{"id":"https://openalex.org/W7133208370","doi":"https://doi.org/10.1109/tpami.2026.3669188","title":"Semi-Supervised VQA Multi-Modal Explanation via Self-Critical Learning","display_name":"Semi-Supervised VQA Multi-Modal Explanation via Self-Critical Learning","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133208370","doi":"https://doi.org/10.1109/tpami.2026.3669188","pmid":"https://pubmed.ncbi.nlm.nih.gov/41770977"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3669188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3669188","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5077386763","display_name":"Wei Suo","orcid":"https://orcid.org/0000-0002-8283-8637"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Suo","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-8283-8637","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100824433","display_name":"Ji Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Ma","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0004-6813-0511","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055917672","display_name":"Mengyang Sun","orcid":"https://orcid.org/0000-0003-0638-3295"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyang Sun","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0638-3295","affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-9218-9132"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-9218-9132","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-2977-8057","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127777290","display_name":"Qi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3631-256X","affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.20596166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"8361","last_page":"8377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.836899995803833,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.836899995803833,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.02800000086426735,"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":0.017799999564886093,"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/ambiguity","display_name":"Ambiguity","score":0.6421999931335449},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6151999831199646},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6086999773979187},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5551999807357788},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.536899983882904},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4693000018596649},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35040000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325999736785889},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6421999931335449},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6086999773979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605400025844574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.536899983882904},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2026.3669188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3669188","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41770977","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41770977","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:dr.ntu.edu.sg:10356/211903","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/211903","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5412412958","display_name":null,"funder_award_id":"62276176","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6462983346","display_name":null,"funder_award_id":"62472357","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7062685726","display_name":null,"funder_award_id":"2024JC-DXWT-07","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"},{"id":"https://openalex.org/G8813799148","display_name":null,"funder_award_id":"U23B2013","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/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"VQA":[0,10,91,189],"explanation":[1,30,190],"task":[2],"aims":[3],"to":[4,19,32,55,68,81,111,123,138],"explain":[5],"the":[6,47,101,114,118,125,173,179,187],"decision-making":[7],"process":[8,63,116],"of":[9,58,117,157,175],"models":[11],"in":[12,121],"a":[13,88,134,154,182],"way":[14],"that":[15],"is":[16],"easily":[17],"understandable":[18],"humans.":[20],"Existing":[21],"methods":[22],"mostly":[23],"use":[24],"visual":[25,107],"location":[26],"or":[27],"natural":[28],"language":[29],"approaches":[31],"generate":[33],"corresponding":[34],"rationales.":[35],"Although":[36],"significant":[37],"progress":[38],"has":[39],"been":[40],"made,":[41],"these":[42],"frameworks":[43],"are":[44,77],"bottlenecked":[45],"by":[46,104],"following":[48],"challenges:":[49],"1)":[50],"Uni-modal":[51],"paradigm":[52],"inevitably":[53],"leads":[54],"semantic":[56],"ambiguity":[57],"explanations.":[59],"2)":[60],"The":[61],"reasoning":[62],"cannot":[64],"be":[65],"faithfully":[66],"responded":[67],"and":[69,79,108,130,168],"suffers":[70],"from":[71,153],"logical":[72,126],"inconsistency.":[73],"3)":[74],"Human-annotated":[75],"explanations":[76,110,141,161],"expensive":[78],"time-consuming":[80],"collect.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,132],"introduce":[87],"new":[89,183],"Semi-supervised":[90],"Multi-modal":[92],"Explanation":[93],"(SME)":[94],"method":[95,150],"via":[96],"self-critical":[97,136],"learning,":[98],"which":[99],"addresses":[100],"above":[102],"challenges":[103],"leveraging":[105],"both":[106],"textual":[109],"comprehensively":[112],"reveal":[113],"inference":[115],"model.":[119],"Meanwhile,":[120],"order":[122],"improve":[124],"consistency":[127],"between":[128],"answers":[129],"rationales,":[131],"design":[133],"novel":[135],"strategy":[137],"evaluate":[139],"candidate":[140],"based":[142],"on":[143,186],"answer":[144],"reward":[145],"scores.":[146],"More":[147],"importantly,":[148],"our":[149,176],"can":[151],"benefit":[152],"tremendous":[155],"amount":[156],"samples":[158],"without":[159],"human-annotated":[160],"with":[162],"semi-supervised":[163],"learning.":[164],"Extensive":[165],"automatic":[166],"measures":[167],"human":[169],"evaluations":[170],"all":[171],"show":[172],"effectiveness":[174],"method.":[177],"Finally,":[178],"framework":[180],"achieves":[181],"state-of-the-art":[184],"performance":[185],"three":[188],"datasets.":[191]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-03-03T00:00:00"}