{"id":"https://openalex.org/W4408356758","doi":"https://doi.org/10.1109/icassp49660.2025.10888951","title":"MFMamba: A Multimodal Fusion State Space Model for Depression Recognition","display_name":"MFMamba: A Multimodal Fusion State Space Model for Depression Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356758","doi":"https://doi.org/10.1109/icassp49660.2025.10888951"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888951","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/A5100434412","display_name":"Jingyi Liu","orcid":"https://orcid.org/0000-0001-6251-6051"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Liu","raw_affiliation_strings":["Capital Normal University,School of Mathematical Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital Normal University,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924785","display_name":"Yuanyuan Shang","orcid":"https://orcid.org/0000-0003-1786-6487"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Shang","raw_affiliation_strings":["Information Engineering College Capital Normal University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering College Capital Normal University,Beijing,China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595293","display_name":"Mengyuan Yang","orcid":"https://orcid.org/0009-0005-2342-0993"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyuan Yang","raw_affiliation_strings":["Information Engineering College Capital Normal University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering College Capital Normal University,Beijing,China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026412163","display_name":"Zhuhong Shao","orcid":"https://orcid.org/0000-0002-4847-282X"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuhong Shao","raw_affiliation_strings":["Information Engineering College Capital Normal University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering College Capital Normal University,Beijing,China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101715057","display_name":"Jiaxi Lu","orcid":"https://orcid.org/0000-0002-3978-4098"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Lu","raw_affiliation_strings":["Capital Normal University,School of Mathematical Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital Normal University,School of Mathematical Sciences,Beijing,China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101406961","display_name":"Tie Liu","orcid":"https://orcid.org/0000-0002-3251-0158"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie Liu","raw_affiliation_strings":["Information Engineering College Capital Normal University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering College Capital Normal University,Beijing,China","institution_ids":["https://openalex.org/I96852419"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96852419"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9115999937057495,"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":0.9115999937057495,"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":0.576640248298645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48309066891670227},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.44133368134498596},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.41218143701553345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3372254967689514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3257479965686798},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09386909008026123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.576640248298645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48309066891670227},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44133368134498596},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.41218143701553345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3372254967689514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3257479965686798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09386909008026123},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888951","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":24,"referenced_works":["https://openalex.org/W1976066595","https://openalex.org/W1988088279","https://openalex.org/W2003502731","https://openalex.org/W2023687307","https://openalex.org/W2056403322","https://openalex.org/W2084242110","https://openalex.org/W2400979883","https://openalex.org/W2592018447","https://openalex.org/W2736814566","https://openalex.org/W2977251593","https://openalex.org/W3094259155","https://openalex.org/W4206706211","https://openalex.org/W4281667552","https://openalex.org/W4313443450","https://openalex.org/W4372269226","https://openalex.org/W4378591347","https://openalex.org/W4384519140","https://openalex.org/W4390226024","https://openalex.org/W4390605218","https://openalex.org/W4399517994","https://openalex.org/W4401971359","https://openalex.org/W4403511013","https://openalex.org/W6861387779","https://openalex.org/W6869473019"],"related_works":["https://openalex.org/W2086259589","https://openalex.org/W2012885586","https://openalex.org/W59104321","https://openalex.org/W2517686979","https://openalex.org/W2049729969","https://openalex.org/W2198484008","https://openalex.org/W3157863382","https://openalex.org/W1993291419","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Depression":[0],"is":[1,17,76],"a":[2,18,69],"severe":[3],"mental":[4],"illness,":[5],"and":[6,59,78,97,114,133],"extracting":[7],"emotional":[8],"information":[9,116],"from":[10,28],"video-audio":[11,103],"signals":[12],"for":[13,55,87,102],"multimodal":[14,112],"depression":[15],"recognition":[16],"challenging":[19],"problem.":[20],"Recent":[21],"methods":[22],"use":[23],"the":[24,32,39,109],"self-attention":[25],"(SA)":[26],"mechanism":[27],"Transformers":[29],"to":[30,123],"capture":[31,108],"dynamic":[33],"relationships":[34],"between":[35],"different":[36],"modalities.":[37],"However,":[38],"quadratic":[40],"computational":[41],"complexity":[42],"of":[43],"SA":[44],"reduces":[45],"its":[46],"effectiveness":[47],"in":[48],"modeling":[49],"long":[50],"sequences,":[51],"making":[52],"it":[53],"insufficient":[54],"capturing":[56],"complex":[57],"intra-modal":[58],"inter-modal":[60],"complementarity.":[61],"To":[62,106],"address":[63],"this":[64,66],"issue,":[65],"work":[67],"proposes":[68],"Multimodal":[70],"Fusion":[71,120],"Mamba":[72,95,100,121],"(MFMamba)":[73],"framework,":[74],"which":[75],"attention-free":[77],"purely":[79],"focuses":[80],"on":[81,130],"using":[82],"state":[83],"space":[84],"models":[85],"(SSMs)":[86],"long-sequence":[88],"modeling.":[89],"Specifically,":[90],"we":[91,118],"devise":[92],"Video":[93],"Spatio-Temporal":[94],"(VSTMamba)":[96],"Audio":[98],"Temporal":[99],"(ATMamba)":[101],"feature":[104],"extraction.":[105],"fully":[107],"correlations":[110],"among":[111],"features":[113,126],"eliminate":[115],"redundancy,":[117],"introduce":[119],"(FMamba)":[122],"integrate":[124],"various":[125],"effectively.":[127],"In":[128],"experiments":[129],"AVEC":[131,134],"2013":[132],"2014":[135],"datasets,":[136],"our":[137],"method":[138],"achieved":[139],"competitive":[140],"results.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}