{"id":"https://openalex.org/W4408352521","doi":"https://doi.org/10.1109/icassp49660.2025.10889948","title":"Mitigating Category Imbalance: Fosafer System for the Multimodal Emotion and Intent Joint Understanding Challenge","display_name":"Mitigating Category Imbalance: Fosafer System for the Multimodal Emotion and Intent Joint Understanding Challenge","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352521","doi":"https://doi.org/10.1109/icassp49660.2025.10889948"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889948","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.11362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100688967","display_name":"Honghong Wang","orcid":"https://orcid.org/0000-0002-3484-8929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Honghong Wang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542883","display_name":"Yankai Wang","orcid":"https://orcid.org/0009-0000-9240-5459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yankai Wang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064727229","display_name":"Dejun Zhang","orcid":"https://orcid.org/0000-0001-9129-534X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dejun Zhang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727973","display_name":"Jing Deng","orcid":"https://orcid.org/0000-0003-4032-0482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Deng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056442083","display_name":"Rong Zheng","orcid":"https://orcid.org/0000-0003-4070-075X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Zheng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd.,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03842232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7818999886512756,"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":0.7818999886512756,"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/T12031","display_name":"Speech and dialogue systems","score":0.6974999904632568,"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/T10028","display_name":"Topic Modeling","score":0.6550999879837036,"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/joint","display_name":"Joint (building)","score":0.6733391284942627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6252834796905518},{"id":"https://openalex.org/keywords/joint-attention","display_name":"Joint attention","score":0.4233975112438202},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40418151021003723},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.38979533314704895},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.264617919921875},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.128363698720932},{"id":"https://openalex.org/keywords/developmental-psychology","display_name":"Developmental psychology","score":0.10244190692901611}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6733391284942627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6252834796905518},{"id":"https://openalex.org/C137878579","wikidata":"https://www.wikidata.org/wiki/Q9636076","display_name":"Joint attention","level":3,"score":0.4233975112438202},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40418151021003723},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38979533314704895},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.264617919921875},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.128363698720932},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.10244190692901611},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889948","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"},{"id":"pmh:oai:arXiv.org:2508.11362","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.11362","pdf_url":"https://arxiv.org/pdf/2508.11362","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.11362","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.11362","pdf_url":"https://arxiv.org/pdf/2508.11362","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4385571916","https://openalex.org/W4403713281","https://openalex.org/W6790906881","https://openalex.org/W6839936984","https://openalex.org/W6860853044","https://openalex.org/W6870329127"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2464921558","https://openalex.org/W2331316773","https://openalex.org/W4234497699","https://openalex.org/W314221487","https://openalex.org/W2501000359","https://openalex.org/W2137049550","https://openalex.org/W3014989972"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Fosafer\u2019s":[3],"approach":[4,116],"to":[5,66,83,91,119],"the":[6,11,33,59,68,88,93,110,121,127,134,138],"Track":[7,139],"2":[8,140],"Mandarin":[9,141],"in":[10,30,137],"Multimodal":[12],"Emotion":[13],"and":[14,28,53,75,95],"Intent":[15],"Joint":[16],"Understanding":[17],"(MEIJU)":[18],"challenge,":[19],"which":[20,132],"focuses":[21],"on":[22],"achieving":[23],"joint":[24,97],"recognition":[25],"of":[26,35,46,70,129],"emotion":[27,94],"intent":[29,96],"Mandarin,":[31],"despite":[32],"issue":[34],"category":[36],"imbalance.":[37],"To":[38,99],"alleviate":[39],"this":[40],"issue,":[41],"we":[42,57,86,103],"use":[43],"a":[44,105,113],"variety":[45],"data":[47],"augmentation":[48],"techniques":[49],"across":[50],"text,":[51],"video,":[52],"audio":[54],"modalities.":[55],"Additionally,":[56],"introduce":[58,104],"Sample-Weighted":[60],"Focal":[61],"Contrastive":[62],"(SWFC)":[63],"loss,":[64],"designed":[65],"address":[67],"challenges":[69],"recognizing":[71],"minority":[72],"class":[73],"samples":[74],"those":[76],"that":[77],"are":[78],"semantically":[79],"similar":[80],"but":[81],"difficult":[82],"distinguish.":[84],"Moreover,":[85],"fine-tune":[87],"Hubert":[89],"model":[90],"adapt":[92],"recognition.":[98],"mitigate":[100],"modal":[101,106],"competition,":[102],"dropout":[107],"strategy.":[108],"For":[109],"final":[111],"predictions,":[112],"plurality":[114],"voting":[115],"is":[117],"used":[118],"determine":[120],"results.":[122],"The":[123],"experimental":[124],"results":[125],"demonstrate":[126],"effectiveness":[128],"our":[130],"method,":[131],"achieves":[133],"second-best":[135],"performance":[136],"challenge.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}