{"id":"https://openalex.org/W7160250990","doi":"https://doi.org/10.1109/wacv61042.2026.00111","title":"GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection","display_name":"GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160250990","doi":"https://doi.org/10.1109/wacv61042.2026.00111"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5060292732","display_name":"Yu Wang","orcid":"https://orcid.org/0009-0002-4416-937X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Indiana University,Bloomington,Indiana,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,Indiana,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011642798","display_name":"Juhyung Ha","orcid":"https://orcid.org/0000-0002-6596-5116"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juhyung Ha","raw_affiliation_strings":["Indiana University,Bloomington,Indiana,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,Indiana,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135357870","display_name":"Frangil M. Ramirez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frangil M. Ramirez","raw_affiliation_strings":["Indiana University,Bloomington,Indiana,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,Indiana,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375397","display_name":"Yuchen Wang","orcid":"https://orcid.org/0000-0002-1077-5294"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchen Wang","raw_affiliation_strings":["Indiana University,Bloomington,Indiana,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,Indiana,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135297181","display_name":"David J. Crandall","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David J. Crandall","raw_affiliation_strings":["Indiana University,Bloomington,Indiana,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,Indiana,USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1074","last_page":"1083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7537999749183655,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7537999749183655,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.16590000689029694,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.008799999952316284,"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/fusion","display_name":"Fusion","score":0.4530999958515167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38420000672340393},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3837999999523163},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3010999858379364},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2621999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6344000101089478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5782999992370605},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4318999946117401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2498999983072281}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2962960500","https://openalex.org/W3016098309","https://openalex.org/W3034702511","https://openalex.org/W3048939150","https://openalex.org/W3172472082","https://openalex.org/W3189964604","https://openalex.org/W3205786327","https://openalex.org/W3206008172","https://openalex.org/W4214701094","https://openalex.org/W4225302874","https://openalex.org/W4291920479","https://openalex.org/W4297841641","https://openalex.org/W4312268709","https://openalex.org/W4312319640","https://openalex.org/W4312466984","https://openalex.org/W4372259900","https://openalex.org/W4385822320","https://openalex.org/W4386075783","https://openalex.org/W4390685975","https://openalex.org/W4392903825","https://openalex.org/W4392908938","https://openalex.org/W4394593115","https://openalex.org/W4399513009","https://openalex.org/W4402726986","https://openalex.org/W4402754289","https://openalex.org/W4403913147","https://openalex.org/W4405520428","https://openalex.org/W4408351759","https://openalex.org/W4408352877","https://openalex.org/W4408647465","https://openalex.org/W4410914919","https://openalex.org/W4413144376","https://openalex.org/W7133313111"],"related_works":[],"abstract_inverted_index":{"Active":[0],"Speaker":[1],"Detection":[2],"(ASD)":[3],"aims":[4],"to":[5,24,35,114,125],"identify":[6],"who":[7],"is":[8],"currently":[9],"speaking":[10],"in":[11,47],"each":[12,180],"frame":[13],"of":[14,91,169,179],"a":[15,56,66],"video.":[16],"Most":[17],"state-of-the-art":[18,133],"approaches":[19],"rely":[20],"on":[21,135,151,162],"late":[22,31],"fusion":[23,32,76],"combine":[25],"visual":[26],"and":[27,121,147,154,158],"audio":[28],"features,":[29],"but":[30],"often":[33],"fails":[34],"capture":[36],"fine-grained":[37],"cross-modal":[38],"interactions,":[39],"which":[40],"can":[41],"be":[42],"critical":[43],"for":[44],"robust":[45],"performance":[46,161],"unconstrained":[48],"scenarios.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,105],"introduce":[54],"GateFusion,":[55],"novel":[57],"architecture":[58],"that":[59],"combines":[60],"strong":[61],"pretrained":[62],"unimodal":[63,116],"encoders":[64],"with":[65,118],"Hierarchical":[67],"Gated":[68],"Fusion":[69],"Decoder":[70],"(HiGate).":[71],"HiGate":[72],"enables":[73],"progressive,":[74],"multi-depth":[75],"by":[77,96],"adaptively":[78],"injecting":[79],"contextual":[80],"features":[81],"from":[82],"one":[83],"modality":[84],"into":[85],"the":[86,92,167,176],"other":[87],"at":[88],"multiple":[89],"layers":[90],"Transformer":[93],"backbone,":[94],"guided":[95],"learnable,":[97],"bimodally-conditioned":[98],"gates.":[99],"To":[100],"further":[101],"strengthen":[102],"multimodal":[103,119],"learning,":[104],"propose":[106],"two":[107],"auxiliary":[108],"objectives:":[109],"Masked":[110],"Alignment":[111],"Loss":[112],"(MAL)":[113],"align":[115],"outputs":[117],"predictions,":[120],"Over-Positive":[122],"Penalty":[123],"(OPP)":[124],"suppress":[126],"spurious":[127],"video-only":[128],"activations.":[129],"GateFusion":[130],"establishes":[131],"new":[132],"results":[134],"several":[136],"challenging":[137],"ASD":[138],"benchmarks,":[139,156],"achieving":[140],"77.8%":[141],"mAP":[142,145,149],"(+9.4%),":[143],"86.1%":[144],"(+2.9%),":[146],"96.1%":[148],"(+0.5%)":[150],"Ego4D-ASD,":[152],"UniTalk,":[153],"WASD":[155],"respectively,":[157],"delivering":[159],"competitive":[160],"AVA-ActiveSpeaker.":[163],"Out-of-domain":[164],"experiments":[165],"demonstrate":[166],"generalization":[168],"our":[170],"model,":[171],"while":[172],"comprehensive":[173],"ablations":[174],"show":[175],"complementary":[177],"benefits":[178],"component.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}