{"id":"https://openalex.org/W4285605365","doi":"https://doi.org/10.24963/ijcai.2022/453","title":"Declaration-based Prompt Tuning for Visual Question Answering","display_name":"Declaration-based Prompt Tuning for Visual Question Answering","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285605365","doi":"https://doi.org/10.24963/ijcai.2022/453"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/453","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/453","pdf_url":"https://www.ijcai.org/proceedings/2022/0453.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2022/0453.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028184484","display_name":"Yuhang Liu","orcid":"https://orcid.org/0000-0002-2770-9330"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Liu","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323842","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0003-4488-0102"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066682332","display_name":"Daowan Peng","orcid":"https://orcid.org/0000-0001-5208-3811"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daowan Peng","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003692270","display_name":"Feida Zhu","orcid":"https://orcid.org/0000-0001-6077-4356"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Feida Zhu","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0341,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91453744,"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":"3264","last_page":"3270"},"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":0.9904000163078308,"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":0.9821000099182129,"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/computer-science","display_name":"Computer science","score":0.8007043600082397},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6534504890441895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5937813520431519},{"id":"https://openalex.org/keywords/declaration","display_name":"Declaration","score":0.5791258811950684},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.542654275894165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5396282076835632},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5043851137161255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4980928897857666},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4883212745189667},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4219655990600586},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4133055508136749},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41039231419563293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40429452061653137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007043600082397},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6534504890441895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5937813520431519},{"id":"https://openalex.org/C138147947","wikidata":"https://www.wikidata.org/wiki/Q1183659","display_name":"Declaration","level":2,"score":0.5791258811950684},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.542654275894165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5396282076835632},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5043851137161255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4980928897857666},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4883212745189667},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4219655990600586},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4133055508136749},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41039231419563293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40429452061653137},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/453","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/453","pdf_url":"https://www.ijcai.org/proceedings/2022/0453.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-8755","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=8755&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.24963/ijcai.2022/453","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/453","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/453","pdf_url":"https://www.ijcai.org/proceedings/2022/0453.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[{"id":"https://openalex.org/G1250004542","display_name":null,"funder_award_id":"61602197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1915648697","display_name":null,"funder_award_id":"L1924068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2829588946","display_name":null,"funder_award_id":"AISG-GC-2019-003","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4599077227","display_name":null,"funder_award_id":"AISG Award No: AISG-GC-2019-003","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G7118507406","display_name":"\u878d\u5165\u6982\u5ff5\u7684\u9ad8\u6548\u4e3b\u9898\u5206\u6790\u6846\u67b6\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285605365.pdf","grobid_xml":"https://content.openalex.org/works/W4285605365.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2563399268","https://openalex.org/W2896457183","https://openalex.org/W2963518342","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W3035688398","https://openalex.org/W3080477479","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3111264121","https://openalex.org/W3118500473","https://openalex.org/W3126792443","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3167118264","https://openalex.org/W3173220247","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3204250462","https://openalex.org/W4286901992","https://openalex.org/W4287113019","https://openalex.org/W4288089799","https://openalex.org/W4288286281","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2374822965","https://openalex.org/W2093418863","https://openalex.org/W2993476977","https://openalex.org/W4213003656","https://openalex.org/W2384605597","https://openalex.org/W3134669730","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,64,67,74,96,114,120,124,131,137,146,161,168,182,201],"pre-training-then-fine-tuning":[4],"paradigm":[5,104],"has":[6],"yielded":[7],"immense":[8],"success":[9],"on":[10,175],"a":[11,25,56,86,186],"wide":[12],"spectrum":[13],"of":[14,66,76,89,127,164,170],"cross-modal":[15],"tasks,":[16,82],"such":[17],"as":[18,110],"visual":[19],"question":[20],"answering":[21],"(VQA),":[22],"in":[23,167,191],"which":[24,112,144,159],"visual-language":[26],"(VL)":[27],"model":[28,115],"is":[29],"first":[30],"optimized":[31],"via":[32,55,140],"self-supervised":[33],"task":[34,52,139,157],"objectives,":[35,122],"e.g.,":[36,60],"masked":[37],"language":[38],"modeling":[39],"(MLM)":[40],"and":[41,45,155,195,203],"image-text":[42],"matching":[43],"(ITM),":[44],"then":[46],"fine-tuned":[47,183],"to":[48,50,80,130,208],"adapt":[49],"downstream":[51,81,117,132],"(e.g.,":[53],"VQA)":[54],"brand-new":[57],"objective":[58,68,162],"function,":[59],"answer":[61],"prediction.":[62],"However,":[63],"inconsistency":[65],"forms":[69],"not":[70],"only":[71],"severely":[72],"limits":[73],"generalization":[75],"pre-trained":[77,128],"VL":[78,102],"models":[79,129],"but":[83],"also":[84],"requires":[85],"large":[87,187],"amount":[88],"labeled":[90],"data":[91,202],"for":[92,116,153],"fine-tuning.":[93],"To":[94],"alleviate":[95],"problem,":[97],"we":[98],"propose":[99],"an":[100],"innovative":[101],"fine-tuning":[103],"(named":[105],"Declaration-based":[106],"Prompt":[107],"Tuning,":[108],"abbreviated":[109],"DPT),":[111],"fine-tunes":[113],"VQA":[118,138,165],"using":[119],"pre-training":[121,171],"boosting":[123],"effective":[125],"adaptation":[126],"task.":[133],"Specifically,":[134],"DPT":[135,180],"reformulates":[136],"(1)":[141],"textual":[142],"adaptation,":[143,158],"converts":[145],"given":[147],"questions":[148],"into":[149],"declarative":[150],"sentence":[151],"form":[152],"prompt-tuning,":[154],"(2)":[156],"optimizes":[160],"function":[163],"problem":[166],"manner":[169],"phase.":[172],"Experimental":[173],"results":[174],"GQA":[176],"dataset":[177],"show":[178],"that":[179],"outperforms":[181],"counterpart":[184],"by":[185],"margin":[188],"regarding":[189],"accuracy":[190],"both":[192],"fully-supervised":[193],"(2.68%)":[194],"zero-shot/fewshot":[196],"(over":[197],"31%)":[198],"settings.":[199],"All":[200],"codes":[204],"will":[205],"be":[206],"available":[207],"facilitate":[209],"future":[210],"research.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}