{"id":"https://openalex.org/W3199591511","doi":"https://doi.org/10.1109/thms.2021.3097973","title":"Interaction With Gaze, Gesture, and Speech in a Flexibly Configurable Augmented Reality System","display_name":"Interaction With Gaze, Gesture, and Speech in a Flexibly Configurable Augmented Reality System","publication_year":2021,"publication_date":"2021-08-05","ids":{"openalex":"https://openalex.org/W3199591511","doi":"https://doi.org/10.1109/thms.2021.3097973","mag":"3199591511"},"language":"en","primary_location":{"id":"doi:10.1109/thms.2021.3097973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2021.3097973","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"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 Human-Machine Systems","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/A5100773655","display_name":"Zhimin Wang","orcid":"https://orcid.org/0000-0001-5089-977X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhimin Wang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5089-977X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771231","display_name":"Haofei Wang","orcid":"https://orcid.org/0000-0002-1199-9206"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofei Wang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1199-9206","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070368172","display_name":"Huangyue Yu","orcid":"https://orcid.org/0000-0001-7983-6465"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huangyue Yu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7983-6465","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050527785","display_name":"Feng Lu","orcid":"https://orcid.org/0000-0001-9064-7964"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lu","raw_affiliation_strings":["Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, China","Peng Cheng Laboratory, Shenzhen, China","State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9064-7964","affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100773655"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":5.3886,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.9651864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"51","issue":"5","first_page":"524","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10888","display_name":"Augmented Reality Applications","score":0.9988999962806702,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/gesture","display_name":"Gesture","score":0.803048312664032},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7952452898025513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7685436010360718},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7573487758636475},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7362067103385925},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.6611637473106384},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6214374899864197},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6080862283706665},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.603945255279541},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5286871790885925},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4651084542274475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3769164979457855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3729652166366577},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3643428087234497},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06950291991233826}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.803048312664032},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7952452898025513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685436010360718},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7573487758636475},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7362067103385925},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.6611637473106384},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6214374899864197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6080862283706665},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.603945255279541},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5286871790885925},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4651084542274475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3769164979457855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3729652166366577},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3643428087234497},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06950291991233826},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/thms.2021.3097973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2021.3097973","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"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 