{"id":"https://openalex.org/W7133313111","doi":"https://doi.org/10.1109/ijcb65343.2025.11410746","title":"ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection","display_name":"ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7133313111","doi":"https://doi.org/10.1109/ijcb65343.2025.11410746"},"language":null,"primary_location":{"id":"doi:10.1109/ijcb65343.2025.11410746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"},"type":"article","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/A5088262626","display_name":"Tiago Roxo","orcid":"https://orcid.org/0000-0001-9563-8039"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Tiago Roxo","raw_affiliation_strings":["University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016093558","display_name":"Joana C. Costa","orcid":"https://orcid.org/0000-0003-3995-4621"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joana C. Costa","raw_affiliation_strings":["University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125929752","display_name":"Pedro R. M. In\u00e1cio","orcid":null},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro R. M. In\u00e1cio","raw_affiliation_strings":["University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090305015","display_name":"Hugo Proen\u00e7a","orcid":"https://orcid.org/0000-0003-2551-8570"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Hugo Proen\u00e7a","raw_affiliation_strings":["University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Beira,Instituto de Telecomunica&#x00E7;&#x00F5;es,Interior,Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83696256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4934999942779541,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4934999942779541,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.24529999494552612,"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/T11448","display_name":"Face recognition and analysis","score":0.09269999712705612,"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/face","display_name":"Face (sociological concept)","score":0.6353999972343445},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6161999702453613},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6103000044822693},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5871999859809875},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5684000253677368},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49239999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6420000195503235},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6353999972343445},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6103000044822693},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5871999859809875},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5339000225067139},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45840001106262207},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4271000027656555},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.3249000012874603},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb65343.2025.11410746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","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":42,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2111025459","https://openalex.org/W2316138215","https://openalex.org/W2330149154","https://openalex.org/W2410968923","https://openalex.org/W2604463754","https://openalex.org/W2618799552","https://openalex.org/W2808154247","https://openalex.org/W2867270703","https://openalex.org/W2957702778","https://openalex.org/W2963307811","https://openalex.org/W2963365374","https://openalex.org/W2972729214","https://openalex.org/W2986999591","https://openalex.org/W3016098309","https://openalex.org/W3034702511","https://openalex.org/W3038871978","https://openalex.org/W3048939150","https://openalex.org/W3092990874","https://openalex.org/W3112188842","https://openalex.org/W3116298410","https://openalex.org/W3135222947","https://openalex.org/W3162475350","https://openalex.org/W3172472082","https://openalex.org/W3189964604","https://openalex.org/W3197584784","https://openalex.org/W3200102014","https://openalex.org/W3206008172","https://openalex.org/W3217214873","https://openalex.org/W3217412301","https://openalex.org/W4214701094","https://openalex.org/W4225302874","https://openalex.org/W4285047164","https://openalex.org/W4312268709","https://openalex.org/W4312466984","https://openalex.org/W4385245566","https://openalex.org/W4385822320","https://openalex.org/W4386075783","https://openalex.org/W4390489179","https://openalex.org/W4399513009","https://openalex.org/W4402754289","https://openalex.org/W4405520428"],"related_works":[],"abstract_inverted_index":{"State-of-the-art":[0],"Active":[1],"Speaker":[2],"Detection":[3],"(ASD)":[4],"approaches":[5],"mainly":[6],"use":[7],"audio":[8],"and":[9,34,80,90,125],"facial":[10],"features":[11],"as":[12,143],"input.":[13],"However,":[14],"the":[15,65,115,120],"main":[16],"hypothesis":[17],"in":[18,39,114,119,126,136],"this":[19],"paper":[20],"is":[21,25,91,140],"that":[22,56,109],"body":[23,61,104],"dynamics":[24],"also":[26],"highly":[27],"correlated":[28],"to":[29,82],"\"speaking\"":[30],"(and":[31],"\"listening\")":[32],"actions":[33],"should":[35],"be":[36,48],"particularly":[37],"useful":[38],"wild":[40],"conditions":[41],"(e.g.,":[42],"surveillance":[43],"settings),":[44],"where":[45],"face":[46,59,102],"cannot":[47],"reliably":[49],"accessed.":[50],"We":[51],"propose":[52],"ASDnB,":[53],"a":[54,144],"model":[55],"singularly":[57],"integrates":[58],"with":[60,93,103],"information":[62],"by":[63],"merging":[64],"inputs":[66],"at":[67,153],"different":[68],"steps":[69],"of":[70,88,101,123],"feature":[71,96],"extraction.":[72],"Our":[73,106],"approach":[74],"splits":[75],"3D":[76],"convolution":[77],"into":[78],"2D":[79],"1D":[81],"reduce":[83],"computation":[84],"cost":[85],"without":[86],"loss":[87],"performance,":[89],"trained":[92],"adaptive":[94],"weight":[95],"importance":[97],"for":[98,147],"improved":[99],"complement":[100],"data.":[105],"experiments":[107],"show":[108],"ASDnB":[110,133],"achieves":[111],"state-of-the-art":[112],"results":[113],"benchmark":[116],"dataset":[117],"(AVA-ActiveSpeaker),":[118],"challenging":[121],"data":[122],"WASD,":[124],"cross-domain":[127],"settings":[128],"using":[129],"Columbia.":[130],"This":[131],"way,":[132],"can":[134],"perform":[135],"multiple":[137],"settings,":[138],"which":[139],"positively":[141],"regarded":[142],"strong":[145],"baseline":[146],"robust":[148],"ASD":[149],"models":[150],"(code":[151],"available":[152],"https://github.com/Tiago-Roxo/ASDnB).":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}
