{"id":"https://openalex.org/W7127125799","doi":"https://doi.org/10.1109/tmm.2026.3660119","title":"Multi-Modal Refined Prompting for Advancing Knowledge-Based Visual Question Answering","display_name":"Multi-Modal Refined Prompting for Advancing Knowledge-Based Visual Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7127125799","doi":"https://doi.org/10.1109/tmm.2026.3660119"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3660119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660119","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5101417345","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0002-4569-1429"},"institutions":[{"id":"https://openalex.org/I52180223","display_name":"Hunan Agricultural University","ror":"https://ror.org/01dzed356","country_code":"CN","type":"education","lineage":["https://openalex.org/I52180223"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["College of Information and Intelligence, Hunan Agricultural University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-4569-1429","affiliations":[{"raw_affiliation_string":"College of Information and Intelligence, Hunan Agricultural University, Changsha, China","institution_ids":["https://openalex.org/I52180223"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046092071","display_name":"Mengxi Ying","orcid":null},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxi Ying","raw_affiliation_strings":["School of Computer, Hunan University of Technology, Zhuzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-5566-3900","affiliations":[{"raw_affiliation_string":"School of Computer, Hunan University of Technology, Zhuzhou, China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124795582","display_name":"Chengyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyuan Zhang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2721-6867","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086497042","display_name":"Deyin Liu","orcid":"https://orcid.org/0000-0002-0371-9921"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyin Liu","raw_affiliation_strings":["Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0371-9921","affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124776547","display_name":"Lin Wu Shichao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lin Yuanbo Wu","raw_affiliation_strings":["School of Engineering, University of Warwick, England, U.K"],"raw_orcid":"https://orcid.org/0000-0001-6119-058X","affiliations":[{"raw_affiliation_string":"School of Engineering, University of Warwick, England, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124773868","display_name":"Xuelong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichao Zhang","raw_affiliation_strings":["Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0001-9981-2970","affiliations":[{"raw_affiliation_string":"Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI) of China Telecom, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2924-946X","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI) of China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101417345"],"corresponding_institution_ids":["https://openalex.org/I52180223"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17143614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3444","last_page":"3457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.9965999722480774,"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/T10028","display_name":"Topic Modeling","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/T10036","display_name":"Advanced Neural Network Applications","score":0.00039999998989515007,"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/closed-captioning","display_name":"Closed captioning","score":0.9617999792098999},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8083999752998352},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6812000274658203},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5055000185966492},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4124000072479248},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4088999927043915}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9617999792098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413000106811523},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8083999752998352},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6812000274658203},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5020999908447266},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4180000126361847},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4124000072479248},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2653999924659729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3660119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660119","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2254430272","display_name":null,"funder_award_id":"62072166","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2708669506","display_name":null,"funder_award_id":"62372150","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3340851556","display_name":null,"funder_award_id":"2023JJ30169","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G4682488780","display_name":null,"funder_award_id":"2022JJ40190","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G4754647585","display_name":null,"funder_award_id":"62202163","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4770605057","display_name":null,"funder_award_id":"2022JJ30231","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G8441992883","display_name":null,"funder_award_id":"62472161","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Knowledge-based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(KB-VQA)":[4],"has":[5],"surfaced":[6],"as":[7],"a":[8,59,78,96,125,173],"critical":[9],"task":[10],"in":[11,154,176],"advancing":[12],"AI":[13],"capabilities.":[14],"Despite":[15],"significant":[16,152],"progress":[17],"enabled":[18],"by":[19],"large":[20],"language":[21],"models":[22],"(LLMs),":[23],"there":[24],"are":[25,121],"still":[26],"three":[27],"major":[28],"challenges:":[29],"(1)":[30],"flawed":[31],"image":[32,80,116],"captions":[33,117],"cause":[34],"unreliable":[35],"reasoning;":[36],"(2)":[37],"noisy":[38],"explicit":[39,119],"knowledge":[40,98,120],"can":[41],"disrupts":[42],"answering;":[43],"and":[44,100,118,143],"(3)":[45],"massive":[46,141],"LLMs":[47,142],"scale":[48],"is":[49,83],"irreplaceable":[50],"to":[51,85,103],"robustness.":[52],"To":[53,73],"overcome":[54],"these":[55],"challenges,":[56],"we":[57,94],"develop":[58],"novel":[60],"approach,":[61],"Multi-Modal":[62],"Refined":[63],"Prompting":[64],"(MMRP),":[65],"which":[66],"generates":[67],"high-quality":[68],"prompts":[69],"tailored":[70],"for":[71,147],"LLMs.":[72,135],"tackle":[74],"the":[75,111,131,145,160,168],"first":[76],"challenge,":[77],"multi-faceted":[79],"captioning":[81],"strategy":[82,102],"employed":[84],"generate":[86],"detailed,":[87],"contextually":[88,106],"relevant":[89,107],"visual":[90],"descriptions.":[91],"In":[92],"addition,":[93],"introduce":[95],"complementary":[97],"retrieval":[99],"refinement":[101],"deliver":[104],"concise,":[105],"knowledge,":[108],"effectively":[109,129],"overcoming":[110],"second":[112],"challenge.":[113],"These":[114],"enhanced":[115],"then":[122],"integrated":[123],"into":[124],"knowledge-infused":[126],"in-context":[127],"prompt,":[128],"activating":[130],"reasoning":[132],"capabilities":[133],"of":[134,170],"Importantly,":[136],"MMRP":[137],"eliminates":[138],"reliance":[139],"on":[140,159],"avoids":[144],"need":[146],"model":[148],"fine-tuning,":[149],"while":[150],"achieving":[151],"improvements":[153],"answer":[155],"accuracy.":[156],"Extensive":[157],"evaluations":[158],"widely-used":[161],"OK-VQA":[162],"benchmark":[163],"against":[164],"22":[165],"baselines":[166],"prove":[167],"superiority":[169],"MMRP,":[171],"establishing":[172],"new":[174],"state-of-the-art":[175],"KB-VQA.":[177]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-02-03T00:00:00"}