{"id":"https://openalex.org/W7137916771","doi":"https://doi.org/10.1609/aaai.v40i39.40579","title":"Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion","display_name":"Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137916771","doi":"https://doi.org/10.1609/aaai.v40i39.40579"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i39.40579","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40579","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i39.40579","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103238482","display_name":"Yi Shi","orcid":"https://orcid.org/0009-0009-0834-1030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051774674","display_name":"Wenlong Meng","orcid":"https://orcid.org/0000-0002-1032-3618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenlong Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051086253","display_name":"Zhenyuan Guo","orcid":"https://orcid.org/0000-0003-2564-6433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenyuan Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006624972","display_name":"Chengkun Wei","orcid":"https://orcid.org/0000-0001-8849-8808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengkun Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101562847","display_name":"Wenzhi Chen","orcid":"https://orcid.org/0000-0003-1674-4701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhi Chen","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"39","first_page":"32974","last_page":"32982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.30570000410079956,"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":0.30570000410079956,"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/T11795","display_name":"Humor Studies and Applications","score":0.2574999928474426,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.10830000042915344,"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/robustness","display_name":"Robustness (evolution)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4406000077724457},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4154999852180481},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.3815000057220459},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.36000001430511475},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.3312999904155731},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3310999870300293},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.3305000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507000088691711},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49729999899864197},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i39.40579","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40579","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i39.40579","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40579","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4056781232357025,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,34,97,125,144,157,162,172,216],"rapid":[2],"rise":[3],"of":[4,58,67,103,220],"social":[5],"media":[6],"and":[7,63,71,100,112,115,129,154,165,186,205,212,218],"Internet":[8],"culture,":[9],"memes":[10,38],"have":[11,47],"become":[12],"a":[13,56,81,90,139],"popular":[14],"medium":[15],"for":[16,84,133,227],"expressing":[17],"emotional":[18,35,179],"tendencies.":[19],"This":[20,168],"has":[21],"sparked":[22],"growing":[23],"interest":[24],"in":[25],"Meme":[26],"Emotion":[27],"Understanding":[28],"(MEU),":[29],"which":[30],"aims":[31],"to":[32,109,174],"classify":[33],"intent":[36],"behind":[37],"by":[39,201],"leveraging":[40],"their":[41],"multimodal":[42,60],"contents.":[43],"While":[44],"existing":[45],"efforts":[46],"achieved":[48],"promising":[49],"results,":[50],"two":[51,183],"major":[52],"challenges":[53],"remain:":[54],"(1)":[55],"lack":[57],"fine-grained":[59],"fusion":[61,142,149,170],"strategies,":[62],"(2)":[64],"insufficient":[65],"mining":[66],"memes'":[68],"implicit":[69,114],"meanings":[70],"background":[72],"knowledge.":[73],"To":[74],"address":[75],"these":[76],"challenges,":[77],"we":[78,88,137],"propose":[79],"MemoDetector,":[80],"novel":[82],"framework":[83],"advancing":[85,228],"MEU.":[86,229],"First,":[87],"introduce":[89],"four-step":[91],"textual":[92,166],"enhancement":[93],"module":[94],"that":[95,189],"utilizes":[96],"rich":[98],"knowledge":[99],"reasoning":[101],"capabilities":[102],"Multimodal":[104],"Large":[105],"Language":[106],"Models":[107],"(MLLMs)":[108],"progressively":[110],"infer":[111],"extract":[113],"contextual":[116],"insights":[117],"from":[118],"memes.":[119],"These":[120],"enhanced":[121,163],"texts":[122],"significantly":[123],"enrich":[124],"original":[126],"meme":[127,152],"contents":[128],"provide":[130],"valuable":[131],"guidance":[132],"downstream":[134],"classification.":[135],"Next,":[136],"design":[138],"dual-stage":[140],"modal":[141],"strategy:":[143],"first":[145],"stage":[146,159],"performs":[147],"shallow":[148],"on":[150,182,203,207],"raw":[151],"image":[153],"text,":[155],"while":[156],"second":[158],"deeply":[160],"integrates":[161],"visual":[164],"features.":[167],"hierarchical":[169],"enables":[171],"model":[173],"better":[175],"capture":[176],"nuanced":[177],"cross-modal":[178],"cues.":[180],"Experiments":[181],"datasets,":[184],"MET-MEME":[185,204],"MOOD,":[187],"demonstrate":[188],"our":[190,221],"method":[191],"consistently":[192],"outperforms":[193],"state-of-the-art":[194],"baselines.":[195],"Specifically,":[196],"MemoDetector":[197],"improves":[198],"F1":[199],"scores":[200],"4.3%":[202],"3.4%":[206],"MOOD.":[208],"Further":[209],"ablation":[210],"studies":[211],"in-depth":[213],"analyses":[214],"validate":[215],"effectiveness":[217],"robustness":[219],"approach,":[222],"highlighting":[223],"its":[224],"strong":[225],"potential":[226]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}