{"id":"https://openalex.org/W4415536723","doi":"https://doi.org/10.1145/3746027.3762062","title":"DepFormer: A Unified Framework with Bimodal Collaborative Transformer for Depression Detection","display_name":"DepFormer: A Unified Framework with Bimodal Collaborative Transformer for Depression Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536723","doi":"https://doi.org/10.1145/3746027.3762062"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762062","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5029413019","display_name":"Fangyuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyuan Liu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-6498-6655","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090369859","display_name":"Sirui Zhao","orcid":"https://orcid.org/0000-0001-8103-0321"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sirui Zhao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8103-0321","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110966296","display_name":"Kang Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Yin","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-1421-0121","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025292786","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4246-5386","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4835-4102","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25421304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13930","last_page":"13936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9883999824523926,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied 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/feature-learning","display_name":"Feature learning","score":0.6209999918937683},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4595000147819519},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.39750000834465027},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.35499998927116394},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3285999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758000254631042},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6209999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4595000147819519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43950000405311584},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35499998927116394},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C134362201","wikidata":"https://www.wikidata.org/wiki/Q317309","display_name":"Mental health","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C96199812","wikidata":"https://www.wikidata.org/wiki/Q2145290","display_name":"Mental representation","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762062","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3056434094","display_name":null,"funder_award_id":"6240624,61727809,62222213,U22B2059","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2003502731","https://openalex.org/W2018988971","https://openalex.org/W2095540482","https://openalex.org/W2182998784","https://openalex.org/W2346454595","https://openalex.org/W2530305026","https://openalex.org/W2530421149","https://openalex.org/W2805970382","https://openalex.org/W2889847952","https://openalex.org/W2957148965","https://openalex.org/W2960672642","https://openalex.org/W2970963824","https://openalex.org/W3094259155","https://openalex.org/W4225788814","https://openalex.org/W4283815599","https://openalex.org/W4310333988","https://openalex.org/W4313527090","https://openalex.org/W4360999323","https://openalex.org/W4388833473","https://openalex.org/W4389195633","https://openalex.org/W4390605218","https://openalex.org/W4392172671","https://openalex.org/W4392377367","https://openalex.org/W4397031610","https://openalex.org/W4402979565","https://openalex.org/W4403792402"],"related_works":[],"abstract_inverted_index":{"Depression":[0],"is":[1,17],"an":[2,115],"increasingly":[3],"prevalent":[4],"mental":[5],"health":[6],"issue":[7],"worldwide,":[8],"especially":[9],"among":[10],"the":[11,96,108,140],"elderly,":[12],"where":[13],"effective":[14],"early":[15],"detection":[16],"crucial":[18],"for":[19,34,70],"timely":[20],"intervention.":[21],"While":[22],"recent":[23],"multimodal":[24],"approaches":[25],"demonstrate":[26],"promise":[27],"in":[28,139],"leveraging":[29],"visual":[30],"and":[31,50,74,102,118,126],"auditory":[32],"cues":[33],"automatic":[35],"depression":[36,105],"recognition,":[37],"existing":[38],"methods":[39],"often":[40],"fail":[41],"to":[42,79,122],"extract":[43],"fine-grained,":[44],"depression-specific":[45],"patterns":[46],"from":[47],"pre-extracted":[48],"features":[49],"underutilize":[51],"cross-modal":[52,71],"interactions.":[53],"To":[54],"address":[55],"these":[56],"challenges,":[57],"we":[58],"propose":[59],"DepFormer,":[60],"a":[61,66,75,119],"unified":[62],"framework":[63],"that":[64],"incorporates":[65],"Bimodal":[67],"Collaborative":[68],"Transformer(BCT)":[69],"representation":[72,93],"learning":[73,94,128],"personalized":[76,99],"fusion":[77],"module":[78],"enhance":[80],"individual-specific":[81],"modeling.":[82],"The":[83],"architecture":[84],"comprises:":[85],"(1)":[86],"unimodal":[87],"feature":[88,100],"extraction,":[89],"(2)":[90],"bimodal":[91],"collaborative":[92],"via":[95],"BCT,":[97],"(3)":[98],"fusion,":[101],"(4)":[103],"final":[104],"classification.":[106],"Critically,":[107],"BCT":[109],"employs":[110],"symmetric":[111],"bidirectional":[112],"branches":[113],"comprising":[114],"Audio-to-Video":[116],"Transformer":[117,121],"Video-to-Audio":[120],"enable":[123],"mutual":[124],"enhancement":[125],"complementary":[127],"across":[129],"modalities.":[130],"Extensive":[131],"experiments":[132],"validate":[133],"DepFormer's":[134],"effectiveness,":[135],"securing":[136],"first":[137],"place":[138],"MPDD":[141],"Challenge":[142],"2025":[143],"(Elderly":[144],"Track),":[145],"underscoring":[146],"its":[147],"strong":[148],"practical":[149],"potential.":[150]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}