{"id":"https://openalex.org/W4366259363","doi":"https://doi.org/10.1109/msmc.2022.3224843","title":"Addressee Detection Using Facial and Audio Features in Mixed Human\u2013Human and Human\u2013Robot Settings: A Deep Learning Framework","display_name":"Addressee Detection Using Facial and Audio Features in Mixed Human\u2013Human and Human\u2013Robot Settings: A Deep Learning Framework","publication_year":2023,"publication_date":"2023-04-01","ids":{"openalex":"https://openalex.org/W4366259363","doi":"https://doi.org/10.1109/msmc.2022.3224843"},"language":"en","primary_location":{"id":"doi:10.1109/msmc.2022.3224843","doi":"https://doi.org/10.1109/msmc.2022.3224843","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/msmc.2022.3224843","pdf_url":null,"source":{"id":"https://openalex.org/S2501039776","display_name":"IEEE Systems Man and Cybernetics Magazine","issn_l":"2333-942X","issn":["2333-942X","2334-0126","2380-1298"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"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 Systems, Man, and Cybernetics Magazine","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5090074861","display_name":"Fiseha B. Tesema","orcid":"https://orcid.org/0000-0002-7472-4007","observed_orcids":["https://orcid.org/0000-0002-7472-4007"]},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fiseha B. Tesema","raw_affiliation_strings":["Postdoctoral Fellow, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China"],"raw_orcid":"https://orcid.org/0000-0002-7472-4007","affiliations":[{"raw_affiliation_string":"Postdoctoral Fellow, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010340252","display_name":"Jason J. Gu","orcid":"https://orcid.org/0000-0002-7626-1077","observed_orcids":["https://orcid.org/0000-0002-7626-1077"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Gu","raw_affiliation_strings":["Engineering Institute of Canada, Halifax, NS, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7626-1077","affiliations":[{"raw_affiliation_string":"Engineering Institute of Canada, Halifax, NS, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074371475","display_name":"Wei Song","orcid":"https://orcid.org/0000-0002-0828-7486","observed_orcids":["https://orcid.org/0000-0002-0828-7486","https://orcid.org/0000-0002-4227-7417","https://orcid.org/0000-0002-7084-5231"]},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Song","raw_affiliation_strings":["Principal Investigator, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China"],"raw_orcid":"https://orcid.org/0000-0002-0828-7486","affiliations":[{"raw_affiliation_string":"Principal Investigator, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079051307","display_name":"Hong Qi Wu","orcid":"https://orcid.org/0000-0002-7019-8046","observed_orcids":["https://orcid.org/0000-0002-7019-8046"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Wu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, P.R. China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039356472","display_name":"Shiqiang Zhu","orcid":"https://orcid.org/0000-0002-5687-4001","observed_orcids":["https://orcid.org/0000-0002-5687-4001"]},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqiang Zhu","raw_affiliation_strings":["Director of Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Director of Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028966460","display_name":"Zheyuan Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyuan Lin","raw_affiliation_strings":["Engineer, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineer, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078866305","display_name":"Min Huang","orcid":"https://orcid.org/0000-0001-6152-7912","observed_orcids":["https://orcid.org/0000-0001-6152-7912","https://orcid.org/0009-0002-4841-9532"]},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Huang","raw_affiliation_strings":["Engineer, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineer, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396400","display_name":"Wen Wang","orcid":"https://orcid.org/0009-0009-1644-2341","observed_orcids":["https://orcid.org/0009-0009-1644-2341"]},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Assistant Researcher, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Assistant Researcher, Zhejiang Lab, Hangzhou, Zhejiang Province, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071564241","display_name":"Rajesh Kumar","orcid":"https://orcid.org/0000-0003-0813-7485","observed_orcids":["https://orcid.org/0000-0003-0813-7485"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rajesh Kumar","raw_affiliation_strings":["Associate professor, Yangtze Delta Region Institute (Huzhou), UESTC, Huzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0813-7485","affiliations":[{"raw_affiliation_string":"Associate professor, Yangtze Delta Region Institute (Huzhou), UESTC, Huzhou, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4272,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.58792096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"9","issue":"2","first_page":"25","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8960000276565552,"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/T12031","display_name":"Speech and dialogue systems","score":0.8960000276565552,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.06719999760389328,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.01899999938905239,"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/human-robot-interaction","display_name":"human-robot interaction","score":0.9079999923706055},{"id":"https://openalex.org/keywords/facial-features","display_name":"facial features","score":0.6380000114440918},{"id":"https://openalex.org/keywords/audio-features","display_name":"audio