{"id":"https://openalex.org/W4381786712","doi":"https://doi.org/10.1109/wf-iot54382.2022.10152230","title":"Facial Landmark Predictions with Applications to Metaverse","display_name":"Facial Landmark Predictions with Applications to Metaverse","publication_year":2022,"publication_date":"2022-10-26","ids":{"openalex":"https://openalex.org/W4381786712","doi":"https://doi.org/10.1109/wf-iot54382.2022.10152230"},"language":"en","primary_location":{"id":"doi:10.1109/wf-iot54382.2022.10152230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wf-iot54382.2022.10152230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","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/A5110373920","display_name":"Qiao Han","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Qiao Han","raw_affiliation_strings":["Nanyang Technological University Singapore,Computer Science and Engineering,Singapore","Computer Science and Engineering, Nanyang Technological University Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University Singapore,Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Computer Science and Engineering, Nanyang Technological University Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071321132","display_name":"Jun Zhao","orcid":"https://orcid.org/0000-0002-3004-7091"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jun Zhao","raw_affiliation_strings":["Nanyang Technological University Singapore,Computer Science and Engineering,Singapore","Computer Science and Engineering, Nanyang Technological University Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University Singapore,Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Computer Science and Engineering, Nanyang Technological University Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101720092","display_name":"Kwok\u2010Yan Lam","orcid":"https://orcid.org/0000-0001-7479-7970"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kwok-Yan Lam","raw_affiliation_strings":["Nanyang Technological University Singapore,Computer Science and Engineering,Singapore","Computer Science and Engineering, Nanyang Technological University Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University Singapore,Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Computer Science and Engineering, Nanyang Technological University Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110373920"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.2976,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54441261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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":0.9700000286102295,"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":0.7385114431381226},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5739302635192871},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5164902210235596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5031387209892273},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48068103194236755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48000210523605347},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.44875630736351013},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.436906635761261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37682849168777466},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3534696102142334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385114431381226},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5739302635192871},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5164902210235596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031387209892273},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48068103194236755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48000210523605347},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.44875630736351013},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.436906635761261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37682849168777466},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3534696102142334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":1,"locations":[{"id":"doi:10.1109/wf-iot54382.2022.10152230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wf-iot54382.2022.10152230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G1908428699","display_name":null,"funder_award_id":"Tier 1 RG97/20,Tier 1 RG24/20,Tier 2 MOE2019-T2-1-176","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1569907127","https://openalex.org/W2004789217","https://openalex.org/W2129360799","https://openalex.org/W2296650210","https://openalex.org/W2398336962","https://openalex.org/W2721682741","https://openalex.org/W2739192055","https://openalex.org/W2795230330","https://openalex.org/W2804619907","https://openalex.org/W2807126412","https://openalex.org/W2891205112","https://openalex.org/W2963587345","https://openalex.org/W2964243274","https://openalex.org/W2971905065","https://openalex.org/W2980581183","https://openalex.org/W3025521275","https://openalex.org/W3031722511","https://openalex.org/W3103806448","https://openalex.org/W3120163087","https://openalex.org/W6628308797","https://openalex.org/W6631190155","https://openalex.org/W6676946368","https://openalex.org/W6697679221","https://openalex.org/W6754420807","https://openalex.org/W6768158615"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2026924879","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W2052388267","https://openalex.org/W2950647290","https://openalex.org/W1968481813","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"This":[0],"research":[1],"aims":[2],"to":[3,36,42,128],"make":[4],"metaverse":[5],"characters":[6],"more":[7],"realistic":[8],"by":[9,101],"adding":[10],"lip":[11,44,92],"animations":[12],"learnt":[13],"from":[14,80],"videos":[15,78],"in":[16,50,90,108],"the":[17,68,130],"wild.":[18],"To":[19],"achieve":[20],"this,":[21],"our":[22],"approach":[23],"<sup":[24,27],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[25,28],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[26,29],"Code":[30],"is":[31,35,70],"available":[32],"at":[33],"https://github.com/sweatybridge/text-to-anime":[34],"extend":[37],"Tacotron":[38],"2":[39],"text-to-speech":[40],"synthesizer":[41],"generate":[43],"movements":[45],"together":[46],"with":[47],"mel":[48],"spectrogram":[49],"one":[51],"pass.":[52],"The":[53],"encoder":[54,126],"and":[55,124,137],"gate":[56],"layer":[57],"weights":[58,127],"are":[59],"pre-trained":[60,125],"on":[61,72],"LJ":[62],"Speech":[63],"1.1":[64],"data":[65,83],"set":[66],"while":[67],"decoder":[69,87],"retrained":[71],"93":[73],"clips":[74],"of":[75,116,132],"TED":[76],"talk":[77],"extracted":[79,100],"LRS":[81],"3":[82],"set.":[84],"Our":[85],"novel":[86],"predicts":[88],"displacement":[89],"20":[91],"landmark":[93,104],"positions":[94],"across":[95],"time,":[96],"using":[97,111],"labels":[98],"automatically":[99],"OpenFace":[102],"2.0":[103],"predictor.":[105],"Training":[106],"converged":[107],"7":[109],"hours":[110],"less":[112],"than":[113],"5":[114],"minutes":[115],"video.":[117],"We":[118],"conducted":[119],"ablation":[120],"study":[121],"for":[122],"Pre/Post-Net":[123],"demonstrate":[129],"effectiveness":[131],"transfer":[133],"learning":[134],"between":[135],"audio":[136],"visual":[138],"speech":[139],"data.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}