{"id":"https://openalex.org/W3204195485","doi":"https://doi.org/10.5220/0011612900003417","title":"The VVAD-LRS3 Dataset for Visual Voice Activity Detection","display_name":"The VVAD-LRS3 Dataset for Visual Voice Activity Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W3204195485","doi":"https://doi.org/10.5220/0011612900003417","mag":"3204195485"},"language":"en","primary_location":{"id":"doi:10.5220/0011612900003417","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011612900003417","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0011612900003417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089577854","display_name":"Adrian Lubitz","orcid":null},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Adrian Lubitz","raw_affiliation_strings":["Department of Computer Science, University of Bremen, 28359 Bremen, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bremen, 28359 Bremen, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013519837","display_name":"Mat\u00edas Valdenegro-Toro","orcid":"https://orcid.org/0000-0001-5793-9498"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE","NL"],"is_corresponding":false,"raw_author_name":"Matias Valdenegro-Toro","raw_affiliation_strings":["Department of AI, University of Groningen, 9747 AG Groningen, The Netherlands, --- Select a Country ---","Robotics Innovation Center, German Research Center for Artificial Intelligence, Bremen, Germany"],"affiliations":[{"raw_affiliation_string":"Department of AI, University of Groningen, 9747 AG Groningen, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I169381384"]},{"raw_affiliation_string":"Robotics Innovation Center, German Research Center for Artificial Intelligence, Bremen, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016436943","display_name":"Frank Kirchner","orcid":"https://orcid.org/0000-0002-1713-9784"},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Kirchner","raw_affiliation_strings":["Department of Computer Science, University of Bremen, 28359 Bremen, Germany, --- Select a Country ---","Robotics Innovation Center, German Research Center for Artificial Intelligence, Bremen, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bremen, 28359 Bremen, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I180437899"]},{"raw_affiliation_string":"Robotics Innovation Center, German Research Center for Artificial Intelligence, Bremen, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089577854"],"corresponding_institution_ids":["https://openalex.org/I180437899"],"apc_list":null,"apc_paid":null,"fwci":0.2429,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4832484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8485070466995239},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7133592367172241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6847710609436035},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5897572040557861},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5733867883682251},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5671674609184265},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.560914158821106},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47269749641418457},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4597068428993225},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.444210410118103},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4276789128780365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34335875511169434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485070466995239},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7133592367172241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6847710609436035},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5897572040557861},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5733867883682251},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5671674609184265},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.560914158821106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47269749641418457},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4597068428993225},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.444210410118103},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4276789128780365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34335875511169434},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0011612900003417","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011612900003417","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.13789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.13789","pdf_url":"https://arxiv.org/pdf/2109.13789","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":"doi:10.5220/0011612900003417","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011612900003417","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W143363694","https://openalex.org/W581546343","https://openalex.org/W587875510","https://openalex.org/W1509579205","https://openalex.org/W2064675550","https://openalex.org/W2098923380","https://openalex.org/W2115252128","https://openalex.org/W2155948168","https://openalex.org/W2156507789","https://openalex.org/W2162947270","https://openalex.org/W2169614656","https://openalex.org/W2323437298","https://openalex.org/W2325939864","https://openalex.org/W2405164344","https://openalex.org/W2612445135","https://openalex.org/W2795038878","https://openalex.org/W2801740959","https://openalex.org/W2891205112","https://openalex.org/W2963446712","https://openalex.org/W3040865677","https://openalex.org/W4249003903","https://openalex.org/W4285719527","https://openalex.org/W4297775537","https://openalex.org/W4308264370"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W4387327236","https://openalex.org/W2183488467","https://openalex.org/W4309907966","https://openalex.org/W4387896287","https://openalex.org/W2187490799","https://openalex.org/W1990237101","https://openalex.org/W4300172249","https://openalex.org/W3170838353"],"abstract_inverted_index":{"Robots":[0],"are":[1,46,75],"becoming":[2],"everyday":[3],"devices,":[4],"increasing":[5],"their":[6],"interaction":[7,13],"with":[8,165],"humans.":[9],"To":[10],"make":[11],"human-machine":[12],"more":[14],"natural,":[15],"cognitive":[16],"features":[17],"like":[18],"Visual":[19],"Voice":[20],"Activity":[21],"Detection":[22],"(VVAD),":[23],"which":[24],"can":[25],"detect":[26],"whether":[27],"a":[28,38,89,140],"person":[29],"is":[30],"speaking":[31],"or":[32],"not,":[33],"given":[34],"visual":[35],"input":[36],"of":[37,48,70,82,127,155,173],"camera,":[39],"need":[40],"to":[41],"be":[42],"implemented.":[43],"Neural":[44,142],"networks":[45],"state":[47],"the":[49,80,94,102,115,160,176],"art":[50],"for":[51,79],"tasks":[52],"in":[53],"Image":[54],"Processing,":[55],"Time":[56],"Series":[57],"Prediction,":[58],"Natural":[59],"Language":[60],"Processing":[61],"and":[62,130,133,135],"other":[63],"domains.":[64],"Those":[65],"Networks":[66],"require":[67],"large":[68,90],"quantities":[69],"labeled":[71],"data.":[72],"Currently":[73],"there":[74],"not":[76],"many":[77],"datasets":[78],"task":[81],"VVAD.":[83],"In":[84],"this":[85],"work":[86],"we":[87],"created":[88],"scale":[91],"dataset":[92,107,118],"called":[93],"VVAD-LRS3":[95,106],"dataset,":[96],"derived":[97],"by":[98],"automatic":[99],"annotations":[100],"from":[101],"LRS3":[103],"dataset.":[104],"The":[105],"contains":[108],"over":[109,112],"44K":[110],"samples,":[111],"three":[113],"times":[114],"next":[116],"competitive":[117],"(WildVVAD).":[119],"We":[120],"evaluate":[121],"different":[122],"baselines":[123],"on":[124,150,159,175],"four":[125],"kinds":[126],"features:":[128],"facial":[129,134,151],"lip":[131,136],"images,":[132],"landmark":[137],"features.":[138],"With":[139],"Convolutional":[141],"Network":[143],"Long":[144],"Short":[145],"Term":[146],"Memory":[147],"(CNN":[148],"LSTM)":[149],"images":[152],"an":[153,171],"accuracy":[154,172],"92%":[156],"was":[157],"reached":[158],"test":[161,177],"set.":[162,178],"A":[163],"study":[164],"humans":[166],"showed":[167],"that":[168],"they":[169],"reach":[170],"87.93%":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
