{"id":"https://openalex.org/W4403792436","doi":"https://doi.org/10.1145/3664647.3681648","title":"Ada2I: Enhancing Modality Balance for Multimodal Conversational Emotion Recognition","display_name":"Ada2I: Enhancing Modality Balance for Multimodal Conversational Emotion Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792436","doi":"https://doi.org/10.1145/3664647.3681648"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5033033186","display_name":"Cam-Van Thi Nguyen","orcid":"https://orcid.org/0009-0001-9675-2105"},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Cam-Van Thi Nguyen","raw_affiliation_strings":["VNU University of Engineering and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0001-9675-2105","affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108988627","display_name":"The-Son Le","orcid":null},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"The-Son Le","raw_affiliation_strings":["VNU University of Engineering and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0006-7639-129X","affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093234933","display_name":"Anh-Tuan Mai","orcid":null},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Anh-Tuan Mai","raw_affiliation_strings":["VNU University of Engineering and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0002-7211-2637","affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101555110","display_name":"Duc-Trong Le","orcid":"https://orcid.org/0000-0003-4621-8956"},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duc-Trong Le","raw_affiliation_strings":["VNU University of Engineering and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-4621-8956","affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67868205"],"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":"9330","last_page":"9339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9955999851226807,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8179010152816772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6734825968742371},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.6103708744049072},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.49619466066360474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48926517367362976},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45263588428497314},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4129328429698944},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3472515344619751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34156596660614014},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22564035654067993},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12008938193321228},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.04171633720397949}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8179010152816772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734825968742371},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.6103708744049072},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.49619466066360474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48926517367362976},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45263588428497314},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4129328429698944},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3472515344619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34156596660614014},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22564035654067993},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12008938193321228},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.04171633720397949}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":31,"referenced_works":["https://openalex.org/W2085662862","https://openalex.org/W2341528187","https://openalex.org/W2609575245","https://openalex.org/W2740550900","https://openalex.org/W2805662932","https://openalex.org/W2912083425","https://openalex.org/W2962922273","https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2982108874","https://openalex.org/W2990503944","https://openalex.org/W3035333188","https://openalex.org/W3045969489","https://openalex.org/W3092695663","https://openalex.org/W3101227480","https://openalex.org/W3101998545","https://openalex.org/W3120680448","https://openalex.org/W3166100196","https://openalex.org/W3214127792","https://openalex.org/W4221154966","https://openalex.org/W4285606617","https://openalex.org/W4287887917","https://openalex.org/W4301104990","https://openalex.org/W4312639100","https://openalex.org/W4380355289","https://openalex.org/W4386076642","https://openalex.org/W4387872955","https://openalex.org/W4387967986","https://openalex.org/W4387968266","https://openalex.org/W4387969701","https://openalex.org/W4393146934"],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2462138927","https://openalex.org/W3111427900","https://openalex.org/W4302009627","https://openalex.org/W4212781403","https://openalex.org/W4388989680","https://openalex.org/W2901011898","https://openalex.org/W4236665645","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Multimodal":[0],"Emotion":[1],"Recognition":[2],"in":[3,12,26,127],"Conversations":[4],"(ERC)":[5],"is":[6],"a":[7,41,78,89],"typical":[8],"multimodal":[9,22],"learning":[10,32,102],"task":[11],"exploiting":[13],"various":[14],"data":[15],"modalities":[16,107],"concurrently.":[17],"Prior":[18],"studies":[19],"on":[20,122],"effective":[21,92],"ERC":[23],"encounter":[24],"challenges":[25],"addressing":[27,128],"modality":[28,129],"imbalances":[29],"and":[30,57,64,72],"optimizing":[31],"across":[33],"modalities.":[34],"Dealing":[35],"with":[36,116],"these":[37],"problems,":[38],"we":[39,76],"present":[40],"novel":[42],"framework":[43],"named":[44],"Ada2I,":[45],"which":[46],"consists":[47],"of":[48,84,99,114],"two":[49],"inseparable":[50],"modules":[51],"namely":[52],"Adaptive":[53,58],"Feature":[54],"Weighting":[55,60],"(AFW)":[56],"Modality":[59],"(AMW)":[61],"for":[62],"feature-level":[63],"modality-level":[65],"balancing":[66],"respectively":[67],"via":[68],"leveraging":[69],"both":[70],"Inter-":[71],"Intra-modal":[73],"interactions.":[74],"Additionally,":[75],"introduce":[77],"refined":[79],"disparity":[80],"ratio":[81],"as":[82],"part":[83],"our":[85],"training":[86],"optimization":[87],"strategy,":[88],"simple":[90],"yet":[91],"measure":[93],"to":[94,120],"assess":[95],"the":[96,100,112],"overall":[97],"discrepancy":[98],"model's":[101],"process":[103],"when":[104],"handling":[105],"multiple":[106],"simultaneously.":[108],"Experimental":[109],"results":[110],"validate":[111],"effectiveness":[113],"Ada2I":[115],"state-of-the-art":[117],"performance":[118],"compared":[119],"baselines":[121],"three":[123],"benchmark":[124],"datasets,":[125],"particularly":[126],"imbalances.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}