{"id":"https://openalex.org/W4387969662","doi":"https://doi.org/10.1145/3581783.3612222","title":"Self-PT: Adaptive Self-Prompt Tuning for Low-Resource Visual Question Answering","display_name":"Self-PT: Adaptive Self-Prompt Tuning for Low-Resource Visual Question Answering","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969662","doi":"https://doi.org/10.1145/3581783.3612222"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5100740413","display_name":"Bowen Yuan","orcid":"https://orcid.org/0000-0002-8051-3070"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bowen Yuan","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101970691","display_name":"Sisi You","orcid":"https://orcid.org/0009-0004-2173-1694"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sisi You","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications & Peng Cheng Laboratory, Nanjing & Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications & Peng Cheng Laboratory, Nanjing & Shenzhen, China","institution_ids":["https://openalex.org/I41198531","https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100740413"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.2384,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53529251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5089","last_page":"5098"},"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":0.9980000257492065,"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":0.9836999773979187,"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/overfitting","display_name":"Overfitting","score":0.8757340908050537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8238447904586792},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6020488142967224},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5656549334526062},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5327406525611877},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5136551260948181},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4893438220024109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4811781346797943},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.47104716300964355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4563671946525574},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4186929762363434},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41274768114089966},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15965500473976135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09822165966033936}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8757340908050537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238447904586792},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6020488142967224},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5656549334526062},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5327406525611877},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5136551260948181},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4893438220024109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4811781346797943},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.47104716300964355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4563671946525574},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4186929762363434},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41274768114089966},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15965500473976135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09822165966033936},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4317995357","display_name":null,"funder_award_id":"61936005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5854786607","display_name":null,"funder_award_id":"Tianjin","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320317442","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322701","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2947312908","https://openalex.org/W2963518342","https://openalex.org/W3153675281","https://openalex.org/W3166140588","https://openalex.org/W3173220247","https://openalex.org/W3173777717","https://openalex.org/W3174770825","https://openalex.org/W3176828726","https://openalex.org/W3177174258","https://openalex.org/W3198377975","https://openalex.org/W3198571508","https://openalex.org/W3199693760","https://openalex.org/W3207493267","https://openalex.org/W4205460703","https://openalex.org/W4238846128","https://openalex.org/W4285191490","https://openalex.org/W4285247752","https://openalex.org/W4286856918","https://openalex.org/W4287113019","https://openalex.org/W4287122891","https://openalex.org/W4304014869","https://openalex.org/W4312238419","https://openalex.org/W4312310776","https://openalex.org/W4312784228","https://openalex.org/W4312884055","https://openalex.org/W4385572883","https://openalex.org/W4385573610","https://openalex.org/W4386071687","https://openalex.org/W4386075505","https://openalex.org/W6603054696","https://openalex.org/W6804126242","https://openalex.org/W6820618299"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Pretraining":[0],"and":[1,25,64,121,133,142,151,170,192],"finetuning":[2,17],"large":[3],"vision-language":[4],"models":[5],"(VLMs)":[6],"have":[7,39],"achieved":[8],"remarkable":[9],"success":[10],"in":[11,32,57,208,218],"visual":[12],"question":[13],"answering":[14],"(VQA).":[15],"However,":[16],"VLMs":[18],"requires":[19],"heavy":[20],"computation,":[21],"expensive":[22],"storage":[23],"costs,":[24],"is":[26,221],"prone":[27],"to":[28,97,113,137,154],"overfitting":[29,115],"for":[30,81,182],"VQA":[31,83,189],"low-resource":[33,82,196],"settings.":[34],"Existing":[35],"prompt":[36,54,78,152,176],"tuning":[37,79],"methods":[38],"reduced":[40],"the":[41,103,116,147,159,165,172,175,203],"number":[42,148,161],"of":[43,61,92,105,149,162,174],"tunable":[44],"parameters,":[45,129],"but":[46],"they":[47],"cannot":[48],"capture":[49],"valid":[50],"context-aware":[51,99],"information":[52],"during":[53,125],"encoding,":[55],"resulting":[56],"1)":[58],"poor":[59],"generalization":[60,104],"unseen":[62,106],"answers":[63,123],"2)":[65],"lower":[66],"improvements":[67,214],"with":[68,194],"more":[69,140],"parameters.":[70,163],"To":[71,101,127],"address":[72],"these":[73],"issues,":[74],"we":[75,130],"propose":[76],"a":[77,179],"method":[80],"named":[84],"Adaptive":[85],"Self-Prompt":[86],"Tuning":[87],"(Self-PT),":[88],"which":[89],"utilizes":[90],"representations":[91],"question-image":[93],"pairs":[94],"as":[95],"conditions":[96],"obtain":[98],"prompts.":[100],"enhance":[102],"answers,":[107],"Self-PT":[108,139,201],"uses":[109],"dynamic":[110],"instance-level":[111],"prompts":[112,120,157],"avoid":[114],"correlations":[117],"between":[118],"static":[119],"seen":[122],"observed":[124],"training.":[126],"reduce":[128],"utilize":[131],"hyper-networks":[132],"low-rank":[134,166,180],"parameter":[135,167,184],"factorization":[136,168],"make":[138],"flexible":[141],"efficient.":[143],"The":[144],"hyper-network":[145],"decouples":[146],"parameters":[150],"length":[153],"generate":[155],"flexible-length":[156],"by":[158],"fixed":[160],"While":[164],"decomposes":[169],"reparameterizes":[171],"weights":[173],"encoder":[177],"into":[178],"subspace":[181],"better":[183],"efficiency.":[185],"Experiments":[186],"conducted":[187],"on":[188],"v2,":[190],"GQA,":[191],"OK-VQA":[193],"different":[195],"settings":[197],"show":[198],"that":[199],"our":[200],"outperforms":[202],"state-of-the-art":[204],"parameter-efficient":[205],"methods,":[206],"especially":[207],"lower-shot":[209],"settings,":[210],"e.g.,":[211],"6%":[212],"average":[213],"cross":[215],"three":[216],"datasets":[217],"16-shot.":[219],"Code":[220],"available":[222],"at":[223],"https://github.com/NJUPT-MCC/Self-PT.":[224]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}