features","score":0.9860000014305115},{"id":"https://openalex.org/keywords/gaze","display_name":"gaze","score":0.37400001287460327},{"id":"https://openalex.org/keywords/utterance","display_name":"utterance","score":0.4880000054836273},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776612043380737},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7456730008125305},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.7252219915390015},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.6490365862846375},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6044000387191772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.587676465511322},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5548292398452759},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5271570086479187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4923475980758667},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4740138649940491},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4327213168144226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.323677122592926},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13906264305114746},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11271771788597107},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09559348225593567}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msmc.2022.3224843","doi":"https://doi.org/10.1109/msmc.2022.3224843","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/msmc.2022.3224843","pdf_url":null,"source":{"id":"https://openalex.org/S2501039776","display_name":"IEEE Systems Man and Cybernetics Magazine","issn_l":"2333-942X","issn":["2333-942X","2334-0126","2380-1298"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"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 Systems, Man, and Cybernetics Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2552995194","display_name":null,"funder_award_id":"2019R51010","funder_id":"https://openalex.org/F4320336605","funder_display_name":"National Ten Thousand Talent Program"},{"id":"https://openalex.org/G3886522921","display_name":null,"funder_award_id":"115002-UB2107QJ","funder_id":"https://openalex.org/F4320336605","funder_display_name":"National Ten Thousand Talent Program"},{"id":"https://openalex.org/G492650815","display_name":null,"funder_award_id":"U21A20488","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"},{"id":"https://openalex.org/F4320336605","display_name":"National Ten Thousand Talent Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W186850435","https://openalex.org/W238427141","https://openalex.org/W639708223","https://openalex.org/W1543320899","https://openalex.org/W1545326209","https://openalex.org/W1570557094","https://openalex.org/W1851144431","https://openalex.org/W1964448421","https://openalex.org/W1976538460","https://openalex.org/W2041957242","https://openalex.org/W2099019320","https://openalex.org/W2101807845","https://openalex.org/W2104246439","https://openalex.org/W2104657103","https://openalex.org/W2106738935","https://openalex.org/W2118847468","https://openalex.org/W2137785778","https://openalex.org/W2143402463","https://openalex.org/W2147768505","https://openalex.org/W2150610356","https://openalex.org/W2150715964","https://openalex.org/W2163605009","https://openalex.org/W2164350434","https://openalex.org/W2170565092","https://openalex.org/W2184540135","https://openalex.org/W2508984437","https://openalex.org/W2596627958","https://openalex.org/W2604379605","https://openalex.org/W2612919868","https://openalex.org/W2626778328","https://openalex.org/W2752782242","https://openalex.org/W2806785077","https://openalex.org/W2807844885","https://openalex.org/W2906848589","https://openalex.org/W2945047231","https://openalex.org/W2953092061","https://openalex.org/W2954802314","https://openalex.org/W2964171275","https://openalex.org/W3013020904","https://openalex.org/W3093835562","https://openalex.org/W3123104852","https://openalex.org/W3206008172","https://openalex.org/W4235653892"],"related_works":["https://openalex.org/W2043571528","https://openalex.org/W7095601112","https://openalex.org/W7095184931","https://openalex.org/W2144155486","https://openalex.org/W7096274898","https://openalex.org/W7029136855","https://openalex.org/W2888185730","https://openalex.org/W6964334382","https://openalex.org/W2745199549","https://openalex.org/W2325341608"],"abstract_inverted_index":{"Addressee":[0],"detection":[1],"(AD)":[2],"enables":[3],"robots":[4],"to":[5,58,110],"interact":[6],"smoothly":[7],"with":[8],"a":[9,35,42],"human":[10],"by":[11],"distinguishing":[12],"whether":[13],"it":[14],"is":[15,108],"being":[16],"addressed.":[17],"However,":[18],"this":[19,31],"has":[20],"not":[21,66,84],"been":[22],"widely":[23],"explored.":[24],"The":[25],"few":[26],"studies":[27],"that":[28],"have":[29,83],"explored":[30,85],"area":[32,114],"focused":[33],"on":[34,60],"human-to-human":[36,104],"or":[37,75],"human-to-robot":[38,106],"conversation":[39,88],"confined":[40],"inside":[41],"meeting":[43],"room":[44],"using":[45,115],"gaze":[46],"and":[47,53,72,78,81,91,105],"utterance.":[48],"These":[49],"works":[50],"used":[51],"statistical":[52],"rule-based":[54],"approaches,":[55],"which":[56],"tend":[57],"depend":[59],"specific":[61],"settings.":[62],"Further,":[63],"they":[64,82],"did":[65],"fully":[67],"leverage":[68],"the":[69,76,113],"available":[70,109],"audio":[71,92],"visual":[73],"information":[74],"short-term":[77],"long-term":[79],"segments,":[80],"combining":[86],"important":[87],"cues\u2014the":[89],"facial":[90],"features.":[93],"In":[94],"addition,":[95],"no":[96],"audiovisual":[97],"spatiotemporal":[98],"annotated":[99],"dataset":[100],"captured":[101],"in":[102],"mixed":[103],"settings":[107],"support":[111],"exploring":[112],"new":[116],"approaches.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-04-20T00:00:00"}