{"id":"https://openalex.org/W4415538181","doi":"https://doi.org/10.1145/3746027.3754462","title":"KDTalker++: Controllable Talking Portrait Generation with Audio, Text, and Expression Editing","display_name":"KDTalker++: Controllable Talking Portrait Generation with Audio, Text, and Expression Editing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538181","doi":"https://doi.org/10.1145/3746027.3754462"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Chaolong Yang","orcid":"https://orcid.org/0000-0003-0396-6559"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chaolong Yang","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0396-6559","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016681207","display_name":"Yinuo Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinuo Guo","raw_affiliation_strings":["Duke Kunshan University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-6867-6944","affiliations":[{"raw_affiliation_string":"Duke Kunshan University, Suzhou, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047420717","display_name":"Kai Yao","orcid":"https://orcid.org/0000-0003-4623-0365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yao","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4623-0365","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588204","display_name":"Jing Yan","orcid":"https://orcid.org/0000-0003-2824-1431"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyao Yan","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2824-1431","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663021","display_name":"Jie Sun","orcid":"https://orcid.org/0000-0002-4654-3081"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Sun","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4654-3081","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026022035","display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Duke Kunshan University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3034-9639","affiliations":[{"raw_affiliation_string":"Duke Kunshan University, Suzhou, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15598035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13486","last_page":"13488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9732000231742859,"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/portrait","display_name":"Portrait","score":0.6947000026702881},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6500999927520752},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.6025999784469604},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32739999890327454},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3003000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958000063896179},{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.6947000026702881},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.6025999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.2766000032424927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8471152906","display_name":null,"funder_award_id":"No. 92370119, and 62376113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W3081492798"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"KDTalker++,":[3],"a":[4,13,23],"real-time":[5],"system":[6],"for":[7],"generating":[8],"talking":[9],"portrait":[10],"videos":[11],"from":[12],"single":[14],"image":[15],"using":[16],"audio":[17],"or":[18],"text":[19],"input.":[20],"Built":[21],"on":[22],"keypoint-based":[24],"spatiotemporal":[25],"diffusion":[26],"model,":[27],"it":[28],"adds":[29],"voice":[30],"cloning,":[31],"background":[32],"editing,":[33],"and":[34],"fine-grained":[35],"expression":[36],"control.":[37],"The":[38],"demo":[39],"is":[40,48],"available":[41,49],"at":[42,50],"https://kdtalker.com.":[43],"A":[44],"live":[45],"presentation":[46],"video":[47],"https://drive.google.com/file/d/1N4Ggu0Y32DTsV3mbKhXS4kGY6l2ZYKSp/view.":[51]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}
