{"id":"https://openalex.org/W1964448421","doi":"https://doi.org/10.1145/2733373.2806293","title":"Deep Multimodal Speaker Naming","display_name":"Deep Multimodal Speaker Naming","publication_year":2015,"publication_date":"2015-10-13","ids":{"openalex":"https://openalex.org/W1964448421","doi":"https://doi.org/10.1145/2733373.2806293","mag":"1964448421"},"language":"en","primary_location":{"id":"doi:10.1145/2733373.2806293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1507.04831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yongtao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yongtao Hu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jimmy SJ. Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jimmy SJ. Ren","raw_affiliation_strings":["SenseTime Group Limited, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingwen Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwen Dai","raw_affiliation_strings":["Xim Industry Inc., Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xim Industry Inc., Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chang Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Yuan","raw_affiliation_strings":["Lenovo Group Limited, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo Group Limited, Hong Kong, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xu","raw_affiliation_strings":["SenseTime Group Limited, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenping Wang","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1107","last_page":"1110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9901000261306763,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5695000290870667},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.47380000352859497},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46399998664855957},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43140000104904175},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41119998693466187},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.4056999981403351},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6783999800682068},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2733373.2806293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1507.04831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1507.04831","pdf_url":"https://arxiv.org/pdf/1507.04831","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1507.04831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1507.04831","pdf_url":"https://arxiv.org/pdf/1507.04831","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1971414456","https://openalex.org/W2028285070","https://openalex.org/W2029848040","https://openalex.org/W2050968192","https://openalex.org/W2058685270","https://openalex.org/W2062826588","https://openalex.org/W2064125229","https://openalex.org/W2093153344","https://openalex.org/W2105303679","https://openalex.org/W2119031011","https://openalex.org/W2121027212","https://openalex.org/W2121647436","https://openalex.org/W2138451337","https://openalex.org/W2153635508","https://openalex.org/W2161381512","https://openalex.org/W2163808566","https://openalex.org/W2168996682","https://openalex.org/W2172013424"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"speaker":[1,130],"naming":[2,131],"is":[3,21,35,125],"the":[4,49,97],"problem":[5,24,46],"of":[6,51,100,143],"localizing":[7],"as":[8,10],"well":[9,64],"identifying":[11],"each":[12],"speaking":[13],"character":[14],"in":[15],"a":[16,22,85],"TV/movie/live":[17],"show":[18,107],"video.":[19],"This":[20],"challenging":[23],"mainly":[25],"attributes":[26],"to":[27,37,44,70,94,127],"its":[28],"multimodal":[29,42,122],"nature,":[30],"namely":[31],"face":[32,102,111],"cue":[33],"alone":[34],"insufficient":[36],"achieve":[38,71,128],"good":[39],"performance.":[40],"Previous":[41],"approaches":[43,62],"this":[45,81],"usually":[47],"process":[48],"data":[50],"different":[52],"modalities":[53],"individually":[54],"and":[55,103,141],"merge":[56],"them":[57],"using":[58,110],"handcrafted":[59],"heuristics.":[60],"Such":[61],"work":[63],"for":[65,74],"simple":[66],"scenes,":[67],"but":[68],"fail":[69],"high":[72],"performance":[73,132],"speakers":[75],"with":[76,120],"large":[77],"appearance":[78],"variations.":[79],"In":[80],"paper,":[82],"we":[83],"propose":[84],"novel":[86],"convolutional":[87],"neural":[88],"networks":[89],"(CNN)":[90],"based":[91],"learning":[92],"framework":[93],"automatically":[95],"learn":[96],"fusion":[98],"function":[99],"both":[101],"audio":[104],"cues.":[105],"We":[106],"that":[108],"without":[109],"tracking,":[112],"facial":[113],"landmark":[114],"localization":[115],"or":[116],"subtitle/transcript,":[117],"our":[118,144],"system":[119],"robust":[121],"feature":[123],"extraction":[124],"able":[126],"state-of-the-art":[129],"evaluated":[133],"on":[134],"two":[135],"diverse":[136],"TV":[137],"series.":[138],"The":[139],"dataset":[140],"implementation":[142],"algorithm":[145],"are":[146],"publicly":[147],"available":[148],"online.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}