{"id":"https://openalex.org/W4399423378","doi":"https://doi.org/10.1145/3652583.3658105","title":"Multi-Source Augmentation and Composite Prompts for Visual Recognition with Missing Modality","display_name":"Multi-Source Augmentation and Composite Prompts for Visual Recognition with Missing Modality","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399423378","doi":"https://doi.org/10.1145/3652583.3658105"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658105","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658105","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077312505","display_name":"Zhirui Kuai","orcid":"https://orcid.org/0009-0008-8023-7935"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhirui Kuai","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-8023-7935","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046971203","display_name":"Y. L. Zhou","orcid":"https://orcid.org/0009-0008-4888-1827"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulu Zhou","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-4888-1827","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qi Xie","orcid":"https://orcid.org/0009-0001-7851-4605"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Xie","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0001-7851-4605","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100609033","display_name":"Li Kuang","orcid":"https://orcid.org/0000-0003-4975-034X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Kuang","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4975-034X","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077312505"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47929688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"543","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9925000071525574,"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/missing-data","display_name":"Missing data","score":0.8153997659683228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745082437992096},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.725947916507721},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6953186392784119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6232975721359253},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.604271411895752},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.5083207488059998},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42684975266456604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.406477689743042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40120795369148254},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.354328989982605}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.8153997659683228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745082437992096},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.725947916507721},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6953186392784119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6232975721359253},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.604271411895752},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.5083207488059998},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42684975266456604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.406477689743042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40120795369148254},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.354328989982605},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658105","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658105","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321514","display_name":"Central South University","ror":"https://ror.org/00f1zfq44"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399423378.pdf","grobid_xml":"https://content.openalex.org/works/W4399423378.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2265228180","https://openalex.org/W2277195237","https://openalex.org/W2296448531","https://openalex.org/W2809410879","https://openalex.org/W2962931510","https://openalex.org/W3012721484","https://openalex.org/W3114214226","https://openalex.org/W3175825020","https://openalex.org/W3176404283","https://openalex.org/W4225303565","https://openalex.org/W4225744324","https://openalex.org/W4226278401","https://openalex.org/W4229065466","https://openalex.org/W4312238419","https://openalex.org/W4312933868","https://openalex.org/W4313164293","https://openalex.org/W4372260527","https://openalex.org/W4386057714","https://openalex.org/W6600003358"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"In":[0],"multimodal":[1],"learning":[2],"for":[3,58,77,84,91,197,213],"visual":[4],"recognition,":[5],"missing":[6,38,49,111,163,195,221,269],"modality":[7,50,79,268],"is":[8,56,75,275],"a":[9,32,42,70,148,177,189,211],"common":[10,57],"issue":[11],"that":[12,74,182,217],"can":[13],"significantly":[14],"impact":[15,266],"the":[16,29,48,85,104,143,158,172,194,206,220,224,228,237,240,258,265],"performance":[17,159],"and":[18,39,66,93,128,151,168,188,227],"robustness":[19,105],"of":[20,106,117,230,239,260,267],"vision-language":[21,107,241,272],"models.":[22],"Most":[23],"existing":[24],"approaches":[25,100,119],"have":[26],"only":[27],"considered":[28],"situation":[30],"where":[31],"single":[33],"modality-either":[34],"image":[35,62,94],"or":[36,61],"text-is":[37],"then":[40],"use":[41],"data":[43,71,95,112,167,173,179,185,190,196],"augmentation":[44,72,180,186,231],"method":[45,73,154,212],"to":[46,63,109,124,156,162,192,243],"recover":[47],"data.":[51,232],"However,":[52],"in":[53,67,223,248,263],"reality,":[54],"it":[55],"either":[59],"text":[60,92],"be":[64,82,135],"missing,":[65],"such":[68],"cases,":[69],"effective":[76],"one":[78],"might":[80],"not":[81],"suitable":[83],"other,":[86],"thereby":[87],"necessitating":[88],"distinct":[89],"methods":[90,187],"augmentation.":[96],"There":[97],"are":[98],"also":[99],"aimed":[101],"at":[102],"enhancing":[103],"models":[108],"handle":[110,244],"inputs.":[113],"However":[114],"since":[115],"most":[116],"these":[118,132],"often":[120],"involve":[121],"significant":[122],"modifications":[123],"complex":[125],"model":[126,169,207,225,242],"structures":[127],"require":[129],"extensive":[130],"retraining,":[131],"solutions":[133],"would":[134],"impractical":[136],"with":[137],"limited":[138],"computational":[139],"resources.":[140],"To":[141],"address":[142],"abovementioned":[144],"limitations,":[145],"we":[146,175,209],"develop":[147],"<u>M</u>ulti-source":[149],"<u>A</u>ugmentation":[150],"<u>C</u>omposite":[152],"<u>P</u>rompts":[153],"(<u>MACP</u>)":[155],"alleviate":[157],"degradation":[160],"due":[161],"modalities":[164,222],"from":[165],"both":[166],"levels.":[170],"On":[171,205],"level,":[174,208],"designed":[176,210],"multi-source":[178],"framework":[181],"integrates":[183],"different":[184,245],"selector":[191],"restore":[193],"each":[198],"image-text":[199],"sample":[200],"as":[201,203],"well":[202],"possible.":[204],"generating":[214],"prompt":[215,253],"vectors":[216],"simultaneously":[218],"indicate":[219],"input":[226,246],"source":[229],"The":[233],"prompts":[234],"will":[235],"enhance":[236],"ability":[238],"types":[247],"low-resource":[249],"situations":[250],"by":[251],"applying":[252],"tuning.":[254],"Experimental":[255],"results":[256],"demonstrate":[257],"effectiveness":[259],"our":[261],"approach":[262],"mitigating":[264],"on":[270],"three":[271],"datasets.":[273],"Code":[274],"available.":[276]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}