Article(id=1329419803737043635, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329419793389695520, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202550560, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1753804800000, receivedDateStr=2025-07-30, revisedDate=1766505600000, revisedDateStr=2025-12-24, acceptedDate=1767715200000, acceptedDateStr=2026-01-07, onlineDate=1794887980636, onlineDateStr=2026-11-17, pubDate=1780243200000, pubDateStr=2026-06-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794887980636, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794887980636, creator=13701087609, updateTime=1794887980636, updator=13701087609, issue=Issue{id=1329419793389695520, tenantId=1146029695717560320, journalId=1324759914146529478, year='2026', volume='63', issue='6', pageStart='1377', pageEnd='1638', issueExtLink='null', onlineDate='null', pubDate='1780243200000', pubDateStr='2026-06-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794887978168, creator='13701087609', updateTime=1794892139295, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1329437246815580885, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329419793389695520, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1329437246815580886, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329419793389695520, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1451, endPage=1477, ext={EN=ArticleExt(id=1329419803942564533, articleId=1329419803737043635, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey of 2D Virtual Human Driving Technology Based on Deep Learning, columnId=1325489891789910943, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence, runingTitle=null, highlight=null, articleAbstract=
In recent years, the rapid advancement of deep learning and multimodal information fusion has significantly propelled the development of 2D virtual human driving technologies. Existing methods can generate highly realistic facial expressions and body movements for specified characters by leveraging diverse input data such as video, audio, facial cues, and poses. This remarkable progress offers substantial convenience for applications in virtual entertainment, online education, and intelligent interaction. This survey provides a systematic review of the current state and evolutionary trajectory of deep learning-based 2D virtual human driving methodologies. It thoroughly outlines the underlying principles and fundamental models commonly employed in this domain. The driving techniques are categorized and summarized according to both the target driving components (e.g., face, body) and the corresponding architectural frameworks, with a focused comparison and detailed elaboration of prominent methods developed in recent years. The research status and development prospects of holistic driving systems are also introduced. Furthermore, this survey delves into the critical technical challenges currently faced by the field, including generation realism, the quality of datasets, and the real-time performance of models. The aim of this survey is to offer a comprehensive technological overview and perspective for researchers in related fields, thereby contributing to the further advancement of this domain.
, authors=Lujia Yang, Xishi Zhou, Junchao Wang, Jinshan Zhang*, Tao Jin, Jianwei Yin, authorsList=Lujia Yang, Xishi Zhou, Junchao Wang, Jinshan Zhang, Tao Jin, Jianwei Yin, authorCompany=null, correspAuthors=Jinshan Zhang, authorNote=
born in 2001. Master candidate. Her main research interest includes talking head generation
born in 2003. Maser candidate. His main research interest includes generative artificial intelligence
born in 2000. Master candidate. His main research interest includes talking head generation
born in 1983. PhD, associate professor. His main research interest includes generative artificial intelligence
born in 1996. PhD, assistant professor. His main research interest includes multimodal understanding and generation
born in 1974. PhD, professor. His main research interests include metaverse and digital services, data science, and artificial intelligence
, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1329419806492701392, articleId=1329419803737043635, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于深度学习的2D虚拟人驱动技术综述, columnId=1325489892104483745, journalTitle=计算机研究与发展, columnName=人工智能, runingTitle=null, highlight=null, articleAbstract=
近年来,随着深度学习和多模态信息融合技术的快速发展,现有2D虚拟人驱动技术能够根据输入的视频、语音、表情和姿态等信息,驱动指定人物生成逼真的表情和动作,为虚拟娱乐、在线教育和智能交互等场景带来了极大的便利。综述系统地梳理了基于深度学习的2D虚拟人驱动技术的发展现状,概括了其原理与所采用的基础模型。同时,根据驱动部位及实现架构的不同,对驱动技术进行分类与概述,重点阐述并对比了近年来的主要方法,介绍了集成驱动的研究状况与发展前景。此外,还深入探讨了当前研究面临的生成逼真性、数据集质量、模型实时性等方面的技术挑战,旨在为相关领域研究人员提供较为全面的技术梳理与展望,帮助推动该领域的进一步发展。
, authors=杨璐嘉, 周溪石, 王俊超, 张金山*, 金涛, 尹建伟, authorsList=杨璐嘉, 周溪石, 王俊超, 张金山, 金涛, 尹建伟, authorCompany=null, correspAuthors=张金山, authorNote=
作者贡献声明
杨璐嘉负责文献调研并撰写驱动部分;周溪石负责撰写基础模型和集成部分;王俊超负责部分文献整理和论文勘误;张金山提出指导意见并修改论文;金涛对论文提出修改意见;尹建伟提出总体指导意见。
 |
2001年生。硕士研究生。主要研究方向为说话人生成 |
 |
2003年生。硕士研究生。主要研究方向为生成式人工智能 |
 |
2000年生。硕士研究生。主要研究方向为说话人生成 |
 |
1983年生。博士,副教授。主要研究方向为生成式人工智能 |
 |
1996年生。博士,助理研究员。主要研究方向为多模态理解与生成 |
 |
1974年生。博士,教授。主要研究方向为元宇宙与数字服务、数据科学、人工智能 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2026 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=JOjagONUE81CVqxytDHlKg==, magXml=C1bubcXPUFvQ500v7JyUpw==, pdfUrl=null, pdf=2+3vD20sKOtsdmRM9rQ52Q==, pdfFileSize=1900199, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=leiSjWyDy7yLbF9Y1t0CCQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=00Dn1iLdyUxjQ7V8HYrcmw==, mapNumber=null, fund=null)}, authors=[Author(id=1329419806815662805, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yanglujia@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419806895354583, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419806815662805, language=EN, stringName=Lujia Yang, firstName=Lujia, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106, bio={"content":"
born in 2001. Master candidate. Her main research interest includes talking head generation
"}, bioImg=null, bioContent=
born in 2001. Master candidate. Her main research interest includes talking head generation
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419806970852056, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419806815662805, language=CN, stringName=杨璐嘉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学软件学院 浙江宁波 315106, bio={"img":"NFyHmOCVdMWWShsvZ94zAg==","content":"
2001年生。硕士研究生。主要研究方向为说话人生成
"}, bioImg=NFyHmOCVdMWWShsvZ94zAg==, bioContent=
2001年生。硕士研究生。主要研究方向为说话人生成
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419806727582417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, xref=null, ext=[AuthorCompanyExt(id=1329419806735971026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106), AuthorCompanyExt(id=1329419806744359635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学软件学院 浙江宁波 315106)])]), Author(id=1329419807054738138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419807117652700, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807054738138, language=EN, stringName=Xishi Zhou, firstName=Xishi, middleName=null, lastName=Zhou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106, bio={"content":"
born in 2003. Maser candidate. His main research interest includes generative artificial intelligence
"}, bioImg=null, bioContent=
born in 2003. Maser candidate. His main research interest includes generative artificial intelligence
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419807184761565, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807054738138, language=CN, stringName=周溪石, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学软件学院 浙江宁波 315106, bio={"img":"igmWQx3Z1AvLJdzFEFS5/Q==","content":"
2003年生。硕士研究生。主要研究方向为生成式人工智能
"}, bioImg=igmWQx3Z1AvLJdzFEFS5/Q==, bioContent=
2003年生。硕士研究生。主要研究方向为生成式人工智能
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419806727582417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, xref=null, ext=[AuthorCompanyExt(id=1329419806735971026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106), AuthorCompanyExt(id=1329419806744359635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学软件学院 浙江宁波 315106)])]), Author(id=1329419807260259040, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419807335756514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807260259040, language=EN, stringName=Junchao Wang, firstName=Junchao, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106, bio={"content":"
born in 2000. Master candidate. His main research interest includes talking head generation
"}, bioImg=null, bioContent=
born in 2000. Master candidate. His main research interest includes talking head generation
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419807419642595, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807260259040, language=CN, stringName=王俊超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学软件学院 浙江宁波 315106, bio={"img":"NNOwG/HP+eHNJN6mWO0XUQ==","content":"
2000年生。硕士研究生。主要研究方向为说话人生成
"}, bioImg=NNOwG/HP+eHNJN6mWO0XUQ==, bioContent=
