{"id":"https://openalex.org/W4387967993","doi":"https://doi.org/10.1145/3581783.3611939","title":"Parameter-Efficient Transfer Learning for Audio-Visual-Language Tasks","display_name":"Parameter-Efficient Transfer Learning for Audio-Visual-Language Tasks","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967993","doi":"https://doi.org/10.1145/3581783.3611939"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5100662332","display_name":"Hongye Liu","orcid":"https://orcid.org/0000-0003-2558-7939"},"institutions":[{"id":"https://openalex.org/I55538621","display_name":"China Jiliang University","ror":"https://ror.org/05v1y0t93","country_code":"CN","type":"education","lineage":["https://openalex.org/I55538621"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongye Liu","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, China JiLiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2558-7939","affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, China JiLiang University, Hangzhou, China","institution_ids":["https://openalex.org/I55538621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113031793","display_name":"Xianhai Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhai Xie","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-3996-1590","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859093","display_name":"Yang Gao","orcid":"https://orcid.org/0009-0002-6717-0373"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-6717-0373","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8407-1137","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"387","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9945999979972839,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.8840258121490479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8490302562713623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5487027764320374},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5278254151344299},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39007166028022766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3838801383972168},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12106087803840637}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8840258121490479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490302562713623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5487027764320374},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5278254151344299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39007166028022766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3838801383972168},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12106087803840637},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G2294246951","display_name":null,"funder_award_id":"LDT23F02025F02","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4033949287","display_name":"\u6f14\u5316\u8de8\u6a21\u6001\u8bed\u4e49\u7684\u7ed3\u6784\u5316\u7406\u89e3\u4e0e\u53ef\u89e3\u91ca\u63a8\u7406\u65b9\u6cd5","funder_award_id":"LDT23F02025F02","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G6290763762","display_name":"\u53ef\u4fe1\u8de8\u5a92\u4f53\u5206\u6790\u63a8\u7406","funder_award_id":"LR22F020001","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G7336325476","display_name":"\u5916\u90e8\u201c\u6570\u636e-\u77e5\u8bc6\u201d\u8054\u5408\u589e\u5f3a\u7684\u89c6\u89c9\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":"\u57fa\u4e8e\u5927\u89c4\u6a21\u8de8\u5a92\u4f53\u77e5\u8bc6\u7f51\u7edc\u7684\u590d\u6742\u89c6\u9891\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8010506932","display_name":null,"funder_award_id":"No.62072147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2560647685","https://openalex.org/W2932399282","https://openalex.org/W2964109005","https://openalex.org/W2980339970","https://openalex.org/W3021321555","https://openalex.org/W3091588028","https://openalex.org/W3093051361","https://openalex.org/W3138516171","https://openalex.org/W3169318522","https://openalex.org/W3176028309","https://openalex.org/W3203592524","https://openalex.org/W3207798279","https://openalex.org/W4225274194","https://openalex.org/W4225274946","https://openalex.org/W4287113836","https://openalex.org/W4312415534","https://openalex.org/W4312558481","https://openalex.org/W4312784228","https://openalex.org/W4312864639","https://openalex.org/W4313175608","https://openalex.org/W4319300466"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2160602540","https://openalex.org/W2485605994","https://openalex.org/W4385571108","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,149],"pretrain-then-finetune":[1],"paradigm":[2],"has":[3],"been":[4,76],"widely":[5],"used":[6],"in":[7],"various":[8],"unimodal":[9,63,197],"and":[10,42,51,97,143,163,192],"multimodal":[11],"tasks.":[12],"However,":[13],"finetuning":[14],"all":[15],"the":[16,25,34,39,68,102,105,108,115,120,124,138,144,156,160,164,210],"parameters":[17,48],"of":[18,130,133,159,212],"a":[19,45,82,184],"pre-trained":[20,40,103,182],"model":[21,26,41,119],"becomes":[22],"prohibitive":[23],"as":[24],"size":[27],"grows":[28],"exponentially.":[29],"To":[30],"address":[31],"this":[32],"issue,":[33],"adapter":[35,58,69,110,135],"mechanism":[36],"that":[37],"freezes":[38],"only":[43],"finetunes":[44],"few":[46],"extra":[47],"is":[49,112,189],"introduced":[50],"delivers":[52],"promising":[53],"results.":[54],"Most":[55],"studies":[56],"on":[57,101,183,203],"architectures":[59,70],"are":[60],"dedicated":[61],"to":[62,118,154,176],"or":[64,198],"bimodal":[65,199],"tasks,":[66],"while":[67],"for":[71,90],"trimodal":[72,179,186,206],"tasks":[73,93,208],"have":[74],"not":[75],"investigated":[77],"yet.":[78],"This":[79],"paper":[80],"introduces":[81],"novel":[83],"Long":[84],"Short-Term":[85],"Trimodal":[86],"Adapter":[87],"(LSTTA)":[88],"approach":[89],"video":[91,161],"understanding":[92],"involving":[94],"audio,":[95],"visual,":[96],"language":[98],"modalities.":[99,126],"Based":[100],"from":[104],"three":[106,125],"modalities,":[107],"designed":[109],"module":[111,142,168],"inserted":[113],"between":[114],"sequential":[116],"blocks":[117],"dense":[121],"interactions":[122,171],"across":[123],"Specifically,":[127],"LSTTA":[128,188,213],"consists":[129],"two":[131],"types":[132],"complementary":[134],"modules,":[136],"namely":[137],"long-term":[139,150],"semantic":[140,146,151,166],"filtering":[141,152],"short-term":[145,165],"interaction":[147,167],"module.":[148],"aims":[153],"characterize":[155],"temporal":[157],"importance":[158],"frames":[162],"models":[169],"local":[170],"within":[172],"short":[173],"periods.":[174],"Compared":[175],"previous":[177],"state-of-the-art":[178,216],"learning":[180,207],"methods":[181],"large-scale":[185],"corpus,":[187],"more":[190],"flexible":[191],"can":[193],"inherit":[194],"any":[195],"powerful":[196],"models.":[200],"Experimental":[201],"results":[202],"four":[204],"typical":[205],"show":[209],"effectiveness":[211],"over":[214],"existing":[215],"methods.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}