{"id":"https://openalex.org/W4402979869","doi":"https://doi.org/10.1109/icme57554.2024.10688369","title":"Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models","display_name":"Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979869","doi":"https://doi.org/10.1109/icme57554.2024.10688369"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5034227509","display_name":"Juncheng Yang","orcid":"https://orcid.org/0000-0002-0412-1139"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Yang","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002584135","display_name":"Zuchao Li","orcid":"https://orcid.org/0000-0003-0436-8446"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuchao Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101025866","display_name":"Shuai Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Xie","raw_affiliation_strings":["JD Explore Academy,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102915055","display_name":"Weiping Zhu","orcid":"https://orcid.org/0000-0001-7714-350X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Zhu","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596138","display_name":"Wei Yu","orcid":"https://orcid.org/0000-0003-2550-5833"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yu","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100678042","display_name":"Shijun Li","orcid":"https://orcid.org/0000-0002-3243-3025"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijun Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1979,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91472224,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9954000115394592,"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":0.9954000115394592,"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":0.9692000150680542,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9509000182151794,"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/adapter","display_name":"Adapter (computing)","score":0.7441580295562744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190945148468018},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6231265068054199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45150765776634216},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4385642409324646},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4204961657524109},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33170491456985474},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08179283142089844},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07516926527023315},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.06582337617874146}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7441580295562744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190945148468018},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6231265068054199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45150765776634216},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4385642409324646},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4204961657524109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33170491456985474},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08179283142089844},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07516926527023315},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.06582337617874146},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4313175608","https://openalex.org/W4386075788","https://openalex.org/W4386790226"],"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/W4200251711"],"abstract_inverted_index":{"Adapter-based":[0],"parameter-efficient":[1,66],"transfer":[2],"learning":[3,132],"has":[4],"achieved":[5],"exciting":[6],"results":[7,136],"in":[8,58,120],"vision-language":[9],"models.":[10,60],"Traditional":[11],"adapter":[12],"methods":[13,30,146],"often":[14],"require":[15],"training":[16,35],"or":[17,25],"fine-tuning,":[18],"facing":[19],"challenges":[20],"such":[21],"as":[22],"insufficient":[23],"samples":[24,116],"resource":[26],"limitations.":[27],"While":[28],"some":[29],"overcome":[31],"the":[32,45,53,96],"need":[33],"for":[34,52,74,91],"by":[36],"leveraging":[37],"image":[38,78],"modality":[39],"cache":[40,72],"and":[41,49,77,123,151],"retrieval,":[42],"they":[43],"overlook":[44],"text":[46,76],"modality\u2019s":[47],"importance":[48],"cross-modal":[50,65,101,121],"cues":[51],"efficient":[54],"adaptation":[55],"of":[56,130],"parameters":[57],"visual-language":[59,85],"This":[61],"work":[62],"introduces":[63],"a":[64],"approach":[67],"named":[68],"XMAdapter.":[69],"XMAdapter":[70,142],"establishes":[71],"models":[73],"both":[75],"modalities.":[79],"It":[80],"then":[81],"leverages":[82],"retrieval":[83],"through":[84,127],"bimodal":[86],"information":[87],"to":[88,107],"gather":[89],"clues":[90],"inference.":[92],"By":[93],"dynamically":[94],"adjusting":[95],"affinity":[97,122],"ratio,":[98],"it":[99,113],"achieves":[100],"fusion,":[102],"decoupling":[103],"different":[104],"modal":[105],"similarities":[106],"assess":[108],"their":[109],"respective":[110],"contributions.":[111],"Additionally,":[112],"explores":[114],"hard":[115],"based":[117],"on":[118,137],"differences":[119],"enhances":[124],"model":[125],"performance":[126],"adaptive":[128],"adjustment":[129],"sample":[131],"intensity.":[133],"Extensive":[134],"experimental":[135],"benchmark":[138],"datasets":[139],"demonstrate":[140],"that":[141],"outperforms":[143],"previous":[144],"adapter-based":[145],"significantly":[147],"regarding":[148],"accuracy,":[149],"generalization,":[150],"efficiency.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}