2000年生。硕士研究生。主要研究方向为说话人生成
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419806727582417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, xref=null, ext=[AuthorCompanyExt(id=1329419806735971026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106), AuthorCompanyExt(id=1329419806744359635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学软件学院 浙江宁波 315106)])]), Author(id=1329419807499334373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangjinshan@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329419807574831847, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807499334373, language=EN, stringName=Jinshan Zhang, firstName=Jinshan, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106, bio={"content":"
born in 1983. PhD, associate professor. His main research interest includes generative artificial intelligence
"}, bioImg=null, bioContent=
born in 1983. PhD, associate professor. His main research interest includes generative artificial intelligence
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419807650329320, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807499334373, language=CN, stringName=张金山, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=浙江大学软件学院 浙江宁波 315106, bio={"img":"XxHsDDLyyFnQojnb4heM5w==","content":"
1983年生。博士,副教授。主要研究方向为生成式人工智能
"}, bioImg=XxHsDDLyyFnQojnb4heM5w==, bioContent=
1983年生。博士,副教授。主要研究方向为生成式人工智能
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419806727582417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, xref=null, ext=[AuthorCompanyExt(id=1329419806735971026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106), AuthorCompanyExt(id=1329419806744359635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学软件学院 浙江宁波 315106)])]), Author(id=1329419807717438186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419807826490092, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807717438186, language=EN, stringName=Tao Jin, firstName=Tao, middleName=null, lastName=Jin, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106, bio={"content":"
born in 1996. PhD, assistant professor. His main research interest includes multimodal understanding and generation
"}, bioImg=null, bioContent=
born in 1996. PhD, assistant professor. His main research interest includes multimodal understanding and generation
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419807889404653, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807717438186, language=CN, stringName=金涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学软件学院 浙江宁波 315106, bio={"img":"liYNHlgnXefjyQW9u6mUng==","content":"
1996年生。博士,助理研究员。主要研究方向为多模态理解与生成
"}, bioImg=liYNHlgnXefjyQW9u6mUng==, bioContent=
1996年生。博士,助理研究员。主要研究方向为多模态理解与生成
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419806727582417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, xref=null, ext=[AuthorCompanyExt(id=1329419806735971026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106), AuthorCompanyExt(id=1329419806744359635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学软件学院 浙江宁波 315106)])]), Author(id=1329419807956513519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419808027816689, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807956513519, language=EN, stringName=Jianwei Yin, firstName=Jianwei, middleName=null, lastName=Yin, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106, bio={"content":"
born in 1974. PhD, professor. His main research interests include metaverse and digital services, data science, and artificial intelligence
"}, bioImg=null, bioContent=
born in 1974. PhD, professor. His main research interests include metaverse and digital services, data science, and artificial intelligence
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419808086536946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, authorId=1329419807956513519, language=CN, stringName=尹建伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=浙江大学软件学院 浙江宁波 315106, bio={"img":"vWcFWInoaSf18EDEpsVQqg==","content":"
1974年生。博士,教授。主要研究方向为元宇宙与数字服务、数据科学、人工智能
"}, bioImg=vWcFWInoaSf18EDEpsVQqg==, bioContent=
1974年生。博士,教授。主要研究方向为元宇宙与数字服务、数据科学、人工智能
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419806727582417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, xref=null, ext=[AuthorCompanyExt(id=1329419806735971026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106), AuthorCompanyExt(id=1329419806744359635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学软件学院 浙江宁波 315106)])])], keywords=[Keyword(id=1329419808203977459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, orderNo=1, keyword=virtual digital human), Keyword(id=1329419808266892020, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, orderNo=2, keyword=talking head generation), Keyword(id=1329419808325612277, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, orderNo=3, keyword=multi-modal fusion), Keyword(id=1329419808392721142, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, orderNo=4, keyword=video generation), Keyword(id=1329419808476607223, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, orderNo=5, keyword=deep learning), Keyword(id=1329419808543716088, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, orderNo=1, keyword=虚拟数字人), Keyword(id=1329419808619213561, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, orderNo=2, keyword=说话人生成), Keyword(id=1329419808673739514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, orderNo=3, keyword=多模态融合), Keyword(id=1329419808732459771, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, orderNo=4, keyword=视频生成), Keyword(id=1329419808824734460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, orderNo=5, keyword=深度学习)], refs=[Reference(id=1329419810695394065, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei Liyi, Lefebvre S, Kwatra V, et al. State of the art in example-based texture synthesis[J]. Eurographics 2009, State of the Art Reports, 2009: 93−117, articleTitle=null, refAbstract=null), Reference(id=1329419810758308626, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[C]//Proc of the 27th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2014: 2672−2680, articleTitle=null, refAbstract=null), Reference(id=1329419810821223187, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models[J]. Advances in Neural Information Processing Systems, 2020, 33: 6840−6851, articleTitle=null, refAbstract=null), Reference(id=1329419810875749140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Jiaming, Meng Chenlin, Ermon S. Denoising diffusion implicit models[J]. arXiv preprint, arXiv: 2010.02502, 2020, articleTitle=null, refAbstract=null), Reference(id=1329419810947052309, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=宋一飞, 张炜, 陈智能, 等. 数字说话人视频生成综述[J]. 计算机辅助设计与图形学学报, 2023, 35(10): 1457−1468, articleTitle=null, refAbstract=null), Reference(id=1329419811009966870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Yifei, Zhang Wei, Chen Zhineng, et al. A survey on talking head generation[J]. Journal of Computer-Aided Design & Computer Graphics, 2023, 35(10): 1457−1468 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419811077075735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=包仪华, 涂子奇, 骆乐, 等. 数字人面部表情迁移: 从人脸表示到表情迁移综述[J]. 计算机辅助设计与图形学学报, 2025, 37(8): 1283−1299, articleTitle=null, refAbstract=null), Reference(id=1329419811156767512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Bao Yihua, Tu Ziqi, Luo Le, et al. Digital human facial expression transfer: A review from face representation to expression transfer[J]. Journal of Computer-Aided Design & Computer Graphics, 2025, 37(8): 1283−1299 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419811232264985, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2017: 6000−6010, articleTitle=null, refAbstract=null), Reference(id=1329419811353899802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren Yi, Liu Jinglin, Zhao Zhou. Portaspeech: Portable and high-quality generative text-to-speech[J]. Advances in Neural Information Processing Systems, 2021, 34: 13963−13974, articleTitle=null, refAbstract=null), Reference(id=1329419811421008667, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Kingma D P, Welling M. Auto-encoding variational Bayes[C/OL]//Proc of the 2nd Int Conf on Learning Representations. 