{"id":"https://openalex.org/W4408351850","doi":"https://doi.org/10.1109/icassp49660.2025.10889576","title":"GateM 2 Former: Gated Feature Selection and Expert Modeling in Multimodal Emotion Recognition","display_name":"GateM 2 Former: Gated Feature Selection and Expert Modeling in Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351850","doi":"https://doi.org/10.1109/icassp49660.2025.10889576"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100552019","display_name":"Weixiang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixiang Xu","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104298357","display_name":"Zhongren Dong","orcid":"https://orcid.org/0000-0001-8074-1746"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongren Dong","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044489032","display_name":"Runming Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runming Wang","raw_affiliation_strings":["Hunan Normal University,School of Information Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Normal University,School of Information Science and Engineering,China","institution_ids":["https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049684805","display_name":"Xinzhou Xu","orcid":"https://orcid.org/0000-0002-4017-5919"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Xinzhou Xu","raw_affiliation_strings":["Graz University of Technology,Signal Processing and Speech Communication Laboratory,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graz University of Technology,Signal Processing and Speech Communication Laboratory,Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036056631","display_name":"Zixing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0207,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96783465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9520999789237976,"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":0.9520999789237976,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9359999895095825,"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/computer-science","display_name":"Computer science","score":0.6332481503486633},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6232478618621826},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.59519362449646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.538079023361206},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49106669425964355},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4856208860874176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4825415015220642},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43006086349487305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40701574087142944},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3481268584728241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6332481503486633},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6232478618621826},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.59519362449646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.538079023361206},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49106669425964355},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4856208860874176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4825415015220642},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43006086349487305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40701574087142944},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3481268584728241},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/W2146334809","https://openalex.org/W2892550322","https://openalex.org/W2939614220","https://openalex.org/W2963686995","https://openalex.org/W2964276171","https://openalex.org/W3016138882","https://openalex.org/W3084283759","https://openalex.org/W3097777922","https://openalex.org/W3160183718","https://openalex.org/W3208314443","https://openalex.org/W3209984917","https://openalex.org/W4221154966","https://openalex.org/W4224917001","https://openalex.org/W4281492411","https://openalex.org/W4313887688","https://openalex.org/W4372260431","https://openalex.org/W4372266717","https://openalex.org/W4372340824","https://openalex.org/W4379356527","https://openalex.org/W4385864193","https://openalex.org/W4389833432","https://openalex.org/W4392903113","https://openalex.org/W4392903758","https://openalex.org/W4394862910","https://openalex.org/W6766673545","https://openalex.org/W6860710830"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W2380784125","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W4386564352","https://openalex.org/W2952668426","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W4407198734"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"multimodal":[3,154],"emotion":[4],"recognition":[5],"(MER)":[6],"has":[7],"gained":[8],"significant":[9],"attention":[10],"due":[11],"to":[12,15,26,40,76,115,158],"its":[13],"potential":[14,104],"integrate":[16],"information":[17,33],"from":[18,45,82],"diverse":[19],"signals.":[20],"However,":[21],"existing":[22],"methods":[23],"often":[24],"struggle":[25],"effectively":[27],"capture":[28],"complex":[29],"interactions":[30,105],"and":[31,36,38,63,87,99,103,143,165],"contextual":[32],"both":[34],"inter-":[35],"intra-modalities,":[37],"even":[39],"extract":[41],"the":[42,78,93,100,118,130,133,141,160],"salient":[43],"representations":[44,81],"pre-trained":[46,83],"models.":[47,84],"To":[48,128],"address":[49],"these":[50],"issues,":[51],"we":[52,109,136],"propose":[53],"a":[54,111,152],"novel":[55],"model,":[56,135],"gated":[57],"Mixture":[58],"of":[59,65,96,132],"Multimodal":[60],"Experts":[61,66],"(MoME)":[62],"Mixtral":[64],"(MixMoE)":[67],"models,":[68],"namely":[69],"GateM2Former.":[70],"The":[71,85,146],"gate":[72],"mechanism":[73],"is":[74,156],"used":[75],"select":[77],"most":[79],"relevant":[80],"MoME":[86],"MixMoE":[88],"expert":[89],"modules":[90],"respectively":[91],"learn":[92],"individual":[94],"characteristics":[95],"each":[97],"modality":[98],"intrinsic":[101],"alignment":[102],"between":[106],"modalities.":[107],"Besides,":[108],"design":[110],"hierarchical":[112],"merge":[113],"structure":[114],"better":[116],"suit":[117],"long":[119],"sequence":[120],"scenario":[121],"(i.":[122],"e.,":[123],"speech":[124],"in":[125],"our":[126],"case).":[127],"verify":[129],"effectiveness":[131],"introduced":[134],"conducted":[137],"extensive":[138],"experiments":[139],"on":[140,163],"IEMOCAP":[142,164],"MELD":[144,166],"datasets.":[145],"results":[147,162],"show":[148],"that":[149],"GateM2Former,":[150],"with":[151,168],"universal":[153],"structure,":[155],"able":[157],"achieve":[159],"best":[161],"compared":[167],"other":[169],"latest":[170],"approaches.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}