{"id":"https://openalex.org/W4389665509","doi":"https://doi.org/10.1109/iros55552.2023.10342522","title":"Attention-Based VR Facial Animation with Visual Mouth Camera Guidance for Immersive Telepresence Avatars","display_name":"Attention-Based VR Facial Animation with Visual Mouth Camera Guidance for Immersive Telepresence Avatars","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665509","doi":"https://doi.org/10.1109/iros55552.2023.10342522"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5009180266","display_name":"Andre Rochow","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andre Rochow","raw_affiliation_strings":["University of Bonn,Autonomous Intelligent Systems group,Germany","Autonomous Intelligent Systems group, University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn,Autonomous Intelligent Systems group,Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Autonomous Intelligent Systems group, University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023789533","display_name":"Max Schwarz","orcid":"https://orcid.org/0000-0002-9942-6604"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Max Schwarz","raw_affiliation_strings":["University of Bonn,Autonomous Intelligent Systems group,Germany","Autonomous Intelligent Systems group, University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn,Autonomous Intelligent Systems group,Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Autonomous Intelligent Systems group, University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027761977","display_name":"Sven Behnke","orcid":"https://orcid.org/0000-0002-5040-7525"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Behnke","raw_affiliation_strings":["University of Bonn,Autonomous Intelligent Systems group,Germany","Autonomous Intelligent Systems group, University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn,Autonomous Intelligent Systems group,Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Autonomous Intelligent Systems group, University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009180266"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":0.369,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61601474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1276","last_page":"1283"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9952999949455261,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.791470468044281},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7197273373603821},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6888558864593506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6575682163238525},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5064517259597778},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.4982461929321289},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.49535810947418213},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4864889979362488},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.440976083278656},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4188958406448364},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.41307157278060913},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3466285467147827},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.23396915197372437},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.20283243060112},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.2026856541633606},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.20021066069602966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791470468044281},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7197273373603821},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6888558864593506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575682163238525},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5064517259597778},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.4982461929321289},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.49535810947418213},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4864889979362488},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.440976083278656},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4188958406448364},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.41307157278060913},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3466285467147827},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.23396915197372437},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.20283243060112},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2026856541633606},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.20021066069602966},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2811426698","https://openalex.org/W2891298711","https://openalex.org/W2957926190","https://openalex.org/W2962785568","https://openalex.org/W2963168844","https://openalex.org/W2981087920","https://openalex.org/W3008823916","https://openalex.org/W3120163087","https://openalex.org/W3182714435","https://openalex.org/W3201823266","https://openalex.org/W3207250917","https://openalex.org/W4312561237","https://openalex.org/W4312955607","https://openalex.org/W6767264202"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2748502319","https://openalex.org/W2906438086","https://openalex.org/W615219140","https://openalex.org/W2165663879","https://openalex.org/W2139716748","https://openalex.org/W4385825592","https://openalex.org/W2188148675","https://openalex.org/W2096968018","https://openalex.org/W3040900128"],"abstract_inverted_index":{"Facial":[0],"animation":[1,45,67,215],"in":[2,202],"virtual":[3],"reality":[4],"environments":[5],"is":[6,46,63],"essential":[7],"for":[8],"applications":[9],"that":[10,81],"necessitate":[11],"clear":[12],"visibility":[13],"of":[14,32,43,52,73,108,148,161],"the":[15,19,30,50,71,118,131,136,146,173,186,213,221],"user's":[16],"face":[17,31],"and":[18,85,99,139,156,194,205],"ability":[20],"to":[21,96,120,144,166,217],"convey":[22],"emotional":[23],"signals.":[24],"In":[25,208],"our":[26,218],"scenario,":[27],"we":[28,133,164,210],"animate":[29,157],"an":[33,141],"operator":[34],"who":[35],"controls":[36],"a":[37,55,61,78,90,102,126,158,200],"robotic":[38],"Avatar":[39,223],"system.":[40],"The":[41],"use":[42],"facial":[44,74,123,195,214],"particularly":[47],"valuable":[48],"when":[49],"perception":[51],"interacting":[53],"with":[54,70,106,117,190],"specific":[56],"individual,":[57],"rather":[58],"than":[59],"just":[60],"robot,":[62],"intended.":[64],"Purely":[65],"keypoint-driven":[66],"approaches":[68],"struggle":[69],"complexity":[72],"movements.":[75],"We":[76,176],"present":[77],"hybrid":[79],"method":[80,94,198],"uses":[82],"both":[83],"keypoints":[84,138],"direct":[86],"visual":[87,168],"guidance":[88],"from":[89,130],"mouth":[91,127,162,169,187],"camera.":[92],"Our":[93,197],"generalizes":[95],"unseen":[97],"operators":[98],"requires":[100],"only":[101],"quick":[103],"enrolment":[104],"step":[105],"capture":[107],"two":[109],"short":[110],"videos.":[111],"Multiple":[112],"source":[113,150],"images":[114],"are":[115],"selected":[116],"intention":[119],"cover":[121],"different":[122],"expressions.":[124],"Given":[125],"camera":[128,170,188],"frame":[129],"HMD,":[132],"dynamically":[134],"construct":[135],"target":[137],"apply":[140],"attention":[142],"mechanism":[143],"determine":[145],"importance":[147],"each":[149],"image.":[151],"To":[152],"resolve":[153],"keypoint":[154],"ambiguities":[155],"broader":[159],"range":[160],"expressions,":[163],"propose":[165],"inject":[167],"information":[171],"into":[172],"latent":[174],"space.":[175],"enable":[177],"training":[178],"on":[179],"large-scale":[180],"speaking":[181],"head":[182],"datasets":[183],"by":[184],"simulating":[185],"input":[189],"its":[191],"perspective":[192],"differences":[193],"deformations.":[196],"outperforms":[199],"baseline":[201],"quality,":[203],"capability,":[204],"temporal":[206],"consistency.":[207],"addition,":[209],"highlight":[211],"how":[212],"contributed":[216],"victory":[219],"at":[220],"ANA":[222],"XPRIZE":[224],"Finals.":[225]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}