{"id":"https://openalex.org/W7160234495","doi":"https://doi.org/10.1109/tkde.2026.3690133","title":"Modeling Deep Fusion of Intra- and Inter-Modal Incongruity for Multimodal Sarcasm Detection","display_name":"Modeling Deep Fusion of Intra- and Inter-Modal Incongruity for Multimodal Sarcasm Detection","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160234495","doi":"https://doi.org/10.1109/tkde.2026.3690133"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2026.3690133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3690133","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","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/A5009594218","display_name":"Fengmao Lv","orcid":"https://orcid.org/0000-0003-1640-0992"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengmao Lv","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0003-1640-0992","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135316587","display_name":"Junlin Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlin Fang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0002-8162-3201","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135355343","display_name":"Guosheng Lin","orcid":null},"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":"Guosheng Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0329-7458","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135301040","display_name":"Wenya Wang","orcid":null},"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":"Wenya Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5612-7818","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43497994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"7","first_page":"4569","last_page":"4583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.8684999942779541,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.8684999942779541,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01850000023841858,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.014999999664723873,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sarcasm","display_name":"Sarcasm","score":0.8187000155448914},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6015999913215637},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5845000147819519},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41679999232292175},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4106000065803528},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3711000084877014},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.3571000099182129},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.34049999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187000155448914},{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.8187000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7113999724388123},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4083000123500824},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.34049999713897705},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2026.3690133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3690133","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/219765","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/219765","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/G6159829169","display_name":null,"funder_award_id":"2682026ZT007","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8781092357","display_name":null,"funder_award_id":"2025YFHZ0124","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,105],"sarcasm":[1,20],"detection":[2,21],"receives":[3],"increasing":[4],"attentions":[5],"due":[6],"to":[7,23,52,116,162,194],"people's":[8],"growing":[9],"interest":[10],"in":[11],"posting":[12],"multimodal":[13,19,91],"information.":[14,72,127],"The":[15],"key":[16],"factor":[17],"of":[18,67,86,121,140,187,198],"is":[22],"leverage":[24],"incongruity":[25,47,71,87,126,176],"information":[26,135,177],"across":[27],"different":[28],"modalities.":[29],"Existing":[30],"works":[31],"are":[32,50,192],"mainly":[33,60],"based":[34],"on":[35,62,155,167],"the":[36,43,64,80,83,118,130,138,163,168,172,196],"late":[37],"fusion":[38,66,120],"strategy":[39],"by":[40],"simply":[41],"concatenating":[42],"intra-":[44,68,122,173],"and":[45,69,123,174,181],"inter-modal":[46,70,175],"features,":[48],"which":[49,153],"prone":[51],"learning":[53],"surface":[54],"patterns.":[55],"In":[56],"contrast,":[57],"this":[58,74,76,94],"work":[59,77],"focuses":[61,154],"modeling":[63,139],"deep":[65,119,185],"To":[73,128],"end,":[75],"first":[78],"discusses":[79],"incompatibility":[81],"between":[82],"two":[84],"kinds":[85],"features":[88,186],"within":[89],"existing":[90],"frameworks.":[92],"Under":[93],"motivation,":[95],"we":[96],"further":[97],"propose":[98],"an":[99],"end-to-end":[100],"cooperative":[101,147,170],"framework":[102],"dubbed":[103],"Cooperative":[104],"Incongruity":[106],"Learning":[107],"(CoMIL).":[108],"Specifically,":[109],"our":[110,199],"approach":[111],"incorporates":[112],"a":[113,146,150,159],"primary":[114,164],"module":[115,152],"model":[117],"inter":[124,132],"modal":[125,133],"prevent":[129],"integrated":[131,183],"visual":[134],"from":[136],"disturbing":[137],"intra":[141],"text":[142],"incongruity,":[143],"CoMIL":[144,201],"introduces":[145],"mechanism":[148],"incorporating":[149],"reference":[151],"token-level":[156],"correlations":[157],"as":[158],"structural":[160],"guidance":[161],"module.":[165],"Based":[166],"proposed":[169,200],"mechanism,":[171],"can":[178],"be":[179],"compactly":[180],"compatibly":[182],"into":[184],"neural":[188],"models.":[189],"Extensive":[190],"experiments":[191],"conducted":[193],"validate":[195],"effectiveness":[197],"approach.":[202]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-05-06T00:00:00"}