2014[2025-07-04]. https://openreview.net/forum?id=33X9fd2-9FyZd, articleTitle=null, refAbstract=null), Reference(id=1329419811488117532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation[C]//Proc of the 18th Int Conf on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 2015: 234−241, articleTitle=null, refAbstract=null), Reference(id=1329419811580392221, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Peebles W, Xie S. Scalable diffusion models with transformers[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 4195−4205, articleTitle=null, refAbstract=null), Reference(id=1329419811655889695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Suwajanakorn S, Seitz S M, Kemelmacher-Shlizerman I. Synthesizing Obama: Learning lip sync from audio[J]. ACM Transactions on Graphics, 2017, 36(4): 95: 1–95: 13, articleTitle=null, refAbstract=null), Reference(id=1329419811722998560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Jamaludin A, Chung J S, Zisserman A. You said that?: Synthesising talking faces from audio[J]. International Journal of Computer Vision, 2019, 127(11): 1767−1779, articleTitle=null, refAbstract=null), Reference(id=1329419811785913121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Hang, Liu Yu, Liu Ziwei, et al. Talking face generation by adversarially disentangled audio-visual representation[C]//Proc of the 33rd AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2019: 9299−9306, articleTitle=null, refAbstract=null), Reference(id=1329419811844633378, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Yang, Han Xintong, Shechtman E, et al. MakeitTalk: Speaker-aware talking-head animation[J]. ACM Transactions on Graphics, 2020, 39(6): 1−15, articleTitle=null, refAbstract=null), Reference(id=1329419811911742243, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Prajwal K, Mukhopadhyay R, Namboodiri V P, et al. A lip sync expert is all you need for speech to lip generation in the wild[C]//Proc of the 28th ACM Int Conf on Multimedia. New York: ACM, 2020: 484−492, articleTitle=null, refAbstract=null), Reference(id=1329419811995628324, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jian, Qian Xinyuan, Zhang Malu, et al. Seeing what you said: Talking face generation guided by a lip reading expert[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 14653−14662, articleTitle=null, refAbstract=null), Reference(id=1329419812058542885, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhimeng, Hu Zhipeng, Deng Wenjin, et al. DINet: Deformation inpainting network for realistic face visually dubbing on high resolution video[C]//Proc of the 37th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2023: 3543−3551, articleTitle=null, refAbstract=null), Reference(id=1329419812121457446, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=魏清杨, 徐树公. 基于草图引导的少样本说话人视频生成算法研究[J]. 计算机测量与控制, 2024, 32(10): 236−242, 249, articleTitle=null, refAbstract=null), Reference(id=1329419812184372007, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei Qingyang, Xu Shugong. Research on few-shot speaker video generation algorithm guided by sketches[J]. Computer Measurement & Control, 2024, 32(10): 236−242, 249 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419812243092264, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=陈诗航, 孙玉宝. 基于模态仿射融合的语音控制说话人脸视频对抗生成[J/OL]. 计算机工程[2025-07-04]. https: //www.ecice06.com/CN/10.19678/j.issn.1000-3428.0069992, articleTitle=null, refAbstract=null), Reference(id=1329419812306006825, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Shihang, Sun Yubao. Voice-controlled face video adversarial generation based on modal affine fusion[J/OL]. Computer Engineering, [2025-07-04]. https://www.ecice06.com/CN/10.19678/j.issn.1000-3428.0069992(in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419812368921386, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=郭星星, 肖雁南, 温佩芝, 等. 基于注意力机制的音频驱动数字人脸视频生成方法[J/OL]. 计算机科学, 2025: 1−11. [2025-07-04]. http: //kns.cnki.net/kcms/detail/50.1075.TP.20250317.1902.040, articleTitle=null, refAbstract=null), Reference(id=1329419812423447339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Xingxing, Xiao Yannan, Wen Peizhi, et al. Audio driven digital facial video generation method based on attention mechanism[J/OL]. Computer Science, 2025: 1−11. [2025-07-04]. http://kns.cnki.net/kcms/detail/50.1075.TP.20250317.1902.040 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419812486361900, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Siarohin A, Lathuilière S, Tulyakov S, et al. First order motion model for image animation[J/OL]. Advances in Neural Information Processing Systems, 2019, 32[2025-07-04]. https://proceedings.neurips.cc/paper/2019/hash/31c0b36aef265d9221af80872ceb62f9-Abstract.html, articleTitle=null, refAbstract=null), Reference(id=1329419812540887853, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Ha S, Kersner M, Kim B, et al. MarioNETte: Few-shot face reenactment preserving identity of unseen targets[C]//Proc of the 34th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2020: 10893−10900, articleTitle=null, refAbstract=null), Reference(id=1329419812599608110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=年福东, 王文涛, 王妍, 等. 基于关键点表示的语音驱动说话人脸视频生成[J]. 模式识别与人工智能, 2021, 34(6): 572−580, articleTitle=null, refAbstract=null), Reference(id=1329419812654134063, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Nian Fudong, Wang Wentao, Wang Yan, et al. Speech driven talking face video generation via landmarks representation[J]. Pattern Recognition and Artificial Intelligence, 2021, 34(6): 572−580 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419812721242928, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Tingchun, Mallya A, Liu Mingyu. One-shot free-view neural talking-head synthesis for video conferencing[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 10039−10049, articleTitle=null, refAbstract=null), Reference(id=1329419812788351793, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Qiulin, Zhang Lu, Li Bo. SAFA: Structure aware face animation[C]//Proc of the 2021 Int Conf on 3D Vision. Piscataway, NJ: IEEE, 2021: 679−688, articleTitle=null, refAbstract=null), Reference(id=1329419812842877746, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Hong Fating, Zhang Longhao, Shen Li, et al. Depth-aware generative adversarial network for talking head video generation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 3397−3406, articleTitle=null, refAbstract=null), Reference(id=1329419812901598003, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Jian, Zhang Hui. Thin-plate spline motion model for image animation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 3657−3666, articleTitle=null, refAbstract=null), Reference(id=1329419812968706868, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Tao Jiale, Wang Biao, Xu Borun, et al. Structure-aware motion transfer with deformable anchor model[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 3637−3646, articleTitle=null, refAbstract=null), Reference(id=1329419813031621429, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Feida, Zhu Junwei, Chu Wenqing, et al. HifiHead: One-shot high fidelity neural head synthesis with 3D control[C/OL]//Proc of the 31st Int Joint Conf on Artificial Intelligence. 2022: 1750−1756. [2025-07-04]. https://doi.org/10.24963/ijcai.2022/244, articleTitle=null, refAbstract=null), Reference(id=1329419813090341686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Bowen, Qi Chenyang, Zhang Pan, et al. MetaPortrait: Identity-preserving talking head generation with fast personalized adaptation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 22096−22105, articleTitle=null, refAbstract=null), Reference(id=1329419813153256247, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jianrong, Zhao Yaxin, Liu Li, et al. Emotional talking head generation based on memory sharing and attention-augmented networks[J]. arXiv preprint, arXiv: 2306.03594, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419813207782200, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Jianzhu, Zhang Dingyun, Liu Xiaoqing, et al. LivePortrait: Efficient portrait animation with stitching and retargeting control[J]. arXiv preprint, arXiv: 2407.03168, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419813266502457, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Siarohin A, Lathuilière S, Tulyakov S, et al. Animating arbitrary objects via deep motion transfer[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 2377−2386, articleTitle=null, refAbstract=null), Reference(id=1329419813337805626, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Doukas M C, Zafeiriou S, Sharmanska V. HeadGAN: One-shot neural head synthesis and editing[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 14398−14407, articleTitle=null, refAbstract=null), Reference(id=1329419813404914491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Wayne, Zhang Yunxuan, Li Cheng, et al. ReenactGAN: Learning to reenact faces via boundary transfer[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 603−619, articleTitle=null, refAbstract=null), Reference(id=1329419813467829052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Hang, Sun Yasheng, Wu Wayne, et al. Pose-controllable talking face generation by implicitly modularized audio-visual representation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 4176−4186, articleTitle=null, refAbstract=null), Reference(id=1329419813526549309, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yaohui, Yang Di, Bremond F, et al. Latent image animator: Learning to animate images via latent space navigation[C/OL]//Proc of the Int Conf on Learning Representations. 