{"id":"https://openalex.org/W4415708054","doi":"https://doi.org/10.1109/icme59968.2025.11209232","title":"Can MLLMs Tell Jokes Based on Images? A Visual Context-Driven Humor Generation Framework","display_name":"Can MLLMs Tell Jokes Based on Images? A Visual Context-Driven Humor Generation Framework","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708054","doi":"https://doi.org/10.1109/icme59968.2025.11209232"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5101633311","display_name":"Meixuan Chen","orcid":"https://orcid.org/0000-0003-0343-2645"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meixuan Chen","raw_affiliation_strings":["Huazhong Agricultural University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University,Wuhan,China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337487","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0001-6798-0312"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["Huazhong Agricultural University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University,Wuhan,China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042662250","display_name":"Hui Liu","orcid":"https://orcid.org/0000-0002-8249-925X"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Hui","raw_affiliation_strings":["Huazhong Agricultural University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University,Wuhan,China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981033","display_name":"Yujun Wu","orcid":"https://orcid.org/0009-0001-6796-4934"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wu","raw_affiliation_strings":["Huazhong Agricultural University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University,Wuhan,China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025938663","display_name":"Ying Sha","orcid":"https://orcid.org/0000-0002-6638-5009"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Sha","raw_affiliation_strings":["Huazhong Agricultural University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong Agricultural University,Wuhan,China","institution_ids":["https://openalex.org/I204823248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101633311"],"corresponding_institution_ids":["https://openalex.org/I204823248"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37487957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11795","display_name":"Humor Studies and Applications","score":0.6524999737739563,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11795","display_name":"Humor Studies and Applications","score":0.6524999737739563,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16279999911785126,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.039900001138448715,"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/discriminative-model","display_name":"Discriminative model","score":0.5785999894142151},{"id":"https://openalex.org/keywords/rhetorical-question","display_name":"Rhetorical question","score":0.5726000070571899},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5557000041007996},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5099999904632568},{"id":"https://openalex.org/keywords/humor-research","display_name":"Humor research","score":0.4246000051498413},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.39259999990463257},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6028000116348267},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C192562157","wikidata":"https://www.wikidata.org/wiki/Q316694","display_name":"Rhetorical question","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5557000041007996},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C522138142","wikidata":"https://www.wikidata.org/wiki/Q16247567","display_name":"Humor research","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C62291451","wikidata":"https://www.wikidata.org/wiki/Q1762471","display_name":"Rhetorical device","level":3,"score":0.33550000190734863},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3244999945163727},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C23929507","wikidata":"https://www.wikidata.org/wiki/Q263668","display_name":"Pun","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2798778974","https://openalex.org/W2966559663","https://openalex.org/W3117667887","https://openalex.org/W3183822815","https://openalex.org/W4393160465","https://openalex.org/W4401043099","https://openalex.org/W4402670135","https://openalex.org/W4402670757","https://openalex.org/W4402704595","https://openalex.org/W4402727669"],"related_works":[],"abstract_inverted_index":{"Image-based":[0],"humor":[1,41,45,73,111,154],"text":[2,155],"generation":[3],"aims":[4],"to":[5,81,94,116,131],"produce":[6],"humorous":[7],"responses":[8,124],"from":[9],"input":[10,104],"images,":[11],"which":[12],"is":[13,92,114],"a":[14,110],"pivotal":[15],"task":[16],"in":[17,38,152],"computational":[18],"humor.":[19,87],"Current":[20],"research":[21],"predominantly":[22],"leverages":[23],"multimodal":[24],"large":[25],"language":[26],"models":[27],"(MLLMs),":[28],"making":[29],"notable":[30],"progress.":[31],"However,":[32],"these":[33,59],"approaches":[34],"still":[35],"encounter":[36],"challenges":[37],"fully":[39],"understanding":[40],"theory,":[42],"effectively":[43],"utilizing":[44],"rhetorical":[46,76],"devices":[47,77],"(e.g.,":[48],"puns":[49],"and":[50,52,75,105,125],"irony)":[51],"capturing":[53],"nuanced":[54],"visual":[55,96,103],"semantics.":[56],"To":[57],"tackle":[58],"issues,":[60],"we":[61],"propose":[62],"the":[63,83,102,106,122,133,146],"Visual":[64],"Context-Driven":[65],"Humor":[66],"Generation":[67],"(VCDHG)":[68],"framework.":[69],"We":[70],"initially":[71],"incorporate":[72],"theory":[74],"into":[78],"instruction":[79],"tuning":[80],"improve":[82],"MLLM\u2019s":[84],"comprehension":[85],"of":[86],"Subsequently,":[88],"Chain-of-Thought":[89],"prompting":[90],"strategy":[91],"utilized":[93],"extract":[95],"semantics,":[97],"ensuring":[98],"effective":[99],"alignment":[100],"between":[101],"generated":[107,123],"text.":[108],"Additionally,":[109],"discriminative":[112],"model":[113],"employed":[115],"assist":[117],"reinforcement":[118],"learning":[119],"by":[120],"evaluating":[121],"providing":[126],"feedback":[127],"as":[128],"reward":[129],"signals":[130],"refine":[132],"generative":[134],"model.":[135],"Extensive":[136],"experiments":[137],"demonstrate":[138],"that":[139],"VCDHG":[140],"outperforms":[141],"State-of-the-Art":[142],"(SOTA)":[143],"methods":[144],"on":[145],"Oogiri-GO":[147],"dataset,":[148],"validating":[149],"its":[150],"effectiveness":[151],"cross-modal":[153],"generation.":[156]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}