{"id":"https://openalex.org/W4415432897","doi":"https://doi.org/10.21437/interspeech.2025-2060","title":"Multi-Modal Multi-Task Affective States Recognition Based on Label Encoder Fusion","display_name":"Multi-Modal Multi-Task Affective States Recognition Based on Label Encoder Fusion","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432897","doi":"https://doi.org/10.21437/interspeech.2025-2060"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2060","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.library.uu.nl/handle/1874/483074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050029665","display_name":"Maxim Markitantov","orcid":"https://orcid.org/0000-0001-7987-1025"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Maxim Markitantov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465844","display_name":"Elena Ryumina","orcid":"https://orcid.org/0000-0002-4135-6949"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Ryumina","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050585145","display_name":"Heysem Kaya","orcid":"https://orcid.org/0000-0001-7947-5508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heysem Kaya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050029665"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8236,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8849082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3010","last_page":"3014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14512","display_name":"Technology and Human Factors in Education and Health","score":0.7415000200271606,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T14512","display_name":"Technology and Human Factors in Education and Health","score":0.7415000200271606,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11373","display_name":"Sleep and Work-Related Fatigue","score":0.7275999784469604,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7038999795913696,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4465999901294708},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3384999930858612},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.32820001244544983},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32739999890327454},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2906999886035919},{"id":"https://openalex.org/keywords/automatic-target-recognition","display_name":"Automatic target recognition","score":0.27810001373291016}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.608299970626831},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34360000491142273},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2060","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.library.uu.nl:1874/483074","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/483074","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Part of book"}],"best_oa_location":{"id":"pmh:oai:dspace.library.uu.nl:1874/483074","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/483074","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Part of book"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,103],"multi-modal":[4,41],"approaches,":[5],"recognizing":[6],"the":[7,28,77,91,126,136],"full":[8],"range":[9],"of":[10,31,115],"human":[11],"affective":[12,32,105],"states,":[13],"including":[14],"emotions":[15],"and":[16,27,44,51,63,67,94,117,121,131],"sentiments,":[17],"remains":[18],"challenging":[19],"due":[20],"to":[21,80],"complex":[22],"interactions":[23],"between":[24],"different":[25],"modalities":[26],"hierarchical":[29],"nature":[30],"states.":[33],"This":[34],"work":[35],"presents":[36],"a":[37,56,111],"novel":[38],"approach":[39,99],"for":[40,119,135],"multi-task":[42],"emotion":[43,66,120],"sentiment":[45,68,122],"recognition":[46],"that":[47],"integrates":[48],"audio,":[49],"video,":[50],"text":[52],"data.":[53],"We":[54,85],"introduce":[55],"Label":[57],"Encoder":[58],"Fusion":[59],"Strategy,":[60],"which":[61,70],"produces":[62],"processes":[64],"uni-modal":[65],"predictions,":[69],"are":[71],"used":[72],"alongside":[73],"modality-specific":[74],"features":[75],"during":[76],"fusion":[78],"process":[79],"provide":[81],"additional":[82],"contextual":[83],"information.":[84],"conduct":[86],"elaborate":[87],"multi-corpus":[88],"experiments":[89],"on":[90],"RAMAS,":[92],"MELD,":[93,108],"CMU-MOSEI":[95],"corpora.":[96],"The":[97],"proposed":[98],"achieves":[100],"state-of-the-art":[101],"performance":[102],"both":[104],"tasks.":[106,138],"On":[107,124],"we":[109],"achieve":[110],"macro":[112],"F1":[113],"(MF)":[114],"40.9%":[116],"67.02%":[118],"recognition.":[123],"CMU-MOSEI,":[125],"mean":[127],"MF":[128,132],"is":[129,133],"62.30%":[130],"62.00%":[134],"same":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-24T00:00:00"}