2022[2025-07-04]. https://inria.hal.science/hal-03714584/document, articleTitle=null, refAbstract=null), Reference(id=1329419813673349950, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Bounareli S, Tzelepis C, Argyriou V, et al. StyleMask: Disentangling the style space of styleGAN2 for neural face reenactment[C]//Proc of the 17th IEEE Int Conf on Automatic Face and Gesture Recognition. Piscataway, NJ: IEEE, 2023: 1−8, articleTitle=null, refAbstract=null), Reference(id=1329419813744653119, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Hong Fating, Xu Dan. Implicit identity representation conditioned memory compensation network for talking head video generation[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 23062−23072, articleTitle=null, refAbstract=null), Reference(id=1329419813820150592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Bounareli S, Tzelepis C, Argyriou V, et al. DiffusionAct: Controllable diffusion autoencoder for one-shot face reenactment[J]. arXiv preprint, arXiv: 2403.17217, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419813933396801, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie You, Xu Hongyi, Song Guoxian, et al. X-Portrait: Expressive portrait animation with hierarchical motion attention[C]//Proc of the ACM SIGGRAPH 2024 Conf. New York: ACM, 2024: 1−11, articleTitle=null, refAbstract=null), Reference(id=1329419814013088578, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Zeng Bohan, Liu Xuhui, Gao Sicheng, et al. Face animation with an attribute-guided diffusion model[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 628−637, articleTitle=null, refAbstract=null), Reference(id=1329419814092780355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Shuai, Zhao Wenliang, Meng Zibin, et al. Difftalk: Crafting diffusion models for generalized audio-driven portraits animation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 1982−1991, articleTitle=null, refAbstract=null), Reference(id=1329419814159889220, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Chenpeng, Chen Qi, He Tianyu, et al. DAE-Talker: High fidelity speech-driven talking face generation with diffusion autoencoder[C]//Proc of the 31st ACM Int Conf on Multimedia. New York: ACM, 2023: 4281−4289, articleTitle=null, refAbstract=null), Reference(id=1329419814226998085, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Ken, Seneviratne S, Wang Wei, et al. AniFaceDiff: High-fidelity face reenactment via facial parametric conditioned diffusion models[J]. arXiv preprint, arXiv: 2406.13272, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419814302495558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Yue, Liu Hongyue, Wang Hongfa, et al. Follow-Your-Emoji: Fine-controllable and expressive freestyle portrait animation[J]. arXiv preprint, arXiv: 2406.01900, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419814369604423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Sicheng, Chen Guojun, Guo Yuxiao, et al. VASA−1: Lifelike audio-driven talking faces generated in real time[J]. arXiv preprint, arXiv: 2404.10667, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419814436713288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Zhiyaun, Cao Jiaojiong, Chen Zhiquan, et al. EchoMimic: Lifelike audio-driven portrait animations through editable landmark conditions[J]. arXiv preprint, arXiv: 2407.08136, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419814537376585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Tian Linrui, Wang Qi, Zhang Bang, et al. EMO: Emote portrait alive generating expressive portrait videos with audio2video diffusion model under weak conditions[C]//Proc of the European Conf on Computer Vision. Berlin: Springer, 2024: 244−260, articleTitle=null, refAbstract=null), Reference(id=1329419814600291146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Mingwang, Li Hui, Su Qingkun, et al. Hallo: Hierarchical audio-driven visual synthesis for portrait image animation[J]. arXiv preprint, arXiv: 2406.08801, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419814679982923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Jianwei, Liang Chao, Yang Jiaqi, et al. Loopy: Taming audio-driven portrait avatar with long-term motion dependency[J]. arXiv preprint, arXiv: 2409.02634, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419814742897484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Cui Jiahao, Li Hui, Yao Yao, et al. Hallo2: Long-duration and high-resolution audio-driven portrait image animation[J]. arXiv preprint, arXiv: 2410.07718, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419814805812045, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Yudong, Chen Keyu, Liang Sen, et al. Ad-NeRF: Audio driven neural radiance fields for talking head synthesis[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 5784−5794, articleTitle=null, refAbstract=null), Reference(id=1329419814868726606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xian, Xu Yinghao, Wu Qianyi, et al. Semantic-aware implicit neural audio-driven video portrait generation[J]. arXiv preprint, arXiv: 2201.07786, 2022, articleTitle=null, refAbstract=null), Reference(id=1329419815036498767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Shuai, Li Wanhua, Zhu Zheng, et al. Learning dynamic facial radiance fields for few-shot talking head synthesis[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 666−682, articleTitle=null, refAbstract=null), Reference(id=1329419815099413328, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Zhenhui, Jiang Ziyue, Ren Yi, et al. GeneFace: Generalized and high-fidelity audio-driven 3D talking face synthesis[J]. arXiv preprint, arXiv: 2301.13430, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419815166522193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Jianxing, Wang Kaisiyuan, Zhou Hang, et al. Real-time neural radiance talking portrait synthesis via audio-spatial decomposition[J]. arXiv preprint, arXiv: 2211.12368, 2022, articleTitle=null, refAbstract=null), Reference(id=1329419815237825362, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Jianhe, Zhang Jiawei, Bai Xiao, et al. Efficient region-aware neural radiance fields for high-fidelity talking portrait synthesis[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 7568−7578, articleTitle=null, refAbstract=null), Reference(id=1329419815300739923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Yao Shunyu, Zhong Ruizhe, Yan Yichao, et al. Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering[J]. arXiv preprint, arXiv: 2201.00791, 2022, articleTitle=null, refAbstract=null), Reference(id=1329419815380431701, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Weichuang, Zhang Longhao, Wang Dong, et al. One-shot high-fidelity talking-head synthesis with deformable neural radiance field[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 17969−17978, articleTitle=null, refAbstract=null), Reference(id=1329419815451734870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Zhenhui, He Jinzheng, Jiang Ziyue, et al. GeneFace++: Generalized and stable real-time audio driven 3D talking face generation[J]. arXiv preprint, arXiv: 2305.00787, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419815527232343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Zhenhui, Zhong Tianyun, Ren Yi, et al. Real3d-Portrait: One-shot realistic 3D talking portrait synthesis[J]. arXiv preprint, arXiv: 2401.08503, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419815598535512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Cho K, Lee J, Yoon H, et al. GaussianTalker: Real-time high-fidelity talking head synthesis with audio-driven 3D Gaussian splatting[J]. arXiv preprint, arXiv: 2404.16012, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419815665644377, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Bo, Hu Shoukang, Chen Qi, et al. GSTalker: Real-time audio-driven talking face generation via deformable Gaussian splatting[J]. arXiv preprint, arXiv: 2404.19040, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419815736947546, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Hongyun, Qu Zhan, Yu Qihang, et al. GaussianTalker: Speaker-specific talking head synthesis via 3D Gaussian splatting[C]//Proc of the 32nd ACM Int Conf on Multimedia. New York: ACM, 2024: 3548−3557, articleTitle=null, refAbstract=null), Reference(id=1329419815808250715, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Ziqiao, Hu Wentao, Ma Junyuan, et al. SyncTalk++: High-fidelity and efficient synchronized talking heads synthesis using Gaussian splatting[J]. arXiv preprint, arXiv: 2506.14742, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419815866970972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Fan Yingruo, Gao Chenliang, Fu Ying, et al. FaceFormer: Speech-driven 3D facial animation with transformers[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 18749−18758, articleTitle=null, refAbstract=null), Reference(id=1329419815938274141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Richard A, Nguyen P, Corcoran P, et al. MeshTalk: 