{"id":"https://openalex.org/W4414153873","doi":"https://doi.org/10.1109/tmm.2025.3608949","title":"MSSG: Multi-Scale Speaker Graph Network for Active Speaker Detection","display_name":"MSSG: Multi-Scale Speaker Graph Network for Active Speaker Detection","publication_year":2025,"publication_date":"2025-09-11","ids":{"openalex":"https://openalex.org/W4414153873","doi":"https://doi.org/10.1109/tmm.2025.3608949"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3608949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3608949","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5101679484","display_name":"Guanjun Li","orcid":"https://orcid.org/0000-0002-8200-5360"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanjun Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8200-5360","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhengqi Wen","orcid":"https://orcid.org/0009-0004-1632-4293"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1632-4293","affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9598-1881","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102942427","display_name":"Yuwang Wang","orcid":"https://orcid.org/0000-0002-6880-959X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwang Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09296172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"140","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"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":0.9878000020980835,"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":0.9452000260353088,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6259999871253967},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.5321000218391418},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49540001153945923},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.47589999437332153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46639999747276306},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4372999966144562},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4269999861717224},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4101000130176544},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.38029998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8604000210762024},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6259999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5842999815940857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5652999877929688},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.5321000218391418},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4269999861717224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3666999936103821},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.29120001196861267},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3608949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3608949","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1202467192","display_name":null,"funder_award_id":"U21B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G533509358","display_name":null,"funder_award_id":"62306316","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7003438179","display_name":null,"funder_award_id":"62322120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7270707897","display_name":null,"funder_award_id":"62206278","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W790225446","https://openalex.org/W2046394129","https://openalex.org/W2108598243","https://openalex.org/W2154636774","https://openalex.org/W2158387459","https://openalex.org/W2301358467","https://openalex.org/W2323437298","https://openalex.org/W2330149154","https://openalex.org/W2520477759","https://openalex.org/W2565639579","https://openalex.org/W2593116425","https://openalex.org/W2806331055","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2963076818","https://openalex.org/W2963524571","https://openalex.org/W2973179291","https://openalex.org/W2979750740","https://openalex.org/W2987391422","https://openalex.org/W2988452521","https://openalex.org/W3016098309","https://openalex.org/W3024085360","https://openalex.org/W3034702511","https://openalex.org/W3038871978","https://openalex.org/W3041847644","https://openalex.org/W3112188842","https://openalex.org/W3119269912","https://openalex.org/W3189964604","https://openalex.org/W3197584784","https://openalex.org/W3206008172","https://openalex.org/W3217435001","https://openalex.org/W4214701094","https://openalex.org/W4225302874","https://openalex.org/W4283801188","https://openalex.org/W4286378963","https://openalex.org/W4291920479","https://openalex.org/W4293093109","https://openalex.org/W4312268709","https://openalex.org/W4312319640","https://openalex.org/W4312466984","https://openalex.org/W4360596622","https://openalex.org/W4366548962","https://openalex.org/W4385822320","https://openalex.org/W4386075783","https://openalex.org/W4392908938","https://openalex.org/W4399513009","https://openalex.org/W4401692204","https://openalex.org/W4402704547","https://openalex.org/W4402754289","https://openalex.org/W4405778816"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"The":[0,113,172],"active":[1,92],"speaker":[2,93],"detection":[3,46,115],"task":[4],"is":[5,11],"to":[6,41,78],"determine":[7],"whether":[8],"a":[9,16,42,97,120,144,165],"person":[10],"speaking":[12],"or":[13,60],"not":[14],"across":[15],"series":[17],"of":[18,57,150,159],"video":[19],"frames.":[20],"Existing":[21],"methods":[22],"heavily":[23],"rely":[24],"on":[25,88,131],"facial":[26,49,62,81,89,156],"information":[27],"within":[28],"the":[29,69,86,132,138,151],"annotated":[30],"face":[31,58,74],"bounding":[32,75],"boxes":[33],"for":[34],"cross-modal":[35],"learning":[36],"with":[37,143],"audio.":[38],"This":[39],"leads":[40],"substantial":[43],"decline":[44],"in":[45,55,91],"performance":[47,130,167],"when":[48,155],"cues":[50,90,109,157],"are":[51,117,158],"unclear,":[52],"such":[53],"as":[54],"cases":[56],"occlusion":[59],"low-resolution":[61],"appearances.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"extend":[68],"perception":[70],"scale":[71],"using":[72],"only":[73,147],"box":[76],"annotations":[77],"model":[79,145,175],"both":[80],"and":[82,106,137,174],"gestural":[83],"cues,":[84],"addressing":[85],"over-reliance":[87],"detection.":[94],"We":[95],"propose":[96],"novel":[98],"graph":[99,122],"neural":[100],"network":[101],"that":[102,149],"models":[103],"inter-speaker":[104],"interactions":[105],"integrates":[107],"various":[108],"from":[110],"individual":[111],"speakers.":[112],"final":[114],"results":[116],"obtained":[118],"through":[119],"binary":[121],"node":[123],"classification":[124],"task.":[125],"Our":[126],"method":[127,163],"achieves":[128],"state-of-the-art":[129],"AVA-ActiveSpeaker":[133],"dataset":[134,140],"(mAP:":[135,141],"95.6%)":[136],"ASW":[139],"99.4%),":[142],"size":[146],"21%":[148],"second-best":[152],"method.":[153],"Additionally,":[154],"poor":[160],"quality,":[161],"our":[162],"demonstrates":[164],"significant":[166],"advantage":[168],"over":[169],"existing":[170],"approaches.":[171],"code":[173],"weights":[176],"will":[177],"be":[178],"available":[179],"at":[180],"<uri":[181],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/sdqdlgj/MSSG</uri>.":[183]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}