{"id":"https://openalex.org/W4415709721","doi":"https://doi.org/10.1109/icme59968.2025.11210194","title":"TriModal Enhanced Fusion Network: Advancing Multimodal Representation and Fusion for Enhanced Multimodal Intent Recognition","display_name":"TriModal Enhanced Fusion Network: Advancing Multimodal Representation and Fusion for Enhanced Multimodal Intent Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709721","doi":"https://doi.org/10.1109/icme59968.2025.11210194"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210194","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":"conference-paper","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/A5100408478","display_name":"Yixuan Wang","orcid":"https://orcid.org/0000-0003-3079-5572"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Wang","raw_affiliation_strings":["Northeast Normal University,School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,School of Information Science and Technology","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058538859","display_name":"Kehan Wang","orcid":"https://orcid.org/0000-0002-7762-8491"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehan Wang","raw_affiliation_strings":["Northeast Normal University,School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,School of Information Science and Technology","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101408516","display_name":"Huayu Zhang","orcid":"https://orcid.org/0009-0004-0956-9073"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huayu Zhang","raw_affiliation_strings":["Northeast Normal University,School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,School of Information Science and Technology","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638065","display_name":"Ming Fang","orcid":"https://orcid.org/0000-0003-4007-7777"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Fang","raw_affiliation_strings":["Northeast Normal University,School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,School of Information Science and Technology","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106941407","display_name":"Shuhua Liu","orcid":"https://orcid.org/0009-0008-5577-6515"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhua Liu","raw_affiliation_strings":["Northeast Normal University,School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,School of Information Science and Technology","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184983240"],"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":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2669000029563904,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2669000029563904,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.08799999952316284,"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/T11431","display_name":"Action Observation and Synchronization","score":0.059300001710653305,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6053000092506409},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5909000039100647},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4828999936580658},{"id":"https://openalex.org/keywords/information-fusion","display_name":"Information fusion","score":0.46939998865127563},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4560999870300293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4117000102996826},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.400299996137619},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7294999957084656},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6053000092506409},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.34540000557899475},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2778971668","wikidata":"https://www.wikidata.org/wiki/Q5510284","display_name":"Fusion rules","level":4,"score":0.3181000053882599},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210194","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2964051877","https://openalex.org/W3034247804","https://openalex.org/W3034266838","https://openalex.org/W3093051361","https://openalex.org/W3146366485","https://openalex.org/W3184679245","https://openalex.org/W3206201541","https://openalex.org/W4225307240","https://openalex.org/W4226275807","https://openalex.org/W4285149123","https://openalex.org/W4296841290","https://openalex.org/W4304080418","https://openalex.org/W4311461310","https://openalex.org/W4312905520","https://openalex.org/W4321793515","https://openalex.org/W4361199562","https://openalex.org/W4376226279","https://openalex.org/W4376455521","https://openalex.org/W4379514984","https://openalex.org/W4379806336","https://openalex.org/W4385267466","https://openalex.org/W4389833432","https://openalex.org/W4393151871","https://openalex.org/W4393156689"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"intent":[1,40],"recognition":[2],"integrates":[3],"language,":[4],"expression,":[5],"speech,":[6],"and":[7,19,52,68,93,104,107,121],"action":[8],"to":[9,37,127],"accurately":[10],"determine":[11],"intent.":[12],"However,":[13],"the":[14,20,31,59,75,79,115,118,122,129],"completeness":[15],"of":[16,45,65],"feature":[17],"information":[18,61,73],"deep":[21],"dependencies":[22,109],"between":[23],"different":[24,66],"modalities":[25],"remain":[26],"challenges.":[27],"This":[28],"paper":[29],"proposes":[30],"Tri-Modal":[32],"Enhanced":[33],"Fusion":[34,50,89],"Network":[35],"(TriMod-EFN)":[36],"enhance":[38],"multimodal":[39],"recognition.":[41],"It":[42],"is":[43],"composed":[44],"Deformable":[46,55],"Global-Local":[47,56],"Transformer,":[48],"Calibrated":[49,88],"Module":[51,90],"Dual-Classifier.":[53],"The":[54,87],"Transformer":[57],"realizes":[58],"intra-modal":[60],"interaction":[62],"for":[63],"sequences":[64],"lengths,":[67],"focuses":[69],"on":[70,134],"local":[71],"detail":[72],"within":[74],"modality":[76,101,105],"while":[77],"acquiring":[78,83],"global":[80],"information,":[81],"thus":[82],"richer":[84],"semantic":[85,95,98],"information.":[86],"performs":[91],"cross-scale":[92],"cross-modality":[94],"calibration,":[96],"reducing":[97],"loss":[99],"during":[100],"dimensionality":[102],"reduction":[103],"interaction,":[106],"learns":[108],"with":[110],"adaptive":[111],"fusion":[112],"weights.":[113],"In":[114],"Dual-Classifier":[116],"structure,":[117],"primary":[119],"classifier":[120,124],"auxiliary":[123],"are":[125],"co-trained":[126],"reduce":[128],"prediction":[130],"confusion.":[131],"Experimental":[132],"results":[133],"two":[135],"datasets":[136],"show":[137],"that":[138],"TriMod-EFN":[139],"outperforms":[140],"other":[141],"advanced":[142],"models":[143],"in":[144],"multiple":[145],"evaluation":[146],"metrics.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}