{"id":"https://openalex.org/W4403791481","doi":"https://doi.org/10.1145/3664647.3681389","title":"Multi-grained Correspondence Learning of Audio-language Models for Few-shot Audio Recognition","display_name":"Multi-grained Correspondence Learning of Audio-language Models for Few-shot Audio Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791481","doi":"https://doi.org/10.1145/3664647.3681389"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103240423","display_name":"Shengwei Zhao","orcid":"https://orcid.org/0009-0004-3882-7959"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwei Zhao","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-3882-7959","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013585366","display_name":"Linhai Xu","orcid":"https://orcid.org/0000-0001-7785-6913"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhai Xu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-7785-6913","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685987","display_name":"Yuying Liu","orcid":"https://orcid.org/0000-0002-7295-3308"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuying Liu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-7295-3308","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044668212","display_name":"Shaoyi Du","orcid":"https://orcid.org/0000-0002-7092-0596"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyi Du","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-7092-0596","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"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":"9244","last_page":"9252"},"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":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811811089515686},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5990406274795532},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.536831796169281},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48483312129974365},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4762668311595917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4390879273414612},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4296188950538635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.392846018075943},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.378547728061676},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3676668405532837},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2243133783340454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811811089515686},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5990406274795532},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.536831796169281},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48483312129974365},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4762668311595917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4390879273414612},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4296188950538635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.392846018075943},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.378547728061676},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3676668405532837},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2243133783340454},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":24,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2892181857","https://openalex.org/W2962999716","https://openalex.org/W3012255272","https://openalex.org/W3015591594","https://openalex.org/W3090449556","https://openalex.org/W3175393820","https://openalex.org/W3176445421","https://openalex.org/W3188008942","https://openalex.org/W3198377975","https://openalex.org/W3212610063","https://openalex.org/W3213106580","https://openalex.org/W4205236539","https://openalex.org/W4205509257","https://openalex.org/W4212774754","https://openalex.org/W4226442948","https://openalex.org/W4294831657","https://openalex.org/W4313175608","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4384661029","https://openalex.org/W4386075985","https://openalex.org/W4388191278"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W1611900921","https://openalex.org/W3110605476","https://openalex.org/W1803351015"],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1],"audio-language":[2,29,71],"models":[3,30,72,85],"excel":[4],"in":[5,17,139],"general":[6],"multi-modal":[7,88],"representation,":[8],"facilitating":[9],"their":[10],"adaptation":[11],"to":[12,41,73,86,131],"downstream":[13],"audio":[14,24,52,75,96,122,158],"recognition":[15,25,76],"tasks":[16],"a":[18],"data-efficient":[19],"manner.":[20],"However,":[21],"existing":[22],"few-shot":[23,157],"methods":[26],"based":[27],"on":[28,33,152],"primarily":[31],"focus":[32],"learning":[34,68],"coarse-grained":[35],"correlations,":[36],"which":[37],"are":[38,107],"not":[39],"sufficient":[40],"capture":[42],"the":[43,48,54,92,98,119],"intricate":[44],"matching":[45,105],"patterns":[46,106],"between":[47,121],"multi-level":[49,93],"information":[50,94],"of":[51,57,95,101],"and":[53,114,123,135],"diverse":[55,99],"characteristics":[56,100],"category":[58,102,124],"concepts.":[59,103,125],"To":[60],"address":[61],"this":[62],"gap,":[63],"we":[64,127],"propose":[65],"multi-grained":[66,111,115],"correspondence":[67,141],"for":[69,156],"bootstrapping":[70],"improve":[74],"with":[77,160],"few":[78],"training":[79],"samples.":[80],"This":[81],"approach":[82],"leverages":[83],"generative":[84],"enrich":[87],"representation":[89],"learning,":[90,142],"mining":[91],"alongside":[97],"Multi-grained":[104],"then":[108],"established":[109],"through":[110],"key-value":[112],"cache":[113],"cross-modal":[116],"contrast,":[117],"enhancing":[118],"alignment":[120],"Additionally,":[126],"incorporate":[128],"optimal":[129],"transport":[130],"tackle":[132],"temporal":[133],"misalignment":[134],"semantic":[136],"intersection":[137],"issues":[138],"fine-grained":[140,145],"enabling":[143],"flexible":[144],"matching.":[146],"Our":[147],"method":[148],"achieves":[149],"state-of-the-art":[150],"results":[151],"multiple":[153],"benchmark":[154],"datasets":[155],"recognition,":[159],"comprehensive":[161],"ablation":[162],"experiments":[163],"validating":[164],"its":[165],"effectiveness.":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}