{"id":"https://openalex.org/W7129457121","doi":"https://doi.org/10.1109/tcsvt.2026.3665739","title":"M <sup>3</sup> Former: Memory-Guided Multi-Modal Generation and Adaptive Mixture Reasoning for Incomplete-Modality Crisis Event Detection","display_name":"M <sup>3</sup> Former: Memory-Guided Multi-Modal Generation and Adaptive Mixture Reasoning for Incomplete-Modality Crisis Event Detection","publication_year":2026,"publication_date":"2026-02-17","ids":{"openalex":"https://openalex.org/W7129457121","doi":"https://doi.org/10.1109/tcsvt.2026.3665739"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3665739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3665739","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5100675829","display_name":"Chenyang Lu","orcid":"https://orcid.org/0000-0002-5565-7689"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Lu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091545406","display_name":"Boyue Wang","orcid":"https://orcid.org/0000-0002-2677-8342"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyue Wang","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2677-8342","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102969335","display_name":"Tengfei Liu","orcid":"https://orcid.org/0000-0002-2739-5220"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengfei Liu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419125","display_name":"Tian Tian","orcid":"https://orcid.org/0000-0002-6044-9083"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Tian","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongli Hu","orcid":"https://orcid.org/0000-0003-0440-438X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongli Hu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0440-438X","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126179873","display_name":"Baocai Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3121-1823","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1598127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"7965","last_page":"7978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11121","display_name":"Public Relations and Crisis Communication","score":0.6647999882698059,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11121","display_name":"Public Relations and Crisis Communication","score":0.6647999882698059,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12330000102519989,"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":0.03519999980926514,"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/event","display_name":"Event (particle physics)","score":0.6310999989509583},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5787000060081482},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5465999841690063},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5311999917030334},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/situation-awareness","display_name":"Situation awareness","score":0.4887999892234802},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.43560001254081726},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38659998774528503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8561999797821045},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6310999989509583},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5465999841690063},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C145804949","wikidata":"https://www.wikidata.org/wiki/Q478123","display_name":"Situation awareness","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4235000014305115},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3610999882221222},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.33160001039505005},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3034000098705292},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C123606473","wikidata":"https://www.wikidata.org/wiki/Q907918","display_name":"Complex event processing","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3665739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3665739","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1098515591","display_name":null,"funder_award_id":"62272015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G583279621","display_name":null,"funder_award_id":"2023YFC3304601","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6152166824","display_name":null,"funder_award_id":"92370102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6770101281","display_name":null,"funder_award_id":"52441202","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"crisis":[1,106,220],"event":[2,107],"detection":[3],"is":[4,239],"critical":[5],"for":[6,103,138,146],"timely":[7],"situational":[8],"awareness":[9],"across":[10,69],"diverse":[11],"real-world":[12,219],"emergencies.":[13],"In":[14],"practice,":[15],"however,":[16],"multi-modal":[17,105,142],"data\u2014typically":[18],"composed":[19],"of":[20,36,111,122,212,234],"images":[21],"and":[22,71,74,84,131,141,157,165,178,185,201,208],"textual":[23],"reports\u2014are":[24],"often":[25],"incomplete,":[26],"with":[27],"many":[28],"instances":[29],"providing":[30],"only":[31],"a":[32,99,119,192,232],"single":[33],"modality":[34],"because":[35],"data":[37,125],"loss,":[38],"platform":[39],"constraints,":[40],"or":[41],"real-time":[42],"limitations.":[43],"This":[44],"modality-incomplete":[45,104,235],"setting":[46],"poses":[47],"three":[48],"key":[49],"challenges:":[50],"(1)":[51],"how":[52,63,76],"to":[53,58,64,77,126,182,204],"reliably":[54],"reconstruct":[55],"missing":[56],"modalities":[57],"restore":[59],"cross-modal":[60,160,180],"context,":[61],"(2)":[62],"extract":[65],"deep":[66],"semantic":[67,161,186],"clues":[68],"original":[70,164],"completed":[72,166],"data,":[73],"(3)":[75],"bridge":[78],"the":[79,210],"distributional":[80,206],"gap":[81],"between":[82,163],"reconstructed":[83],"fully-observed":[85],"samples":[86,130],"during":[87],"model":[88],"training.":[89],"To":[90],"tackle":[91],"these":[92],"issues,":[93],"we":[94],"propose":[95],"M<sup":[96,224],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[97,225],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>Former,":[98],"unified":[100],"framework":[101],"tailored":[102],"detection.":[108],"It":[109],"consists":[110],"four":[112],"dedicated":[113],"modules:":[114],"Memory-Guided":[115],"Modality":[116],"Completion":[117],"builds":[118],"memory":[120],"bank":[121],"paired":[123],"image\u2013text":[124],"retrieve":[127],"semantically":[128],"related":[129],"keywords,":[132],"guiding":[133],"powerful":[134],"pretrained":[135],"generators\u2014diffusion":[136],"models":[137,145],"image":[139],"synthesis":[140],"large":[143],"language":[144],"text":[147],"generation;":[148],"Crisis-Aware":[149],"Heterogeneous":[150],"Dual-Stream":[151],"Encoders":[152],"jointly":[153],"capture":[154],"modality-specific":[155,200],"cues":[156],"establish":[158],"initial":[159],"alignment":[162],"data;":[167],"Hierarchical":[168],"Attention":[169],"Refinement":[170],"Network":[171],"progressively":[172],"refines":[173],"representations":[174],"through":[175],"hierarchical":[176],"attention":[177],"guided":[179],"interaction":[181],"suppress":[183],"noise":[184],"drift;":[187],"Modality-aware":[188],"Routing":[189],"Experts":[190],"designs":[191],"gated":[193],"mixture-of-experts":[194],"architecture":[195],"that":[196,223],"dynamically":[197],"selects":[198],"both":[199],"shared":[202],"experts":[203],"mitigate":[205],"shifts":[207],"enhance":[209],"quality":[211],"fused":[213],"representations.":[214],"Extensive":[215],"experiments":[216],"on":[217],"two":[218],"datasets":[221],"demonstrate":[222],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>Former":[226],"significantly":[227],"outperforms":[228],"existing":[229],"baselines":[230],"under":[231],"variety":[233],"scenarios.":[236],"The":[237],"code":[238],"available:":[240],"https://github.com/lcygky/M3former.":[241]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-18T00:00:00"}