{"id":"https://openalex.org/W4403713283","doi":"https://doi.org/10.1145/3689092.3689407","title":"Improving Multimodal Emotion Recognition by Leveraging Acoustic Adaptation and Visual Alignment","display_name":"Improving Multimodal Emotion Recognition by Leveraging Acoustic Adaptation and Visual Alignment","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4403713283","doi":"https://doi.org/10.1145/3689092.3689407"},"language":"en","primary_location":{"id":"doi:10.1145/3689092.3689407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689092.3689407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","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/A5024679838","display_name":"Zhixian Zhao","orcid":"https://orcid.org/0000-0002-1136-8279"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixian Zhao","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-1136-8279","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456775","display_name":"Haifeng Chen","orcid":"https://orcid.org/0000-0001-7164-5840"},"institutions":[{"id":"https://openalex.org/I51622183","display_name":"Shaanxi University of Science and Technology","ror":"https://ror.org/034t3zs45","country_code":"CN","type":"education","lineage":["https://openalex.org/I51622183"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Chen","raw_affiliation_strings":["Shaanxi University of Science and Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7164-5840","affiliations":[{"raw_affiliation_string":"Shaanxi University of Science and Technology, Xi'an, China","institution_ids":["https://openalex.org/I51622183"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xi Li","orcid":"https://orcid.org/0009-0009-6236-6431"},"institutions":[{"id":"https://openalex.org/I51622183","display_name":"Shaanxi University of Science and Technology","ror":"https://ror.org/034t3zs45","country_code":"CN","type":"education","lineage":["https://openalex.org/I51622183"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Li","raw_affiliation_strings":["Shaanxi University of Science and Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0009-6236-6431","affiliations":[{"raw_affiliation_string":"Shaanxi University of Science and Technology, Xi'an, China","institution_ids":["https://openalex.org/I51622183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["Peng Cheng Laboratory & Northwestern Polytechnical University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-8499","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory & Northwestern Polytechnical University, Shenzhen, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8234-0823","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.9922999739646912,"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/computer-science","display_name":"Computer science","score":0.7538434267044067},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7406785488128662},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6945570707321167},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.543476402759552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5372529029846191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3428246080875397},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11766248941421509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538434267044067},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7406785488128662},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6945570707321167},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.543476402759552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5372529029846191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3428246080875397},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11766248941421509},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689092.3689407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689092.3689407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5115915298","display_name":null,"funder_award_id":"62236006","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2807126412","https://openalex.org/W2913668833","https://openalex.org/W3036601975","https://openalex.org/W3136363192","https://openalex.org/W3203381531","https://openalex.org/W3209059054","https://openalex.org/W4220866631","https://openalex.org/W4224932952","https://openalex.org/W4366330503","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4387968043","https://openalex.org/W4388823657","https://openalex.org/W4392172801","https://openalex.org/W4392903039","https://openalex.org/W4392903074","https://openalex.org/W4392903856","https://openalex.org/W4392909581","https://openalex.org/W4392931002","https://openalex.org/W4392931772","https://openalex.org/W6851592950"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Multimodal":[0],"Emotion":[1],"Recognition":[2],"(MER)":[3],"aims":[4],"to":[5,47,129],"automatically":[6],"identify":[7],"and":[8,156],"understand":[9],"human":[10],"emotional":[11],"states":[12],"by":[13],"integrating":[14],"information":[15],"from":[16],"various":[17],"modalities.":[18],"However,":[19],"the":[20,28,40,54,60,66,84,110,113,136,143,149,168,172,189],"scarcity":[21],"of":[22,30,43,62,65,105,112,139,180,191],"annotated":[23],"multimodal":[24],"data":[25,128],"significantly":[26],"hinders":[27],"advancement":[29],"this":[31],"research":[32],"field.":[33],"This":[34,123],"paper":[35],"presents":[36],"our":[37,192],"solution":[38],"for":[39,53,90,98,164],"MER-SEMI":[41],"sub-challenge":[42],"MER":[44,55],"2024.":[45],"First,":[46],"better":[48],"adapt":[49],"acoustic":[50,114,144,151],"modality":[51],"features":[52,141],"task,":[56],"we":[57,78,116,159],"experimentally":[58],"evaluate":[59],"contributions":[61],"different":[63],"layers":[64,85],"pre-trained":[67],"speech":[68],"model":[69],"HuBERT":[70],"in":[71],"emotion":[72,91,99],"recognition.":[73],"Based":[74],"on":[75,83],"these":[76],"observations,":[77],"perform":[79],"Parameter-Efficient":[80],"Fine-Tuning":[81],"(PEFT)":[82],"identified":[86],"as":[87],"most":[88],"effective":[89],"recognition":[92,100],"tasks,":[93],"thereby":[94,134],"achieving":[95],"optimal":[96],"adaptation":[97],"with":[101],"a":[102,118,131,176],"minimal":[103],"number":[104],"learnable":[106],"parameters.":[107],"Second,":[108],"leveraging":[109],"strengths":[111],"modality,":[115],"propose":[117],"feature":[119,145,165],"alignment":[120,138],"pre-training":[121],"method.":[122],"approach":[124],"uses":[125],"large-scale":[126],"unlabeled":[127],"train":[130],"visual":[132,140,154],"encoder,":[133],"promoting":[135],"semantic":[137],"within":[142],"space.":[146],"Finally,":[147],"using":[148],"adapted":[150],"features,":[152,155,158],"aligned":[153],"lexical":[157],"employ":[160],"an":[161],"attention":[162],"mechanism":[163],"fusion.":[166],"On":[167],"MER2024-SEMI":[169],"test":[170],"set,":[171],"proposed":[173],"method":[174],"achieves":[175],"weighted":[177],"F1":[178],"score":[179],"88.90%,":[181],"ranking":[182],"fourth":[183],"among":[184],"all":[185],"participating":[186],"teams,":[187],"validating":[188],"effectiveness":[190],"approach.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}