{"id":"https://openalex.org/W7164808416","doi":"https://doi.org/10.1145/3805622.3810578","title":"Adaptive Knowledge Generation via Reinforcement-Guided Pattern Completion for Zero-Shot Visual Question Answering","display_name":"Adaptive Knowledge Generation via Reinforcement-Guided Pattern Completion for Zero-Shot Visual Question Answering","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164808416","doi":"https://doi.org/10.1145/3805622.3810578"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810578","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 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://doi.org/10.1145/3805622.3810578","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023956164","display_name":"Zhihui Sun","orcid":"https://orcid.org/0000-0001-7255-7906"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Sun","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7799-1534","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065954736","display_name":"Diwei Su","orcid":"https://orcid.org/0000-0002-2503-4202"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diwei Su","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2503-4202","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059036409","display_name":"Xiuxing Li","orcid":"https://orcid.org/0000-0002-1178-7422"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuxing Li","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1178-7422","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107723891","display_name":"Qixin Wang","orcid":"https://orcid.org/0009-0005-8597-2160"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixin Wang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-8597-2160","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624697","display_name":"Shihao Zhang","orcid":"https://orcid.org/0009-0005-2961-8036"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Zhang","raw_affiliation_strings":["Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-2961-8036","affiliations":[{"raw_affiliation_string":"Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007297993","display_name":"Xia Wu","orcid":"https://orcid.org/0000-0002-2377-6093"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Wu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2377-6093","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93392854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1174","last_page":"1183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.993399977684021,"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":0.993399977684021,"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":0.002400000113993883,"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":0.000699999975040555,"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/question-answering","display_name":"Question answering","score":0.746999979019165},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6854000091552734},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6187999844551086},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37209999561309814},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34279999136924744},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.3402000069618225},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3271999955177307}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.746999979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239000201225281},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6854000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6650000214576721},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810578","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810578","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2107669731","https://openalex.org/W2555661914","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2891394954","https://openalex.org/W2947312908","https://openalex.org/W2964303913","https://openalex.org/W2968235818","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3095319910","https://openalex.org/W3134329288","https://openalex.org/W3173220247","https://openalex.org/W3195541832","https://openalex.org/W3199693760","https://openalex.org/W4226452284","https://openalex.org/W4287113019","https://openalex.org/W4288562623","https://openalex.org/W4312846625","https://openalex.org/W4318718936","https://openalex.org/W4383176408","https://openalex.org/W4385574156","https://openalex.org/W4386076140","https://openalex.org/W4387123761","https://openalex.org/W4387968292","https://openalex.org/W4390059555","https://openalex.org/W4392504399","https://openalex.org/W4393252868","https://openalex.org/W4401655528","https://openalex.org/W4402705643","https://openalex.org/W4402916478","https://openalex.org/W4405288537","https://openalex.org/W4407049645","https://openalex.org/W4407392290","https://openalex.org/W4408050159","https://openalex.org/W4408399585","https://openalex.org/W4409269797","https://openalex.org/W4409641194","https://openalex.org/W4414458022","https://openalex.org/W4415154444","https://openalex.org/W4416615158","https://openalex.org/W6903568121","https://openalex.org/W7105798221","https://openalex.org/W7126447397","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133220561","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"visual":[1,23],"question":[2],"answering":[3],"(VQA)":[4],"requires":[5],"models":[6,38],"to":[7,31,39,59],"reason":[8],"over":[9],"unseen":[10],"image\u2013question":[11],"pairs":[12],"without":[13,144],"task-specific":[14],"supervision,":[15],"where":[16],"performance":[17,156],"is":[18],"often":[19],"undermined":[20],"by":[21,34,68],"incomplete":[22],"grounding":[24],"and":[25,46,83,150,157],"unstable":[26],"reasoning.":[27],"Recent":[28],"approaches":[29],"attempt":[30],"mitigate":[32],"this":[33],"using":[35],"large":[36],"language":[37],"generate":[40],"external":[41,145],"knowledge":[42,125],"conditioned":[43],"on":[44,148],"captions":[45],"questions.":[47],"However,":[48],"these":[49],"methods":[50],"typically":[51],"operate":[52],"in":[53],"an":[54],"open-loop":[55,132],"manner,":[56],"lacking":[57],"mechanisms":[58],"regulate":[60],"competing":[61],"interpretations":[62],"or":[63],"correct":[64],"misaligned":[65],"knowledge.":[66],"Inspired":[67],"the":[69,165,169],"hippocampal":[70],"pattern":[71],"completion":[72,98],"mechanism,":[73],"which":[74,92],"supports":[75],"inference":[76,133],"from":[77,168],"partial":[78],"observations":[79],"through":[80,120],"memory":[81],"reactivation":[82],"competitive":[84,128],"stabilization,":[85],"we":[86],"propose":[87],"ARK-PC":[88,130],"for":[89],"zero-shot":[90,155],"VQA,":[91],"formulates":[93],"reasoning":[94,141],"as":[95],"a":[96,135],"two-stage":[97],"process.":[99],"It":[100],"first":[101],"expands":[102],"fragmented":[103],"multimodal":[104],"cues":[105],"into":[106,134],"multiple":[107],"structured":[108],"candidate":[109],"hypotheses,":[110],"then":[111],"adaptively":[112],"reinforces":[113],"coherent":[114],"candidates":[115],"while":[116],"suppressing":[117],"inconsistent":[118],"ones":[119],"iterative":[121],"feedback.":[122],"By":[123],"coupling":[124],"generation":[126],"with":[127],"refinement,":[129],"transforms":[131],"closed-loop":[136],"stabilization":[137],"process,":[138],"enabling":[139],"robust":[140],"under":[142],"uncertainty":[143],"supervision.":[146],"Experiments":[147],"OK-VQA":[149],"A-OKVQA":[151],"demonstrate":[152],"consistent":[153],"state-of-the-art":[154],"strong":[158],"generalization":[159],"across":[160],"diverse":[161],"backbones,":[162],"indicating":[163],"that":[164],"improvements":[166],"stem":[167],"proposed":[170],"framework":[171],"rather":[172],"than":[173],"model":[174],"scale.":[175]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}