{"id":"https://openalex.org/W4416874103","doi":"https://doi.org/10.1109/ispa66905.2025.11259458","title":"Cross-Modal Fusion Mamba for Multimodal Depression Detection","display_name":"Cross-Modal Fusion Mamba for Multimodal Depression Detection","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4416874103","doi":"https://doi.org/10.1109/ispa66905.2025.11259458"},"language":null,"primary_location":{"id":"doi:10.1109/ispa66905.2025.11259458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa66905.2025.11259458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Symposium on Image and Signal Processing and Analysis (ISPA)","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/A5120208072","display_name":"Bowen Zhou","orcid":"https://orcid.org/0009-0009-0368-6128"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bowen Zhou","raw_affiliation_strings":["Otto von Guericke University Magdeburg,Neuro-Information Technology Group,Magdeburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto von Guericke University Magdeburg,Neuro-Information Technology Group,Magdeburg,Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039636002","display_name":"Marc-Andr\u00e9 Fiedler","orcid":"https://orcid.org/0000-0002-5606-4033"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc-Andr\u00e9 Fiedler","raw_affiliation_strings":["Otto von Guericke University Magdeburg,Neuro-Information Technology Group,Magdeburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto von Guericke University Magdeburg,Neuro-Information Technology Group,Magdeburg,Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033366160","display_name":"Ayoub Al-Hamadi","orcid":"https://orcid.org/0000-0002-3632-2402"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ayoub Al-Hamadi","raw_affiliation_strings":["Otto von Guericke University Magdeburg,Neuro-Information Technology Group,Magdeburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Otto von Guericke University Magdeburg,Neuro-Information Technology Group,Magdeburg,Germany","institution_ids":["https://openalex.org/I95793202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95793202"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.948199987411499,"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":0.948199987411499,"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/T11309","display_name":"Music and Audio Processing","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.005400000140070915,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/audio-visual","display_name":"Audio visual","score":0.5514000058174133},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5097000002861023},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48980000615119934},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.3862999975681305},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.3504999876022339},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.323199987411499}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.582099974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5817999839782715},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2667999863624573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispa66905.2025.11259458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa66905.2025.11259458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Symposium on Image and Signal Processing and Analysis (ISPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6345105368","display_name":null,"funder_award_id":"ZS/2023/12/182322","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1588539311","https://openalex.org/W2755822369","https://openalex.org/W2964010806","https://openalex.org/W2982183006","https://openalex.org/W4211263234","https://openalex.org/W4221055733","https://openalex.org/W4310333988","https://openalex.org/W4324387123","https://openalex.org/W4360999323","https://openalex.org/W4377861261","https://openalex.org/W4389195633","https://openalex.org/W4390605218","https://openalex.org/W4391547665","https://openalex.org/W4392248604","https://openalex.org/W4401749612","https://openalex.org/W4401750114","https://openalex.org/W4406259896"],"related_works":[],"abstract_inverted_index":{"Depression":[0],"detection":[1],"using":[2],"multimodal":[3,124],"signals":[4],"has":[5],"garnered":[6],"growing":[7],"attention":[8],"due":[9],"to":[10,43],"its":[11],"potential":[12],"for":[13,81,90,102],"early":[14],"warning.":[15],"However,":[16],"existing":[17],"approaches":[18],"often":[19],"rely":[20],"on":[21,39],"limited":[22],"visual":[23,54,68,91],"features":[24,51],"or":[25],"computationally":[26],"intensive":[27],"fusion":[28],"mechanisms.":[29],"In":[30],"this":[31],"study,":[32],"we":[33,74],"present":[34],"a":[35],"novel":[36],"framework":[37,119],"based":[38],"the":[40,65,76,85,95,114,117],"Mamba":[41,78],"structure":[42],"address":[44],"these":[45],"challenges.":[46],"Our":[47],"method":[48],"fuses":[49],"audio":[50,82],"with":[52],"enriched":[53],"representations":[55],"by":[56],"combining":[57],"facial":[58],"landmarks":[59],"and":[60,84],"action":[61],"units":[62],"(AUs),":[63],"enhancing":[64],"expressiveness":[66],"of":[67,116],"cues.":[69],"To":[70],"capture":[71],"intramodal":[72],"information,":[73],"propose":[75],"Audio":[77],"Encoder":[79],"(AME)":[80],"modality,":[83],"Vision":[86],"CrossMamba":[87,97],"(VCM)":[88],"module":[89,99],"feature":[92],"fusion.":[93],"Furthermore,":[94],"Audio-Vision":[96],"(AVCM)":[98],"is":[100],"designed":[101],"intermodal":[103],"interactions.":[104],"Experimental":[105],"results":[106],"demonstrate":[107],"superior":[108],"performance":[109],"over":[110],"several":[111],"baselines,":[112],"highlighting":[113],"effectiveness":[115],"proposed":[118],"in":[120],"detecting":[121],"depression":[122],"from":[123],"data.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-01T00:00:00"}