{"id":"https://openalex.org/W4402754294","doi":"https://doi.org/10.1109/cvpr52733.2024.02249","title":"MMA: Multi-Modal Adapter for Vision-Language Models","display_name":"MMA: Multi-Modal Adapter for Vision-Language Models","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402754294","doi":"https://doi.org/10.1109/cvpr52733.2024.02249"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.02249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5101233264","display_name":"Lingxiao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxiao Yang","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090535979","display_name":"Ru\u2010Yuan Zhang","orcid":"https://orcid.org/0000-0002-0654-715X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru-Yuan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072807699","display_name":"Yanchen Wang","orcid":"https://orcid.org/0000-0002-1215-2277"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanchen Wang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018298892","display_name":"Xiaohua Xie","orcid":"https://orcid.org/0000-0002-0310-4679"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohua Xie","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.8448,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.99025875,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"23826","last_page":"23837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.98580002784729,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9850000143051147,"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":0.8670121431350708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7171739935874939},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5837194919586182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3254537582397461},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.13746687769889832},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06693887710571289}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8670121431350708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171739935874939},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5837194919586182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3254537582397461},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.13746687769889832},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06693887710571289},{"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/cvpr52733.2024.02249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":95,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W24089286","https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1846799578","https://openalex.org/W1903029394","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2031342017","https://openalex.org/W2047643928","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2569272946","https://openalex.org/W2732026016","https://openalex.org/W2752782242","https://openalex.org/W2896457183","https://openalex.org/W2947707615","https://openalex.org/W2963037989","https://openalex.org/W2964130064","https://openalex.org/W2964194231","https://openalex.org/W2998792609","https://openalex.org/W3037492894","https://openalex.org/W3094502228","https://openalex.org/W3113151582","https://openalex.org/W3125736290","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3174770825","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W3213454282","https://openalex.org/W3213647938","https://openalex.org/W3215626407","https://openalex.org/W3217163153","https://openalex.org/W4205991051","https://openalex.org/W4225323055","https://openalex.org/W4226053849","https://openalex.org/W4226058394","https://openalex.org/W4229042118","https://openalex.org/W4229453513","https://openalex.org/W4282005462","https://openalex.org/W4287113019","https://openalex.org/W4289752563","https://openalex.org/W4292779060","https://openalex.org/W4297808394","https://openalex.org/W4306313147","https://openalex.org/W4306820534","https://openalex.org/W4309396952","https://openalex.org/W4310557340","https://openalex.org/W4312310776","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312680544","https://openalex.org/W4312840172","https://openalex.org/W4312960937","https://openalex.org/W4313175608","https://openalex.org/W4322718246","https://openalex.org/W4382490555","https://openalex.org/W4386065556","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4386072228","https://openalex.org/W4386575106","https://openalex.org/W4386790226","https://openalex.org/W4390872306","https://openalex.org/W4390872773","https://openalex.org/W4393148714","https://openalex.org/W6620707391","https://openalex.org/W6683379805","https://openalex.org/W6758026734","https://openalex.org/W6759579507","https://openalex.org/W6763468762","https://openalex.org/W6764990469","https://openalex.org/W6776084611","https://openalex.org/W6778883912","https://openalex.org/W6784333009","https://openalex.org/W6785440099","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6796538260","https://openalex.org/W6796581206","https://openalex.org/W6797716411","https://openalex.org/W6801948084","https://openalex.org/W6802517928","https://openalex.org/W6803953248","https://openalex.org/W6810334672","https://openalex.org/W6810601475","https://openalex.org/W6810932883","https://openalex.org/W6838393215","https://openalex.org/W6838701581","https://openalex.org/W6840108421","https://openalex.org/W6846007759"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Pretrained":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"served":[5],"as":[6],"excellent":[7],"foundation":[8],"models":[9],"for":[10,20,63],"transfer":[11],"learning":[12],"in":[13,113,161,216],"diverse":[14,111],"downstream":[15],"tasks.":[16],"However,":[17],"tuning":[18],"VLMs":[19,64],"few-shot":[21],"generalization":[22,28,196],"tasks":[23],"faces":[24],"a":[25,52,59,83,171],"discrimination":[26,183],"-":[27],"dilemma,":[29],"i.e.,":[30],"general":[31],"knowledge":[32,38],"should":[33,39],"be":[34,40,91],"preserved":[35],"and":[36,73,106,117,120,137,147,184,203],"task-specific":[37],"fine-tuned.":[41],"How":[42],"to":[43,65,98,170,177,197,207],"precisely":[44],"identify":[45],"these":[46],"two":[47,158],"types":[48],"of":[49,108,156,175,190],"representations":[50,70],"remains":[51],"challenge.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,101,166],"propose":[58],"Multi-Modal":[60],"Adapter":[61],"(MMA)":[62],"improve":[66],"the":[67,104,115,154,157,162,188],"alignment":[68],"between":[69,153,182],"from":[71,79],"text":[72],"vision":[74,116],"branches.":[75,94],"MMA":[76,169,212],"aggregates":[77],"features":[78,109,140,155],"different":[80],"branches":[81],"into":[82],"shared":[84],"feature":[85],"space":[86],"so":[87],"that":[88,122],"gradients":[89],"can":[90],"communicated":[92],"across":[93,110],"To":[95],"determine":[96],"how":[97],"incorporate":[99,168],"MMA,":[100],"systematically":[102],"analyze":[103],"discriminability":[105],"generalizability":[107],"datasets":[112],"both":[114],"language":[118,139],"branches,":[119],"find":[121],"(1)":[123],"higher":[124,173],"lay-ers":[125,174],"contain":[126,133],"discriminable":[127,143],"dataset-specific":[128],"knowledge,":[129,136],"while":[130],"lower":[131,163],"layers":[132],"more":[134,142],"generalizable":[135],"(2)":[138],"are":[141,149],"than":[144],"visual":[145],"features,":[146],"there":[148],"large":[150],"semantic":[151],"gaps":[152],"modalities,":[159],"especially":[160],"layers.":[164],"Therefore,":[165],"only":[167],"few":[172],"transformers":[176],"achieve":[178],"an":[179],"optimal":[180],"balance":[181],"generalization.":[185,205],"We":[186],"evaluate":[187],"effectiveness":[189],"our":[191,211],"approach":[192],"on":[193],"three":[194],"tasks:":[195],"novel":[198,200],"classes,":[199],"target":[201],"datasets,":[202],"domain":[204],"Compared":[206],"many":[208],"state-of-the-art":[209],"methods,":[210],"achieves":[213],"leading":[214],"performance":[215],"all":[217],"evaluations.":[218],"Code":[219],"is":[220],"at":[221],"https://github.com/ZjjConan/Multi-Modal-Adapter":[222]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}