{"id":"https://openalex.org/W4415337283","doi":"https://doi.org/10.18653/v1/2026.acl-long.881","title":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","display_name":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415337283","doi":"https://doi.org/10.18653/v1/2026.acl-long.881"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.881","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.881","pdf_url":"https://aclanthology.org/2026.acl-long.881.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.881.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113155098","display_name":"Changin Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changin Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379099","display_name":"Wonseok Lee","orcid":"https://orcid.org/0000-0002-4354-8506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wonseok Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041102782","display_name":"Jungmin Ko","orcid":"https://orcid.org/0000-0002-0879-7355"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jungmin Ko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056032525","display_name":"Wonjong Rhee","orcid":"https://orcid.org/0000-0002-2590-8774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wonjong Rhee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01251469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19291","last_page":"19315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944000244140625,"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":0.9593999981880188,"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":0.7759000062942505},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.48339998722076416},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4648999869823456},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42579999566078186},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4049000144004822},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.40290001034736633},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.3537999987602234},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.3434999883174896},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.32739999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777000069618225},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7759000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C2780613888","wikidata":"https://www.wikidata.org/wiki/Q6423394","display_name":"Knowledge retrieval","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.881","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.881","pdf_url":"https://aclanthology.org/2026.acl-long.881.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.00798","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00798","pdf_url":"https://arxiv.org/pdf/2509.00798","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,"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":"pmh:oai:arXiv.org:2509.00798","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.00798","pdf_url":"https://arxiv.org/pdf/2509.00798","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2509.00798","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2509.00798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.00798","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.881","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.881","pdf_url":"https://aclanthology.org/2026.acl-long.881.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1317682478","display_name":null,"funder_award_id":"NO. RS-2021-II211343","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G269467657","display_name":null,"funder_award_id":"NO.RS-2021-II211343","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G2784508656","display_name":null,"funder_award_id":"NO.RS-2021-II211343","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2947324332","display_name":null,"funder_award_id":"RS-2021II211343","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4475359334","display_name":null,"funder_award_id":"RS2021-II211343","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G6120464043","display_name":null,"funder_award_id":"RS2021-II211343","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7580349198","display_name":null,"funder_award_id":"RS-2023-00235293","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G8441597283","display_name":null,"funder_award_id":"RS-2023-","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415337283.pdf","grobid_xml":"https://content.openalex.org/works/W4415337283.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Knowledge-intensive":[0],"visual":[1,13,19],"question":[2],"answering":[3],"(VQA)":[4],"requires":[5],"external":[6,32],"knowledge":[7,33,47,74,93,96],"beyond":[8],"image":[9],"content,":[10],"demanding":[11],"precise":[12],"grounding":[14],"and":[15,20,48,60,76,87,134,144],"coherent":[16],"integration":[17],"of":[18],"textual":[21],"information.Although":[22],"multimodal":[23],"retrieval-augmented":[24],"generation":[25],"has":[26],"achieved":[27],"notable":[28],"advances":[29],"by":[30],"incorporating":[31],"bases,":[34],"existing":[35],"approaches":[36],"largely":[37],"adopt":[38],"single-pass":[39],"frameworks":[40],"that":[41,64,137],"often":[42],"fail":[43],"to":[44,51,71,90],"acquire":[45],"sufficient":[46],"lack":[49],"mechanisms":[50],"revise":[52],"misdirected":[53],"reasoning.We":[54],"propose":[55],"PMSR":[56,138],"(Progressive":[57],"Multimodal":[58],"Search":[59],"Reasoning),":[61],"a":[62,67],"framework":[63],"progressively":[65],"constructs":[66],"structured":[68],"reasoning":[69,118],"trajectory":[70,89],"enhance":[72],"both":[73,83,141],"acquisition":[75],"synthesis.PMSR":[77],"uses":[78],"dual-scope":[79],"queries":[80],"conditioned":[81],"on":[82],"the":[84,88],"latest":[85],"record":[86],"retrieve":[91],"diverse":[92,127],"from":[94],"heterogeneous":[95],"bases.The":[97],"retrieved":[98],"evidence":[99],"is":[100],"then":[101],"synthesized":[102],"into":[103],"compact":[104],"records":[105],"via":[106],"compositional":[107],"reasoning.This":[108],"design":[109],"facilitates":[110],"controlled":[111],"iterative":[112],"refinement,":[113],"which":[114],"supports":[115],"more":[116],"stable":[117],"trajectories":[119],"with":[120],"reduced":[121],"error":[122],"propagation.Extensive":[123],"experiments":[124],"across":[125],"six":[126],"benchmarks":[128],"(Encyclopedic-VQA,":[129],"InfoSeek,":[130],"MMSearch,":[131],"LiveVQA,":[132],"FVQA,":[133],"OK-VQA)":[135],"demonstrate":[136],"consistently":[139],"improves":[140],"retrieval":[142],"recall":[143],"end-to-end":[145],"answer":[146],"accuracy.":[147]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-19T00:00:00"}