{"id":"https://openalex.org/W4417073329","doi":"https://doi.org/10.1145/3743093.3771008","title":"MCIHN: A Hybrid Network Model Based on Multi-path Cross-modal Interaction for Multimodal Emotion Recognition","display_name":"MCIHN: A Hybrid Network Model Based on Multi-path Cross-modal Interaction for Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073329","doi":"https://doi.org/10.1145/3743093.3771008"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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/A5028025426","display_name":"Haoyang Zhang","orcid":"https://orcid.org/0009-0009-1581-3147"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Zhang","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0009-1581-3147","affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354561","display_name":"Yang Zhou","orcid":"https://orcid.org/0000-0001-6094-073X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Yang","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0001-6094-073X","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ke Sun","orcid":"https://orcid.org/0009-0005-8737-0411"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ke Sun","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0005-8737-0411","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076044143","display_name":"Yucai Pang","orcid":"https://orcid.org/0000-0002-9072-4605"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucai Pang","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-9072-4605","affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007760774","display_name":"Guoliang Xu","orcid":"https://orcid.org/0000-0002-9923-4725"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Xu","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-9923-4725","affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9943000078201294,"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":0.9943000078201294,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.001500000013038516,"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/T10057","display_name":"Face and Expression Recognition","score":0.0005000000237487257,"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":0.8324000239372253},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5968999862670898},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5386999845504761},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.517300009727478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3781000077724457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3725000023841858},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3628000020980835},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.35749998688697815}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8324000239372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021999716758728},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3781000077724457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3125},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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":26,"referenced_works":["https://openalex.org/W1490382748","https://openalex.org/W2095176743","https://openalex.org/W2556418146","https://openalex.org/W2625297138","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964346351","https://openalex.org/W2966518489","https://openalex.org/W3034266838","https://openalex.org/W3034849760","https://openalex.org/W3034897750","https://openalex.org/W3093051361","https://openalex.org/W3095379519","https://openalex.org/W3128412859","https://openalex.org/W3168391820","https://openalex.org/W3188766356","https://openalex.org/W4210611093","https://openalex.org/W4285184319","https://openalex.org/W4312773554","https://openalex.org/W4321439011","https://openalex.org/W4372260395","https://openalex.org/W4376455521","https://openalex.org/W4386826611","https://openalex.org/W4390372502","https://openalex.org/W4391302483","https://openalex.org/W4392903310"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,120],"emotion":[1,11,61,77,130],"recognition":[2,12],"is":[3,45],"crucial":[4],"for":[5,54,128],"future":[6],"human-computer":[7],"interaction.":[8],"However,":[9],"accurate":[10],"still":[13],"faces":[14],"significant":[15],"challenges":[16],"due":[17],"to":[18,70,99],"differences":[19],"between":[20,103,109,117],"different":[21,87,118],"modalities":[22,88],"and":[23,63,112,139],"the":[24,65,76,80,84,101,106,114,123],"difficulty":[25],"of":[26,86],"characterizing":[27],"unimodal":[28],"emotional":[29,107],"information.":[30],"To":[31],"solve":[32],"these":[33],"problems,":[34],"a":[35,68,92],"hybrid":[36],"network":[37],"model":[38,97],"based":[39],"on":[40,135],"multipath":[41],"cross-modal":[42],"interaction":[43,115],"(MCIHN)":[44],"proposed.":[46],"First,":[47],"adversarial":[48],"autoencoders":[49],"(AAE)":[50],"are":[51,89],"constructed":[52],"separately":[53],"each":[55],"modality.":[56],"The":[57],"AAE":[58,85],"learns":[59],"discriminative":[60,73],"features":[62,66,116],"reconstructs":[64],"through":[67],"decoder":[69],"obtain":[71],"more":[72],"information":[74],"about":[75],"classes.":[78],"Then,":[79],"latent":[81],"codes":[82],"from":[83],"fed":[90],"into":[91],"predefined":[93],"Cross-modal":[94],"Gate":[95],"Mechanism":[96],"(CGMM)":[98],"reduce":[100],"discrepancy":[102],"modalities,":[104,111],"establish":[105],"relationship":[108],"interacting":[110],"generate":[113],"modalities.":[119],"fusion":[121],"using":[122],"Feature":[124],"Fusion":[125],"module":[126],"(FFM)":[127],"better":[129],"recognition.":[131],"Experiments":[132],"were":[133],"conducted":[134],"publicly":[136],"available":[137],"SIMS":[138],"MOSI":[140],"datasets,":[141],"demonstrating":[142],"that":[143],"MCIHN":[144],"achieves":[145],"superior":[146],"performance.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-06T00:00:00"}