3D face animation from speech using cross-modality disentanglement[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 1153−1162, articleTitle=null, refAbstract=null), Reference(id=1329419816022160222, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Xing Jinbo, Lei Xiao, Zhang Wei, et al. CodeTalker: Speech-driven 3D facial animation with discrete motion prior[C/OL]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023[2025-07-04]. https://doi.org/10.48550/arXiv.2301.02379, articleTitle=null, refAbstract=null), Reference(id=1329419816093463391, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim S, Lee C, Son G, et al. MultiTalk: Enhancing 3D talking head generation across languages with multilingual video dataset[J]. arXiv preprint, arXiv: 2406.14272, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419816189932384, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Chu Xuangeng, Goswami N, Cui Ziteng, et al. ARTalk: Speech-driven 3D head animation via autoregressive model[J]. arXiv preprint, arXiv: 2502.20323, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419816257041249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhen Dingcheng, Yin Shunshun, Qin Shiyang, et al. Teller: Real-time streaming audio-driven portrait animation with autoregressive motion generation[J]. arXiv preprint, arXiv: 2503.18429, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419816324150114, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Mohan, Bai Yalong, Zhang Wei, et al. Responsive listening head generation: A benchmark dataset and baseline[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 124−142, articleTitle=null, refAbstract=null), Reference(id=1329419816420619107, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Mohan, Bai Yalong, Zhang Wei, et al. Interactive conversational head generation[J]. arXiv preprint, arXiv: 2307.02090, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419816504505188, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Chang Zhigang, Wang Bin, Liu Feng, et al. Hierarchical semantic perceptual listener head video generation: A high-performance pipeline[C]//Proc of the 31st ACM Int Conf on Multimedia. New York: ACM, 2023: 9581−9585, articleTitle=null, refAbstract=null), Reference(id=1329419816580002661, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Miao Liu, Jing Wang, Xinyuan Qian, et al. ListenFormer: Responsive listening head generation with non-autoregressive transformers[C]//Proc of the 32nd ACM Int Conf on Multimedia. New York: ACM, 2024: 7094−7103, articleTitle=null, refAbstract=null), Reference(id=1329419816647111526, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Yongming, Zhang Longhao, Rong Zhengkun, et al. INFP: Audio-driven interactive head generation in dyadic conversations[J]. arXiv preprint, arXiv: 2412.04037, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419816718414695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Kaisiyuan, Wu Qianyi, Song Linsen, et al. MEAD: A large-scale audio-visual dataset for emotional talking-face generation[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 700−717, articleTitle=null, refAbstract=null), Reference(id=1329419816785523560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Sinha S, Biswas S, Yadav R, et al. Emotion-controllable generalized talking face generation[J]. arXiv preprint, arXiv: 2205.01155, 2022, articleTitle=null, refAbstract=null), Reference(id=1329419816852632425, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Xinya, Zhou Hang, Wang Kaisiyuan, et al. EAMM: One-shot emotional talking face via audio-based emotion-aware motion model[C]//Proc of the 2022 ACM SIGGRAPH Conf. New York: ACM, 2022: 1−10, articleTitle=null, refAbstract=null), Reference(id=1329419816923935594, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Drobyshev N, Casademunt A B, Vougioukas K, et al. EMOPortraits: Emotion-enhanced multimodal one-shot head avatars[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 8498−8507, articleTitle=null, refAbstract=null), Reference(id=1329419816986850155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Gan Yuan, Yang Zongxin, Yue Xihang, et al. Efficient emotional adaptation for audio-driven talking-head generation[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 22634−22645, articleTitle=null, refAbstract=null), Reference(id=1329419817045570412, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Chenxu, Wang Chao, Zhang Jianfeng, et al. Dream-Talk: Diffusion-based realistic emotional audio-driven method for single image talking face generation[J]. arXiv preprint, arXiv: 2312.13578, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419817108484973, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=吕天, 温玉辉, 孙志尧, 等. 基于纹理与几何解耦的说话人视频连续情感编辑模型[J]. 中国科学: 信息科学, 2023, 53(12): 2423−2439, articleTitle=null, refAbstract=null), Reference(id=1329419817167205230, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Lv Tian, Wen Yuhui, Sun Zhiyao, et al. A speaker video continuous emotion editing model based on texture and geometry decoupling[J]. SCIENTIA SINICA Informations, 2023, 53(12): 2423−2439 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419817242702703, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Haozhe, Jia Jia, Wang Haoyu, et al. Imitating arbitrary talking style for realistic audio driven talking face synthesis[C]//Proc of the 29th ACM Int Conf on Multimedia. New York: ACM, 2021: 1478−1486, articleTitle=null, refAbstract=null), Reference(id=1329419817314005872, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang Borong, Pan Yan, Guo Zhizhi, et al. Expressive talking head generation with granular audio-visual control[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 3387−3396, articleTitle=null, refAbstract=null), Reference(id=1329419817376920433, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Yifeng, Wang Suzhen, Hu Zhipeng, et al. StyleTalk: One-shot talking head generation with controllable speaking styles[C]//Proc of the 37th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2023: 1896−1904, articleTitle=null, refAbstract=null), Reference(id=1329419817448223602, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Shuai, Ji Bin, Ding Yu, et al. Say anything with any style[C]//Proc of the 38th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2024: 5088−5096, articleTitle=null, refAbstract=null), Reference(id=1329419817502749555, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Shuai, Ji Bin, Pan Ye. Style2Talker: High-resolution talking head generation with emotion style and art style[C]//Proc of the 38th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2024: 5079−5087, articleTitle=null, refAbstract=null), Reference(id=1329419817565664116, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Suzhzen, Ma Yifeng, Ding Yu, et al. StyleTalk++: A unified framework for controlling the speaking styles of talking heads[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(6): 4331−4347, articleTitle=null, refAbstract=null), Reference(id=1329419817628578677, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Liqian, Jia Xu, Sun Qianru, et al. Pose guided person image generation[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2017: 406−416, articleTitle=null, refAbstract=null), Reference(id=1329419817699881846, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Lassner C, Pons-Moll G, Gehler P V. A generative model of people in clothing[C]//Proc of the IEEE Int Conf on Computer vision. Piscataway, NJ: IEEE, 2017: 853−862, articleTitle=null, refAbstract=null), Reference(id=1329419817775379319, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Liqian, Sun Qianru, Georgoulis S, et al. Disentangled person image generation[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 99−108, articleTitle=null, refAbstract=null), Reference(id=1329419817897014136, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Joo D, Kim D, Kim J. Generating a fusion image: One’s identity and another’s shape[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 1635−1643, articleTitle=null, refAbstract=null), Reference(id=1329419817976705913, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=De Bem R, Ghosh A, Boukhayma A, et al. A conditional deep generative model of people in natural images[C]//Proc of the 2019 IEEE Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2019: 1449−1458, articleTitle=null, refAbstract=null), Reference(id=1329419818068980602, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Balakrishnan G, Zhao A, Dalca A V, et al. Synthesizing images of humans in unseen poses[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 8340−8348, articleTitle=null, refAbstract=null), Reference(id=1329419818136089467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren Yurui, Fan Xiaoqing, Li Ge, et al. Neural texture extraction and distribution for controllable person image synthesis[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 