Human-Machine Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6395956615","display_name":null,"funder_award_id":"2020TQ0156","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G730407121","display_name":null,"funder_award_id":"2021M691684","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W172711948","https://openalex.org/W1550283222","https://openalex.org/W1601345954","https://openalex.org/W1747778109","https://openalex.org/W1983239853","https://openalex.org/W1989689139","https://openalex.org/W1991544872","https://openalex.org/W1993448335","https://openalex.org/W1994349244","https://openalex.org/W2006071649","https://openalex.org/W2008517591","https://openalex.org/W2009803366","https://openalex.org/W2021580208","https://openalex.org/W2025530819","https://openalex.org/W2052310875","https://openalex.org/W2065228210","https://openalex.org/W2071215013","https://openalex.org/W2102804490","https://openalex.org/W2105238517","https://openalex.org/W2113336743","https://openalex.org/W2115248110","https://openalex.org/W2116309822","https://openalex.org/W2117043006","https://openalex.org/W2121426035","https://openalex.org/W2125490883","https://openalex.org/W2131813447","https://openalex.org/W2133229061","https://openalex.org/W2136057050","https://openalex.org/W2137864660","https://openalex.org/W2151308976","https://openalex.org/W2151647616","https://openalex.org/W2151905266","https://openalex.org/W2154868891","https://openalex.org/W2159971492","https://openalex.org/W2183910760","https://openalex.org/W2272545788","https://openalex.org/W2293069699","https://openalex.org/W2293649818","https://openalex.org/W2407300725","https://openalex.org/W2439667561","https://openalex.org/W2558712111","https://openalex.org/W2570004323","https://openalex.org/W2610966190","https://openalex.org/W2764065835","https://openalex.org/W2793406758","https://openalex.org/W2796228338","https://openalex.org/W2888827598","https://openalex.org/W2889098203","https://openalex.org/W2890229793","https://openalex.org/W2905309298","https://openalex.org/W2945162082","https://openalex.org/W2967543038","https://openalex.org/W2968220058","https://openalex.org/W2969067747","https://openalex.org/W2979947786","https://openalex.org/W2988817687","https://openalex.org/W3013897564","https://openalex.org/W3034063226","https://openalex.org/W3034484960","https://openalex.org/W3046107845","https://openalex.org/W3092114159","https://openalex.org/W3116043791","https://openalex.org/W3131117436","https://openalex.org/W4247873169","https://openalex.org/W6607057097","https://openalex.org/W6652615446","https://openalex.org/W6685962090","https://openalex.org/W6718508231","https://openalex.org/W6779891576","https://openalex.org/W6787531181"],"related_works":["https://openalex.org/W2172197285","https://openalex.org/W2991048842","https://openalex.org/W2750280393","https://openalex.org/W2355696739","https://openalex.org/W1880689012","https://openalex.org/W3158001554","https://openalex.org/W2771909920","https://openalex.org/W2957704286","https://openalex.org/W2773371143","https://openalex.org/W1801393351"],"abstract_inverted_index":{"Multimodal":[0,34],"interaction":[1,99],"has":[2,40],"become":[3],"a":[4,28,49,60,159],"recent":[5],"research":[6],"focus":[7],"since":[8],"it":[9],"offers":[10],"better":[11],"user":[12],"experience":[13],"in":[14,59,140],"augmented":[15],"reality":[16],"(AR)":[17],"systems.":[18,129],"However,":[19],"most":[20],"existing":[21],"works":[22],"only":[23],"combine":[24],"two":[25,109],"modalities":[26,107],"at":[27],"time,":[29],"e.g.,":[30],"gesture":[31,74],"and":[32,57,76,116,144],"speech.":[33],"interactive":[35,51,161],"system":[36,52,81,154,163],"integrating":[37],"gaze":[38,71],"cue":[39],"rarely":[41],"been":[42],"investigated.":[43],"In":[44],"this":[45],"article,":[46],"we":[47],"propose":[48],"multimodal":[50,160],"that":[53,134,164],"integrates":[54],"gaze,":[55],"gesture,":[56],"speech":[58,77],"flexibly":[61],"configurable":[62],"AR":[63,162],"system.":[64],"Our":[65,153],"lightweight":[66],"head-mounted":[67],"device":[68],"supports":[69],"accurate":[70],"tracking,":[72],"hand":[73],"recognition,":[75],"recognition":[78],"simultaneously.":[79],"The":[80,130],"can":[82],"be":[83],"easily":[84],"configured":[85],"into":[86],"various":[87],"modality":[88,137,147],"combinations,":[89],"which":[90],"enables":[91,165],"us":[92],"to":[93],"investigate":[94],"the":[95,103,111,117,135,145,156],"effects":[96],"of":[97,105,142],"different":[98],"techniques.":[100],"We":[101,121],"evaluate":[102],"efficiency":[104],"these":[106],"using":[108,127],"tasks:":[110],"lamp":[112],"brightness":[113],"adjustment":[114],"task":[115],"cube":[118],"manipulation":[119],"task.":[120],"also":[122],"collect":[123],"subjective":[124],"feedback":[125],"when":[126],"such":[128],"experimental":[131],"results":[132],"demonstrate":[133],"<i>Gaze+Gesture+Speech</i>":[136],"is":[138,148],"superior":[139],"terms":[141],"efficiency,":[143],"<i>Gesture+Speech</i>":[146],"more":[149],"preferred":[150],"by":[151],"users.":[152],"opens":[155],"pathway":[157],"toward":[158],"flexible":[166],"configuration.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}