{"id":"https://openalex.org/W4408353953","doi":"https://doi.org/10.1109/icassp49660.2025.10888673","title":"A Novel Audio-Visual Multimodal Semi-Supervised Model Based on Graph Neural Networks for Depression Detection","display_name":"A Novel Audio-Visual Multimodal Semi-Supervised Model Based on Graph Neural Networks for Depression Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353953","doi":"https://doi.org/10.1109/icassp49660.2025.10888673"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888673","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/A5101897220","display_name":"Yaqin Li","orcid":"https://orcid.org/0000-0003-2363-4834"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqin Li","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109669344","display_name":"Chenjian Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenjian Sun","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018401644","display_name":"Yihong Dong","orcid":"https://orcid.org/0000-0001-6228-4019"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Dong","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science,China","institution_ids":["https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I109935558"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"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":0.8863000273704529,"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":0.8863000273704529,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8222000002861023,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7631193399429321},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6563485860824585},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5304885506629944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4982411861419678},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4700290858745575},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34421372413635254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3440559506416321},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3318767845630646},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15895342826843262},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14589712023735046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631193399429321},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6563485860824585},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5304885506629944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4982411861419678},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4700290858745575},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34421372413635254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3440559506416321},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3318767845630646},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15895342826843262},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14589712023735046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888673","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":33,"referenced_works":["https://openalex.org/W2023687307","https://openalex.org/W2064675550","https://openalex.org/W2157735101","https://openalex.org/W2191779130","https://openalex.org/W2346454595","https://openalex.org/W2607644382","https://openalex.org/W2755822369","https://openalex.org/W2916233667","https://openalex.org/W3039075121","https://openalex.org/W3094378471","https://openalex.org/W3169831618","https://openalex.org/W3203310594","https://openalex.org/W3216416558","https://openalex.org/W4283815599","https://openalex.org/W4302275554","https://openalex.org/W4386222461","https://openalex.org/W4386397728","https://openalex.org/W4386484691","https://openalex.org/W4386524186","https://openalex.org/W4388359375","https://openalex.org/W4388906419","https://openalex.org/W4389048029","https://openalex.org/W4389195633","https://openalex.org/W4390226024","https://openalex.org/W4390746040","https://openalex.org/W4392903053","https://openalex.org/W4392909502","https://openalex.org/W6691669583","https://openalex.org/W6713582272","https://openalex.org/W6725923168","https://openalex.org/W6726873649","https://openalex.org/W6779518175","https://openalex.org/W6838594430"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"There":[0],"is":[1,27,44],"a":[2,35,130],"significant":[3],"correlation":[4],"between":[5,114],"depression,":[6],"verbal":[7],"behavior,":[8],"and":[9,16,46,87,93,122,142],"facial":[10,17,88],"expressions.":[11],"By":[12],"analyzing":[13],"patients\u2019":[14],"audio":[15,85],"visuals,":[18],"depression":[19,68,150],"assessments":[20],"can":[21],"be":[22],"conducted.":[23],"However,":[24],"existing":[25],"work":[26],"predominantly":[28],"based":[29,71],"on":[30,72,148],"single":[31],"modalities.":[32],"Additionally,":[33],"acquiring":[34],"sufficient":[36],"amount":[37],"of":[38,57,91,116],"labeled":[39,60],"data":[40,52,141],"in":[41],"clinical":[42],"settings":[43],"challenging":[45],"costly.":[47],"To":[48],"leverage":[49],"multimodal":[50,66],"audio-visual":[51],"while":[53],"addressing":[54],"the":[55,145],"issue":[56],"lacking":[58],"trainable":[59],"data,":[61],"we":[62],"propose":[63],"an":[64],"audiovisual":[65],"semi-supervised":[67],"detection":[69],"model":[70,78,155],"Graph":[73],"Neural":[74],"Networks":[75],"(AVS-GNN).":[76],"This":[77],"first":[79],"extracts":[80],"dual-modality":[81],"temporal":[82],"information":[83,113],"from":[84],"features":[86,90],"visual":[89],"patients":[92],"obtains":[94],"modality-specific":[95],"high-level":[96],"embedding":[97],"representations":[98],"through":[99],"graph":[100],"representation":[101],"learning.":[102],"Subsequently,":[103],"it":[104],"utilizes":[105],"graph-based":[106],"contrastive":[107],"unsupervised":[108],"learning":[109],"to":[110,123,135,139],"capture":[111],"consistency":[112],"pairs":[115],"unlabeled":[117,140],"samples":[118],"across":[119,159],"different":[120],"modalities":[121],"facilitate":[124],"cross-modal":[125],"interactions.":[126],"We":[127],"specifically":[128],"designed":[129],"hybrid":[131],"weighted":[132],"pseudo-labeling":[133],"strategy":[134],"assign":[136],"high-confidence":[137],"pseudo-labels":[138],"further":[143],"retraining":[144],"model.":[146],"Experiments":[147],"two":[149],"datasets":[151],"show":[152],"that":[153],"this":[154],"outperforms":[156],"baseline":[157],"methods":[158],"all":[160],"evaluation":[161],"metrics.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}