13535−13544, articleTitle=null, refAbstract=null), Reference(id=1329419818207392636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Bhunia A K, Khan S, Cholakkal H, et al. Person image synthesis via denoising diffusion model[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 5968−5976, articleTitle=null, refAbstract=null), Reference(id=1329419818362581885, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Tingchun, Liu Mingyu, Zhu Junyan, et al. Video-to-video synthesis[J]. arXiv preprint, arXiv: 1808.06601, 2018, articleTitle=null, refAbstract=null), Reference(id=1329419818425496446, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Tingchun, Liu Mingyu, Tao A, et al. Few-shot video-to-video synthesis[J]. arXiv preprint, arXiv: 1910.12713, 2019, articleTitle=null, refAbstract=null), Reference(id=1329419818492605311, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Wen, Piao Zhixin, Tu Zhi, et al. Liquid-Warping-GAN with attention: A unified framework for human image synthesis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(9): 5114−5132, articleTitle=null, refAbstract=null), Reference(id=1329419818563908480, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Chan C, Ginosar S, Zhou Tinghui, et al. Everybody dance now[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 5933−5942, articleTitle=null, refAbstract=null), Reference(id=1329419818651988865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Karras J, Holynski A, Wang Tingchun, et al. DreamPose: Fashion image-to-video syn thesis via stable diffusion[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 22623−22633, articleTitle=null, refAbstract=null), Reference(id=1329419818706514818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Li, Gao Xin, Zhang Peng, et al. AnimateAnyone: Consistent and controllable image-to-video synthesis for character animation[J]. arXiv preprint, arXiv: 2311.17117, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419818769429379, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Zhongcong, Zhang Jianfeng, Liew Jun Hao, et al. MagicAnimate: Temporally consistent human image animation using diffusion model[J]. arXiv preprint, arXiv: 2311.16498, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419818823955332, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Tan, Li Linjie, Lin K, et al. DisCo: Disentangled control for realistic human dance generation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 9326−9336, articleTitle=null, refAbstract=null), Reference(id=1329419818886869893, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Shenhao, Chen J L, Dai Zuozhou, et al. Champ: Controllable and consistent human image animation with 3D parametric guidance[J]. arXiv preprint, arXiv: 2403.14781, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419818953978758, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yuang, Gu Jiaxi, Wang Liwen, et al. MimicMotion: High-quality human motion video generation with confidence-aware pose guidance[J]. arXiv preprint, arXiv: 2406.19680, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419819021087623, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Yue, He Yingqing, Cun Xiaodong, et al. Follow Your Pose: Pose-guided text-to-video generation using pose-free videos[C]//Proc of the 38th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2024: 4117−4125, articleTitle=null, refAbstract=null), Reference(id=1329419819088196488, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yabo, Wei Yuxiang, Jiang Dongsheng, et al. Controlvideo: Training-free controllable text-to-video generation[J]. arXiv preprint, arXiv: 2305.13077, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419819205637001, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Qin Bosheng, Ye Wentao, Yu Qifan, et al. DancingAvatar: Pose and text-guided human motion videos synthesis with image diffusion model[J]. arXiv preprint, arXiv: 2308.07749, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419819264357258, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Mengyang, Liu Jinlin, Yu Kai, et al. DreaMoving: A human dance video generation framework based on diffusion models[J]. arXiv preprint, arXiv: 2312.05107, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419819373409163, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Ginosar S, Bar A, Kohavi G, et al. Learning individual styles of conversational gesture[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 3497−3506, articleTitle=null, refAbstract=null), Reference(id=1329419819453100940, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Liao Miao, Zhang Sibo, Wang Peng, et al. Speech2video synthesis with 3D skeleton regularization and expressive body poses[C/OL]//Proc of the 15th Asian Conf on Computer Vision. 2020: 308−323. [2025-07-04]. https://dl.acm.org/doi/abs/10.1007/978-3-030-69541-5_19, articleTitle=null, refAbstract=null), Reference(id=1329419819578930062, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=122, authorNames=null, journalName=null, refType=null, unstructuredReference=Corona E, Zanfir A, Bazavan E G, et al. VLOGGER: Multimodal diffusion for embodied avatar synthesis[J]. arXiv preprint, arXiv: 2403.08764, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419819654427535, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=123, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Gaojie, Jiang Jianwen, Liang Chao, et al. CYBERHOST: Taming audio-driven avatar diffusion model with region codebook attention[J]. arXiv preprint, arXiv: 2409.01876, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419819729925008, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=124, authorNames=null, journalName=null, refType=null, unstructuredReference=Habibie I, Holden D, Tzionas D, et al. Learning speech-driven 3D conversational gestures from video[C]//Proc of the 21st ACM Int Conf on Intelligent Virtual Agents. New York: ACM, 2021: 101–108, articleTitle=null, refAbstract=null), Reference(id=1329419819797033873, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=125, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi Hongwei, Li Xueting, Yu Chen, et al. Generating holistic 3D human motion from speech[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 469−480, articleTitle=null, refAbstract=null), Reference(id=1329419819872531346, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=120, rfOrder=126, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Junming, Wu Yinghao, Ma Zhaofan, et al. DiffSHEG: A diffusion-based approach for real-time speech-driven holistic 3D expression and gesture generation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 7352−7361, articleTitle=null, refAbstract=null), Reference(id=1329419819952223123, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=121, rfOrder=127, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo Yuxuan, Rong Zhengkun, Wang Lizhen, et al. DreamActor-M1: Holistic, expressive and robust human image animation with hybrid guidance[J]. arXiv preprint, arXiv: 2504.01724, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419820086440852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=122, rfOrder=128, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yi, Liang Sen, Zhou Zixiang, et al. HunyuanVideo-Avatar: High-fidelity audio-driven human animation for multiple characters[J]. arXiv preprint, arXiv: 2505.20156, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419820157744021, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=123, rfOrder=129, authorNames=null, journalName=null, refType=null, unstructuredReference=Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 4401−4410, articleTitle=null, refAbstract=null), Reference(id=1329419820229047190, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=124, rfOrder=130, authorNames=null, journalName=null, refType=null, unstructuredReference=Stypułkowski M, Vougioukas K, He Sen, et al. Diffused Heads: Diffusion models beat GANs on talking-face generation[C]//Proc of the IEEE/CVF Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2024: 5091−5100, articleTitle=null, refAbstract=null), Reference(id=1329419820333904791, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=125, rfOrder=131, authorNames=null, journalName=null, refType=null, unstructuredReference=Siarohin A, Woodford O J, Ren J, et al. Motion representations for articulated animation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 13653−13662, articleTitle=null, refAbstract=null), Reference(id=1329419820409402264, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=132, authorNames=null, journalName=null, refType=null, unstructuredReference=Karras T, Laine S, Aittala M, et al. Analyzing and improving the image quality of styleGAN[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 8110−8119, articleTitle=null, refAbstract=null), Reference(id=1329419820505871257, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=127, rfOrder=133, authorNames=null, journalName=null, refType=null, unstructuredReference=Preechakul K, Chatthee N, Wizadwongsa S, et al. Diffusion autoencoders: Toward a meaningful and decodable representation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 10619−10629, articleTitle=null, refAbstract=null), Reference(id=1329419820568785818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=128, rfOrder=134, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Lvmin, Rao Anyi, Agrawala M. Adding conditional control to text-to-image diffusion models[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 3836−3847, articleTitle=null, refAbstract=null), Reference(id=1329419820635894683, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=129, rfOrder=135, authorNames=null, journalName=null, refType=null, unstructuredReference=刘泽润, 尹宇飞, 薛文灏, 等. 