{"id":"https://openalex.org/W4417113935","doi":"https://doi.org/10.1145/3769748.3773362","title":"AKITalk: Audio-Implicit Keypoints for Identity-Preserving Talking-Head Video Synthesis","display_name":"AKITalk: Audio-Implicit Keypoints for Identity-Preserving Talking-Head Video Synthesis","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417113935","doi":"https://doi.org/10.1145/3769748.3773362"},"language":null,"primary_location":{"id":"doi:10.1145/3769748.3773362","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769748.3773362","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773362","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773362","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041861318","display_name":"Riku Takahashi","orcid":"https://orcid.org/0009-0000-1126-0498"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Riku Takahashi","raw_affiliation_strings":["Hosei University, Tokyo, Japan and EQUES Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0000-1126-0498","affiliations":[{"raw_affiliation_string":"Hosei University, Tokyo, Japan and EQUES Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033531033","display_name":"Rongzhi Li","orcid":"https://orcid.org/0009-0003-0569-3619"},"institutions":[{"id":"https://openalex.org/I185088104","display_name":"Tokyo City University","ror":"https://ror.org/04dt6bw53","country_code":"JP","type":"education","lineage":["https://openalex.org/I185088104"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rongzhi Li","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan and EQUES Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0003-0569-3619","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan and EQUES Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I185088104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114135699","display_name":"Yuta Oshima","orcid":"https://orcid.org/0009-0006-6016-3866"},"institutions":[{"id":"https://openalex.org/I185088104","display_name":"Tokyo City University","ror":"https://ror.org/04dt6bw53","country_code":"JP","type":"education","lineage":["https://openalex.org/I185088104"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Oshima","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan and EQUES Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0006-6016-3866","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan and EQUES Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I185088104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109153093","display_name":"Shin-ya Kuno","orcid":"https://orcid.org/0009-0007-2911-8730"},"institutions":[{"id":"https://openalex.org/I185088104","display_name":"Tokyo City University","ror":"https://ror.org/04dt6bw53","country_code":"JP","type":"education","lineage":["https://openalex.org/I185088104"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sho Kuno","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan and EQUES Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0007-2911-8730","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan and EQUES Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I185088104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008003363","display_name":"Ryugo Morita","orcid":"https://orcid.org/0009-0007-6324-9291"},"institutions":[{"id":"https://openalex.org/I4210131443","display_name":"Center for Health and Gender Equity","ror":"https://ror.org/02wf58e57","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210131443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryugo Morita","raw_affiliation_strings":["EQUES Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0007-6324-9291","affiliations":[{"raw_affiliation_string":"EQUES Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210131443"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119050773","display_name":"Issey Sukeda","orcid":"https://orcid.org/0000-0002-8516-9707"},"institutions":[{"id":"https://openalex.org/I4210131443","display_name":"Center for Health and Gender Equity","ror":"https://ror.org/02wf58e57","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210131443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Issey Sukeda","raw_affiliation_strings":["EQUES Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8516-9707","affiliations":[{"raw_affiliation_string":"EQUES Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210131443"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34841888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6880999803543091,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6880999803543091,"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/T10860","display_name":"Speech and Audio Processing","score":0.14589999616146088,"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":0.08900000154972076,"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/generator","display_name":"Generator (circuit theory)","score":0.5634999871253967},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5227000117301941},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3465999960899353},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.3010999858379364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458999991416931},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5634999871253967},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4052000045776367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769748.3773362","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769748.3773362","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773362","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3769748.3773362","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769748.3773362","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773362","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417113935.pdf","grobid_xml":"https://content.openalex.org/works/W4417113935.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2738406145","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3186090335","https://openalex.org/W4310379947","https://openalex.org/W4312933868","https://openalex.org/W4386072021","https://openalex.org/W4390872297","https://openalex.org/W4402917159","https://openalex.org/W4409369524"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"talking-head":[1],"video":[2],"generation":[3],"methods":[4],"using":[5],"speech":[6],"audio":[7],"often":[8],"suffer":[9],"from":[10],"high":[11,69],"computational":[12,75],"costs":[13],"or":[14,60],"degraded":[15],"identity":[16,65],"preservation":[17],"due":[18],"to":[19],"reliance":[20],"on":[21,49],"external":[22],"super-resolution":[23],"models.":[24],"To":[25],"address":[26],"these":[27],"issues,":[28],"we":[29],"propose":[30],"a":[31,46],"lightweight":[32],"framework":[33],"that":[34,55],"efficiently":[35],"synthesizes":[36],"high-quality":[37],"videos":[38],"by":[39],"leveraging":[40],"audio-aware":[41],"implicit":[42],"3D":[43],"features":[44],"and":[45,64,77,90],"generator":[47],"trained":[48],"large-scale":[50],"data.":[51],"Experimental":[52],"results":[53],"demonstrate":[54],"our":[56],"method":[57],"achieves":[58],"comparable":[59],"superior":[61],"visual":[62,78],"quality":[63,79],"preservation,":[66],"while":[67],"ensuring":[68],"inference":[70],"efficiency.":[71],"This":[72],"balance":[73],"of":[74],"performance":[76],"suggests":[80],"broad":[81],"applicability":[82],"in":[83],"real-world":[84],"scenarios":[85],"such":[86],"as":[87],"social":[88],"media":[89],"online":[91],"education.":[92]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-08T00:00:00"}