{"id":"https://openalex.org/W4385572018","doi":"https://doi.org/10.18653/v1/2023.findings-acl.158","title":"Retrieving Multimodal Prompts for Generative Visual Question Answering","display_name":"Retrieving Multimodal Prompts for Generative Visual Question Answering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385572018","doi":"https://doi.org/10.18653/v1/2023.findings-acl.158"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-acl.158","doi":"https://doi.org/10.18653/v1/2023.findings-acl.158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.158","pdf_url":"https://aclanthology.org/2023.findings-acl.158.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-acl.158.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001600835","display_name":"Timothy Ossowski","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy Ossowski","raw_affiliation_strings":["Department of Computer Science,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085263462","display_name":"Junjie Hu","orcid":"https://orcid.org/0000-0002-1911-4361","observed_orcids":["https://orcid.org/0000-0002-1911-4361"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junjie Hu","raw_affiliation_strings":["Department of Biostatistics and Medical Informatics University of Wisconsin, Madison, WI, USA","Department of Computer Science,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Medical Informatics University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"Department of Computer Science,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.71,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90774968,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2518","last_page":"2535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/visual-question-answering","display_name":"visual question answering","score":0.8500000238418579},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.8360000252723694},{"id":"https://openalex.org/keywords/zero-shot-domain-adaptation","display_name":"zero-shot domain adaptation","score":0.7509999871253967},{"id":"https://openalex.org/keywords/few-shot-domain-adaptation","display_name":"few-shot domain adaptation","score":0.7720000147819519},{"id":"https://openalex.org/keywords/medical-visual-question-answering","display_name":"medical visual question answering","score":0.7940000295639038},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7620000243186951}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8509742021560669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273356556892395},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7930962443351746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.714160680770874},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6875661015510559},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6815868616104126},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5635217428207397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5473714470863342},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5336922407150269},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5182230472564697},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4655851423740387},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46472010016441345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41462546586990356},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09236633777618408},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.findings-acl.158","doi":"https://doi.org/10.18653/v1/2023.findings-acl.158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.158","pdf_url":"https://aclanthology.org/2023.findings-acl.158.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.17675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.17675","pdf_url":"https://arxiv.org/pdf/2306.17675","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.17675","doi":"https://doi.org/10.48550/arxiv.2306.17675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.17675","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-acl.158","doi":"https://doi.org/10.18653/v1/2023.findings-acl.158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.158","pdf_url":"https://aclanthology.org/2023.findings-acl.158.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572018.pdf","grobid_xml":"https://content.openalex.org/works/W4385572018.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2142192571","https://openalex.org/W2189070436","https://openalex.org/W2463565445","https://openalex.org/W2745461083","https://openalex.org/W2804243936","https://openalex.org/W2808877322","https://openalex.org/W2889015686","https://openalex.org/W2891394954","https://openalex.org/W2897980926","https://openalex.org/W2901466771","https://openalex.org/W2945383715","https://openalex.org/W2963056065","https://openalex.org/W2963954913","https://openalex.org/W2966146959","https://openalex.org/W2976365868","https://openalex.org/W2981852735","https://openalex.org/W2988841832","https://openalex.org/W3004349648","https://openalex.org/W3008686018","https://openalex.org/W3015883388","https://openalex.org/W3020908159","https://openalex.org/W3027879771","https://openalex.org/W3034671305","https://openalex.org/W3037181498","https://openalex.org/W3094502228","https://openalex.org/W3094950914","https://openalex.org/W3113715488","https://openalex.org/W3124404582","https://openalex.org/W3135367836","https://openalex.org/W3139224848","https://openalex.org/W3152015664","https://openalex.org/W3152956381","https://openalex.org/W3164654615","https://openalex.org/W3165058054","https://openalex.org/W3195541832","https://openalex.org/W4225667278","https://openalex.org/W4226089667","https://openalex.org/W4295938038","https://openalex.org/W4312971273","https://openalex.org/W4385573236","https://openalex.org/W4385574177"],"related_works":["https://openalex.org/W4383047263","https://openalex.org/W4403020990","https://openalex.org/W4402683917","https://openalex.org/W4411711556","https://openalex.org/W4382202719","https://openalex.org/W4408399585","https://openalex.org/W4388328732","https://openalex.org/W4402784356","https://openalex.org/W4409262891","https://openalex.org/W4387968292"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"impressive":[4],"results":[5],"of":[6],"pre-trained":[7],"vision-language":[8],"models":[9],"on":[10,43,107],"knowledge-intensive":[11],"tasks":[12,110],"such":[13],"as":[14],"visual":[15],"question":[16],"answering":[17],"(VQA).Despite":[18],"the":[19],"recent":[20],"advances":[21],"in":[22,86,124],"VQA,":[23],"existing":[24],"methods":[25],"mainly":[26],"adopt":[27],"a":[28,35,66,125],"discriminative":[29],"formulation":[30],"that":[31,76,112],"predicts":[32],"answers":[33,85],"within":[34],"pre-defined":[36],"label":[37],"set,":[38],"leading":[39],"to":[40,58,83,96,120],"easy":[41],"overfitting":[42],"low-resource":[44],"domains":[45],"with":[46],"limited":[47],"labeled":[48],"data":[49,98],"(e.g.,":[50],"medicine)":[51],"and":[52,80,100],"poor":[53],"generalization":[54],"under":[55],"domain":[56,127],"shift":[57],"another":[59],"dataset.To":[60],"tackle":[61],"this":[62],"limitation,":[63],"we":[64],"propose":[65],"novel":[67],"generative":[68,89],"model":[69,90],"enhanced":[70],"by":[71,118],"multimodal":[72,81],"prompt":[73],"retrieval":[74],"(MPR)":[75],"integrates":[77],"retrieved":[78],"prompts":[79],"features":[82],"generate":[84],"free":[87],"text.Our":[88],"enables":[91],"rapid":[92],"zero-shot":[93],"dataset":[94],"adaptation":[95,128],"unseen":[97],"distributions":[99],"open-set":[101],"answer":[102],"labels":[103],"across":[104],"datasets.Our":[105],"experiments":[106],"medical":[108],"VQA":[109],"show":[111],"MPR":[113],"outperforms":[114],"its":[115],"non-retrieval":[116],"counterpart":[117],"up":[119],"30%":[121],"accuracy":[122],"points":[123],"few-shot":[126],"setting.":[129],"1":[130]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-05T00:00:00"}