基于扩散模型的条件引导图像生成综述[J]. 浙江大学学报: 理学版, 2023, 50(6): 651−667, articleTitle=null, refAbstract=null), Reference(id=1329419820715586460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=129, rfOrder=136, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zerun, Yin Yufei, Xue Wenhao, et al. A review of conditional image generation based on diffusion models[J]. Journal of Zhejiang University: Science Edition, 2023, 50(6): 651−667 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419820791083933, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=130, rfOrder=137, authorNames=null, journalName=null, refType=null, unstructuredReference=闫志浩, 周长兵, 李小翠. 生成扩散模型研究综述[J]. 计算机科学, 2024, 51(1): 273−283, articleTitle=null, refAbstract=null), Reference(id=1329419820853998494, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=130, rfOrder=138, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Zhihao, Zhou Changbing, Li Xiaocui. Survey on generative diffusion model[J]. Computer Science, 2024, 51(1): 273−283 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419820925301663, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=131, rfOrder=139, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Yao, Feng Haiwen, Black M J, et al. Learning an animatable detailed 3D face model from in-the-wild images[J]. ACM Transactions on Graphics, 2021, 40(4): 1−13, articleTitle=null, refAbstract=null), Reference(id=1329419820996604832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=132, rfOrder=140, authorNames=null, journalName=null, refType=null, unstructuredReference=Rombach R, Blattmann A, Lorenz D, et al. High-resolution image synthesis with latent diffusion models[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 10684−10695, articleTitle=null, refAbstract=null), Reference(id=1329419821072102305, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=133, rfOrder=141, authorNames=null, journalName=null, refType=null, unstructuredReference=Mildenhall B, Srinivasan P P, Tancik M, et al. Nerf: Representing scenes as neural radiance fields for view synthesis[J]. Communications of the ACM, 2021, 65(1): 99−106, articleTitle=null, refAbstract=null), Reference(id=1329419821151794082, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=134, rfOrder=142, authorNames=null, journalName=null, refType=null, unstructuredReference=Kerbl B, Kopanas G, Leimkühler T, et al. 3D Gaussian splatting for real-time radiance field rendering[J]. ACM Transactions on Graphics, 2023, 42(4): 139: 1−139: 14, articleTitle=null, refAbstract=null), Reference(id=1329419821218902947, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=135, rfOrder=143, authorNames=null, journalName=null, refType=null, unstructuredReference=VanDenOord A, Dieleman S, Zen Heiga, et al. WaveNet: A generative model for raw audio[C/OL]//Proc of the 33rd Int Conf on Machine Learning. 2016[2025-07-04]. https://doi.org/10.48550/arXiv.1609.03499, articleTitle=null, refAbstract=null), Reference(id=1329419821281817508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=136, rfOrder=144, authorNames=null, journalName=null, refType=null, unstructuredReference=Chan E, Lin C, Chan M, et al. Efficient geometry-aware 3D generative adversarial networks[C]//Proc of the IEEE/CVF Conf on computer vision and pattern recognition. Piscataway, NJ: IEEE, 2022: 16123−16133, articleTitle=null, refAbstract=null), Reference(id=1329419821353120677, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=137, rfOrder=145, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Xiangyu, Lei Zhen, Liu Xiaoming, et al. Face alignment across large poses: A 3D solution[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 146−155, articleTitle=null, refAbstract=null), Reference(id=1329419821424423846, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=138, rfOrder=146, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Yuelang, Chen Benwang, Li Zhe, et al. Gaussian head avatar: Ultra high-fidelity head avatar via dynamic gaussians[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 1931−1941, articleTitle=null, refAbstract=null), Reference(id=1329419821483144103, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=139, rfOrder=147, authorNames=null, journalName=null, refType=null, unstructuredReference=Li T, Bolkart T, Black M J, et al. Learning a model of facial shape and expression from 4D scans[J]. ACM Transactions on Graphics, 2017, 36(6): 194: 1−194: 17, articleTitle=null, refAbstract=null), Reference(id=1329419821541864360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=140, rfOrder=148, authorNames=null, journalName=null, refType=null, unstructuredReference=Drobyshev N, Chelishev J, Khakhulin T, et al. MegaPortraits: One-shot megapixel neural head avatars[C]//Proc of the 30th ACM Int Conf on Multimedia. New York: ACM, 2022: 2663−2671, articleTitle=null, refAbstract=null), Reference(id=1329419821596390313, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=141, rfOrder=149, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision[C]//Proc of the 38th Int Conf on Machine Learning. Red Hook, NY: Curran Associates Inc, 2021: 8748−8763, articleTitle=null, refAbstract=null), Reference(id=1329419821667693482, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=142, rfOrder=150, authorNames=null, journalName=null, refType=null, unstructuredReference=De Bem R, Ghosh A, Ajanthan T, et al. A semi-supervised deep generative model for human body analysis[C]//Proc of the European Conf on Computer Vision Workshops. Berlin: Springer, 2018: 500–517, articleTitle=null, refAbstract=null), Reference(id=1329419821738996651, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=143, rfOrder=151, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Zhe, Simon T, Wei S E, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 7291−7299, articleTitle=null, refAbstract=null), Reference(id=1329419821797716908, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=144, rfOrder=152, authorNames=null, journalName=null, refType=null, unstructuredReference=Güler R A, Neverova N, Kokkinos I. DensePose: Dense human pose estimation in the wild[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 7297−7306, articleTitle=null, refAbstract=null), Reference(id=1329419821864825773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=145, rfOrder=153, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Zhendong, Zeng Ailing, Yuan Chun, et al. Effective whole-body pose estimation with two-stages distillation[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 4210−4220, articleTitle=null, refAbstract=null), Reference(id=1329419822091318190, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=146, rfOrder=154, authorNames=null, journalName=null, refType=null, unstructuredReference=Loper M, Mahmood N, Romero J, et al. SMPL: A skinned multi-person linear model[J]. ACM Transactions on Graphics, 2015, 34(6): 1−16, articleTitle=null, refAbstract=null), Reference(id=1329419822150038447, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=147, rfOrder=155, authorNames=null, journalName=null, refType=null, unstructuredReference=邓梓焌, 何相腾, 彭宇新. 文本到视频生成: 研究现状、进展和挑战[J]. 电子与信息学报, 2024, 46(5): 1632−1644, articleTitle=null, refAbstract=null), Reference(id=1329419822204564400, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=147, rfOrder=156, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Zijian, He Xiangteng, Peng Yuxin. Text-to-video generation: Research status, progress and challenges[J]. Journal of Electronics & Information Technology, 2024, 46(5): 1632−1644 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419822254896049, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=148, rfOrder=157, authorNames=null, journalName=null, refType=null, unstructuredReference=巩志祥, 于秀平. 虚拟数字人制作流程及应用场景研究[J]. 电视技术, 2024, 48(12): 178−181, articleTitle=null, refAbstract=null), Reference(id=1329419822317810610, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=148, rfOrder=158, authorNames=null, journalName=null, refType=null, unstructuredReference=Gong Zhixiang, Yu Xiuping. Research on the production process and application scenarios of virtual digital human[J]. TV Technology, 2024, 48(12): 178−181 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419822376530867, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=149, rfOrder=159, authorNames=null, journalName=null, refType=null, unstructuredReference=Howard A G, Zhu Menglong, Chen Bo, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint, arXiv: 1704.04861, 2017, articleTitle=null, refAbstract=null), Reference(id=1329419822431056820, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=150, rfOrder=160, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Mingxing, Le Q. EfficientNet: Rethinking model scaling for convolutional neural networks[C/OL]//Proc of the 36th Int Conf on Machine Learning. 