{"id":"https://openalex.org/W2981921393","doi":"https://doi.org/10.1145/3343031.3350865","title":"3D Singing Head for Music VR","display_name":"3D Singing Head for Music VR","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981921393","doi":"https://doi.org/10.1145/3343031.3350865","mag":"2981921393"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350865","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002277899","display_name":"Chang Wen Chen","orcid":"https://orcid.org/0000-0002-6720-234X"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang Wen Chen","raw_affiliation_strings":["The State University of New York at Buffalo, Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103123751","display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"945","last_page":"952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T12290","display_name":"Human Motion and Animation","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8113000392913818},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.6715381145477295},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6190901398658752},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5929937362670898},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.5814975500106812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5734628438949585},{"id":"https://openalex.org/keywords/synchronicity","display_name":"Synchronicity","score":0.520010769367218},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5141082406044006},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.5034565329551697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49618157744407654},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47992807626724243},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47432559728622437},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36872464418411255},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.20474117994308472},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1139792799949646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113000392913818},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.6715381145477295},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6190901398658752},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5929937362670898},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.5814975500106812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5734628438949585},{"id":"https://openalex.org/C161394823","wikidata":"https://www.wikidata.org/wiki/Q1121101","display_name":"Synchronicity","level":2,"score":0.520010769367218},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5141082406044006},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.5034565329551697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49618157744407654},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47992807626724243},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47432559728622437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36872464418411255},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.20474117994308472},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1139792799949646},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350865","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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":44,"referenced_works":["https://openalex.org/W125358319","https://openalex.org/W170732776","https://openalex.org/W198124244","https://openalex.org/W205801897","https://openalex.org/W1499332833","https://openalex.org/W1643185111","https://openalex.org/W1916406603","https://openalex.org/W1927238661","https://openalex.org/W1981893831","https://openalex.org/W2004068758","https://openalex.org/W2014828600","https://openalex.org/W2019977809","https://openalex.org/W2026405130","https://openalex.org/W2047671930","https://openalex.org/W2048896221","https://openalex.org/W2059171115","https://openalex.org/W2115402659","https://openalex.org/W2123237149","https://openalex.org/W2129360799","https://openalex.org/W2132219293","https://openalex.org/W2133192850","https://openalex.org/W2140390665","https://openalex.org/W2157285372","https://openalex.org/W2263666797","https://openalex.org/W2301937176","https://openalex.org/W2395955767","https://openalex.org/W2398381847","https://openalex.org/W2402610474","https://openalex.org/W2460468435","https://openalex.org/W2541674938","https://openalex.org/W2567154071","https://openalex.org/W2598638573","https://openalex.org/W2604524889","https://openalex.org/W2623464795","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2750787464","https://openalex.org/W2904787397","https://openalex.org/W2922023437","https://openalex.org/W2950248412","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W4231334133"],"related_works":["https://openalex.org/W560220919","https://openalex.org/W4253386791","https://openalex.org/W2493643238","https://openalex.org/W2772409069","https://openalex.org/W2495789417","https://openalex.org/W3167834828","https://openalex.org/W2378998464","https://openalex.org/W2032995526","https://openalex.org/W2107636422","https://openalex.org/W4286779559"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,81],"real-time":[3],"3D":[4],"singing":[5],"head":[6,12,23,45],"system":[7,117],"to":[8,42,85,107,113],"enhance":[9],"the":[10,59,96,130],"talking":[11],"on":[13,91,132],"model":[14,46,89],"integrity,":[15],"keyframe":[16],"generation":[17],"and":[18,39,124],"song":[19,74,109],"synchronicity.":[20],"The":[21,73],"individual":[22],"appearance":[24],"meshes":[25,53],"are":[26,66,103],"first":[27],"obtained":[28],"by":[29,47,105],"matching":[30],"multi-view":[31],"visible":[32],"images":[33],"with":[34,49],"face":[35],"prior":[36],"for":[37,54],"accuracy,":[38],"then":[40],"used":[41],"reconstruct":[43],"entire":[44],"integrating":[48],"generic":[50],"internal":[51],"articulatory":[52],"efficiency.":[55],"After":[56],"embedding":[57],"physiology,":[58],"keyframes":[60,97],"of":[61,76,98],"each":[62],"phoneme-music":[63,100],"note":[64,101],"correspondence":[65],"substantially":[67],"synthesized":[68],"from":[69],"real":[70],"articulation":[71],"data.":[72,94,134],"synchronicity":[75],"articulators":[77],"is":[78],"learned":[79],"using":[80],"deep":[82],"neural":[83],"network":[84],"train":[86],"visual":[87],"co-articulation":[88],"(VCM)":[90],"parallel":[92],"audio-visual":[93],"Finally,":[95],"adjacent":[99],"correspondences":[102],"blended":[104],"VCM":[106],"produce":[108],"synchronized":[110],"animation.":[111],"Compared":[112],"state-of-the-art":[114],"baselines,":[115],"our":[116],"can":[118],"not":[119],"only":[120],"clearly":[121],"distinguish":[122],"phonemes":[123],"notes,":[125],"but":[126],"also":[127],"significantly":[128],"reduce":[129],"dependence":[131],"training":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}