{"id":"https://openalex.org/W4392904055","doi":"https://doi.org/10.1109/icassp48485.2024.10446491","title":"MDAVIF: A Multi-Domain Acoustical-Visual Information Fusion Model for Depression Recognition from Vlog Data","display_name":"MDAVIF: A Multi-Domain Acoustical-Visual Information Fusion Model for Depression Recognition from Vlog Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904055","doi":"https://doi.org/10.1109/icassp48485.2024.10446491"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5113099197","display_name":"Tianfei Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianfei Ling","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Electronic, Electrical and Communication Engineering,Beijing,China","School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Electronic, Electrical and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078266278","display_name":"Deyuan Chen","orcid":"https://orcid.org/0000-0003-4280-574X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyuan Chen","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Electronic, Electrical and Communication Engineering,Beijing,China","School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Electronic, Electrical and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103162735","display_name":"Baobin Li","orcid":"https://orcid.org/0000-0001-5828-9976"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baobin Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8115","last_page":"8119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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/T12488","display_name":"Mental Health via Writing","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9883999824523926,"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/overfitting","display_name":"Overfitting","score":0.8531019687652588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7502022981643677},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5742907524108887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5488229990005493},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5450388193130493},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5426040887832642},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5165857076644897},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4283655881881714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4097288250923157},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3459041118621826},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.340950071811676}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8531019687652588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502022981643677},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5742907524108887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5488229990005493},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5450388193130493},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5426040887832642},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5165857076644897},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4283655881881714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4097288250923157},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3459041118621826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.340950071811676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G7148651236","display_name":null,"funder_award_id":"62236006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7321923418","display_name":null,"funder_award_id":"E2E41902X2","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2023687307","https://openalex.org/W2056403322","https://openalex.org/W2313162948","https://openalex.org/W2946396904","https://openalex.org/W2948133932","https://openalex.org/W2964010806","https://openalex.org/W2966867529","https://openalex.org/W2982183006","https://openalex.org/W2995040299","https://openalex.org/W4206177455","https://openalex.org/W4224924082","https://openalex.org/W4225411558","https://openalex.org/W4283815599","https://openalex.org/W4310333988","https://openalex.org/W4321353437","https://openalex.org/W4324387123","https://openalex.org/W4360999323","https://openalex.org/W4361251501"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2368605798","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483"],"abstract_inverted_index":{"With":[0],"the":[1,43,118,122,126,131,138],"explosive":[2],"popularity":[3],"of":[4,128,133],"social":[5],"media,":[6],"more":[7,9],"and":[8,40,63,94,96,115,130],"people,":[10],"including":[11],"those":[12],"with":[13,58,109,125],"depressive":[14,88],"symptoms,":[15],"are":[16],"starting":[17],"to":[18,53,66,86,104,112],"express":[19],"their":[20],"emotions":[21],"online":[22],"through":[23],"vlogs":[24],"recently,":[25],"which":[26],"makes":[27],"it":[28],"important":[29],"for":[30],"video-based":[31],"depression":[32,59],"recognition.":[33],"As":[34],"video":[35],"data":[36,62],"contains":[37],"rich":[38],"acoustical":[39],"visual":[41],"information,":[42],"main":[44],"challenges":[45],"faced":[46],"by":[47],"existing":[48],"methods":[49],"include":[50],"(1)":[51],"how":[52,65],"accurately":[54],"mine":[55],"features":[56,70,90],"associated":[57],"in":[60],"massive":[61],"(2)":[64],"effectively":[67],"fuse":[68],"various":[69],"from":[71,91],"different":[72],"modalities.":[73],"In":[74],"this":[75],"paper,":[76],"a":[77],"multi-domain":[78],"acoustical-visual":[79],"information":[80,114],"fusion":[81],"network":[82],"(MDAVIF)":[83],"is":[84,102],"designed":[85],"extract":[87],"spatio-temporal":[89],"image":[92],"sequences":[93],"audios,":[95],"an":[97],"adaptive":[98],"feature":[99],"interaction":[100],"module":[101],"proposed":[103,119],"mix":[105],"these":[106],"features.":[107],"Combined":[108],"two":[110],"autoencoders":[111],"retain":[113],"prevent":[116],"overfitting,":[117],"method":[120],"obtains":[121],"state-of-the-art":[123],"result":[124],"precision":[127],"74.25%":[129],"F1-Score":[132],"75.25%":[134],"when":[135],"evaluated":[136],"on":[137],"D-vlog":[139],"dataset.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}