself:":[57],"despite":[58],"being":[59],"trained":[60],"on":[61],"long":[62],"captions,":[63],"CLAP-based":[64,176],"effectively":[66],"utilize":[67],"only":[68],"first":[70],"few":[71],"tokens,":[72],"discarding":[73],"much":[74],"of":[75,128,142,191],"information":[77],"encoded":[78],"in":[79],"detailed":[80],"prompts.Then,":[81],"we":[82,124],"propose":[83],"FIGMA":[84,108,172],"(FIne-Grained":[85],"Music":[86,130,135],"RetrievAl),":[87],"a":[88,120,139,150],"multi-view":[89],"architecture":[91],"addresses":[93],"by":[96],"jointly":[97],"optimizing":[98],"global":[99],"alignment":[101],"and":[102,115,132,167],"frame-level,":[103],"token-wise":[104],"alignment.This":[105],"design":[106],"enables":[107],"capture":[110],"both":[111,154],"high-level":[112],"context":[114],"finegrained":[116],"within":[119],"unified":[121],"representation":[122],"space.Moreover,":[123],"formalize":[125],"task":[127],"Fine-Grained":[129,134],"Retrieval":[131],"construct":[133],"Caption":[136],"dataset":[137,141],"(FGMCaps),":[138],"large-scale":[140],"380K":[143],"music-caption":[144],"pairs":[145],"for":[146],"training":[147],"along":[148],"10K":[151],"test":[152],"set,":[153],"annotated":[155],"beat":[161],"count,":[162],"well":[164],"genre":[166],"mood.Extensive":[168],"experiments":[169],"demonstrate":[170],"consistently":[173],"outperforms":[174],"retrieval":[178,183],"across":[180],"multiple":[181],"benchmarks,":[184],"including":[185],"out-of-domain":[186],"evaluations,":[187],"relative":[189],"improvements":[190],"up":[192],"73.3%.":[194]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}