2019: 6105−6114. [2025-07-04]. https://proceedings.mlr.press/v97/tan19a.html, articleTitle=null, refAbstract=null), Reference(id=1329419822502359989, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=151, rfOrder=161, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Cheng, Zhou Yuhao, Bao Fan, et al. DPM-Solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps[C]//Proc of the 36th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2022: 5775−5787, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329419806727582417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, xref=null, ext=[AuthorCompanyExt(id=1329419806735971026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Software Technology, Zhejiang University, Ningbo, Zhejiang 315106), AuthorCompanyExt(id=1329419806744359635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, companyId=1329419806727582417, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=浙江大学软件学院 浙江宁波 315106)])], figs=[ArticleFig(id=1329419808963146493, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Figure 1, caption=
2D virtual human-driven task, figureFileSmall=BMvdeeaGVHDao8EntAQHbQ==, figureFileBig=leiSjWyDy7yLbF9Y1t0CCQ==, tableContent=null), ArticleFig(id=1329419809017672446, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=图1, caption=
2D虚拟人驱动任务, figureFileSmall=BMvdeeaGVHDao8EntAQHbQ==, figureFileBig=leiSjWyDy7yLbF9Y1t0CCQ==, tableContent=null), ArticleFig(id=1329419809189638911, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Figure 2, caption=
Classification of 2D virtual human-driven technologies, figureFileSmall=N9Hk8qVOz9e9DIVdc8FnBA==, figureFileBig=0wGQ3dgmjDigevgJIyW8Jw==, tableContent=null), ArticleFig(id=1329419809286107904, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=图2, caption=
2D虚拟人驱动技术分类, figureFileSmall=N9Hk8qVOz9e9DIVdc8FnBA==, figureFileBig=0wGQ3dgmjDigevgJIyW8Jw==, tableContent=null), ArticleFig(id=1329419809382576897, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Figure 3, caption=
Lip-driven generation technology based on GANs[16], figureFileSmall=nm7MDVIC76p02Ojn8HitNA==, figureFileBig=L9w2o6Z4OYFE8glwhA2p0w==, tableContent=null), ArticleFig(id=1329419809458074370, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=图3, caption=
基于GANs的唇部驱动生成技术[16], figureFileSmall=nm7MDVIC76p02Ojn8HitNA==, figureFileBig=L9w2o6Z4OYFE8glwhA2p0w==, tableContent=null), ArticleFig(id=1329419809525183235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Figure 4, caption=
Facial generation techniques based on intermediate representations, figureFileSmall=DMedpvWdIe7gqnCa6l/rFw==, figureFileBig=+k2zVWwBQ0awJnvTV0RDXQ==, tableContent=null), ArticleFig(id=1329419809583903492, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=图4, caption=
基于中间表征的面部生成技术, figureFileSmall=DMedpvWdIe7gqnCa6l/rFw==, figureFileBig=+k2zVWwBQ0awJnvTV0RDXQ==, tableContent=null), ArticleFig(id=1329419809646818053, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Figure 5, caption=
Autoregressive talking head generation techniques, figureFileSmall=hikRKNcJgootTQSMTeO7vQ==, figureFileBig=4AuFM/Xsd8ZqIsi1vjExew==, tableContent=null), ArticleFig(id=1329419809705538310, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=图5, caption=
自回归的说话头部生成技术, figureFileSmall=hikRKNcJgootTQSMTeO7vQ==, figureFileBig=4AuFM/Xsd8ZqIsi1vjExew==, tableContent=null), ArticleFig(id=1329419809768452871, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Figure 6, caption=
Facial generation techniques for dyadic dialogues based on reinforcement learning, figureFileSmall=+QzZt+L+6pNieAIeWmrpNg==, figureFileBig=6/n+gkAGYg3irAr1ihbOpw==, tableContent=null), ArticleFig(id=1329419809894281992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=图6, caption=
基于强化学习的二元对话面部生成技术, figureFileSmall=+QzZt+L+6pNieAIeWmrpNg==, figureFileBig=6/n+gkAGYg3irAr1ihbOpw==, tableContent=null), ArticleFig(id=1329419809957196553, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Figure 7, caption=
Video-to-video pose-guided generation technology based on diffusion model[105], figureFileSmall=1ZSPg7Z+J/v+igmSkSZuUw==, figureFileBig=QCKeB59w0vKLmInivygNcQ==, tableContent=null), ArticleFig(id=1329419810020111114, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=图7, caption=
基于扩散模型的视频到视频姿态引导生成技术[105], figureFileSmall=1ZSPg7Z+J/v+igmSkSZuUw==, figureFileBig=QCKeB59w0vKLmInivygNcQ==, tableContent=null), ArticleFig(id=1329419810091414283, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Table 1, caption=
Summary of Lip-Driven Talking Head Generation Technologies
, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 模型 | 驱动对象 | 基础模型 | 中间表征 | 唇部运动 | 面部表情 | 头部运动 |
|---|
| 2017 | SynObama [12] | 特定 | LSTM | landmarks | √ | | |
| 2017 | Speech2Vid[13] | 任意 | CNN | | √ | | |
| 2019 | DAVS[14] | 任意 | GANs | | √ | | |
| 2020 | MakeItTalk[15] | 任意 | LSTM | landmarks | √ | √ | |
| 2020 | Wav2Lip[16] | 任意 | GANs | | √ | | |
| 2023 | TalkLip[17] | 任意 | GANs | | √ | | |
| 2024 | DINet[18] | 任意 | GANs | | √ | | |
| 2024 | 文献[19] | 任意 | CNN+GANs | landmarks | √ | | |
| 2024 | 文献[20] | 任意 | GANs | | √ | | |
| 2025 | M-CSAWav2Lip[21] | 任意 | GANs | | √ | | |
), ArticleFig(id=1329419810166911756, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=表1, caption=
唇形驱动说话人生成技术汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 模型 | 驱动对象 | 基础模型 | 中间表征 | 唇部运动 | 面部表情 | 头部运动 |
|---|
| 2017 | SynObama [12] | 特定 | LSTM | landmarks | √ | | |
| 2017 | Speech2Vid[13] | 任意 | CNN | | √ | | |
| 2019 | DAVS[14] | 任意 | GANs | | √ | | |
| 2020 | MakeItTalk[15] | 任意 | LSTM | landmarks | √ | √ | |
| 2020 | Wav2Lip[16] | 任意 | GANs | | √ | | |
| 2023 | TalkLip[17] | 任意 | GANs | | √ | | |
| 2024 | DINet[18] | 任意 | GANs | | √ | | |
| 2024 | 文献[19] | 任意 | CNN+GANs | landmarks | √ | | |
| 2024 | 文献[20] | 任意 | GANs | | √ | | |
| 2025 | M-CSAWav2Lip[21] | 任意 | GANs | | √ | | |
), ArticleFig(id=1329419810250797837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Table 2, caption=
Summary of Monocular Talking Head Generation Technologies Based on 2D Models
, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 模型 | 驱动信号 | 驱动对象 | 基础模型 | 显式表征 | 隐式表征 | 中间表征 |
|---|
| 2018 | ReenactGAN[36] | 视频 | 特定 | GANs | | √ | |
| 2019 | FOMM[22] | 视频 | 任意 | CNN | √ | | 2D关键点 |
| 2020 | MarioNETte[23] | 视频 | 任意 | Transformer | √ | | landmarks |
| 2021 | 文献[24] | 音频 | 任意 | GANs | √ | | landmarks |
| 2021 | Face vid2vid[25] | 视频 | 任意 | CNN | √ | | 3D关键点 |
| 2021 | SAFA[26] | 视频 | 任意 | CNN | √ | | 3DMM |
| 2021 | PC-AVS[37] | 音频 | 任意 | GANs | | √ | |
| 2022 | DAGAN[27] | 视频 | 任意 | GANs | √ | | 2D关键点 |
| 2022 | TPSM[28] | 视频 | 任意 | CNN | √ | | 2D关键点 |
| 2022 | DAM[29] | 视频 | 任意 | CNN | √ | | 2D关键点 |
| 2022 | HifiHead[30] | 视频 | 特定 | GANs | √ | | 3DMM |
| 2022 | LIA[38] | 视频 | 特定 | GANs | | √ | |
| 2023 | MetaPortrait[31] | 视频 | 任意 | GANs | √ | | landmarks |
| 2023 | Wang等人[32] | 音频 | 任意 | CNN | √ | | landmarks |
| 2023 | StyleMask[39] | 视频 | 特定 | GANs | | √ | |
| 2023 | MCNET[40] | 视频 | 任意 | CNN | | √ | |
| 2023 | FADM[43] | 视频 | 任意 | Diffusion | √ | | 3D关键点 |
| 2023 | Difftalk[44] | 音频 | 任意 | Diffusion | √ | | landmarks |
| 2023 | DAE-Talker[45] | 音频 | 特定 | Diffusion | | √ | |
| 2023 | Diffused Heads[124] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | LivePortrait[33] | 视频 | 任意 | CNN | √ | | 3D关键点 |
| 2024 | DiffusionAct [41] | 视频 | 任意 | Diffusion | | √ | |
| 2024 | X-Portrait[42] | 视频 | 任意 | Diffusion | | √ | |
| 2024 | AniFaceDiff[46] | 视频 | 任意 | Diffusion | √ | | 3D关键点 |
| 2024 | Follow-Your-Emoji[47] | 视频 | 任意 | Diffusion | √ | | 3D关键点 |
| 2024 | VASA-1[48] | 音频 | 任意 | Diffusion | | √ | |
| 2024 | EchoMimic[49] | 音频 | 任意 | Diffusion | √ | | landmarks |
| 2024 | EMO[50] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | Hallo[51] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | Loopy[52] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | Hallo2[53] | 音频 | 任意 | Diffusion | | | 端到端 |
), ArticleFig(id=1329419810347266830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=表2, caption=
基于2D模型的单目说话头生成技术汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 模型 | 驱动信号 | 驱动对象 | 基础模型 | 显式表征 | 隐式表征 | 中间表征 |
|---|
| 2018 | ReenactGAN[36] | 视频 | 特定 | GANs | | √ | |
| 2019 | FOMM[22] | 视频 | 任意 | CNN | √ | | 2D关键点 |
| 2020 | MarioNETte[23] | 视频 | 任意 | Transformer | √ | | landmarks |
| 2021 | 文献[24] | 音频 | 任意 | GANs | √ | | landmarks |
| 2021 | Face vid2vid[25] | 视频 | 任意 | CNN | √ | | 3D关键点 |
| 2021 | SAFA[26] | 视频 | 任意 | CNN | √ | | 3DMM |
| 2021 | PC-AVS[37] | 音频 | 任意 | GANs | | √ | |
| 2022 | DAGAN[27] | 视频 | 任意 | GANs | √ | | 2D关键点 |
| 2022 | TPSM[28] | 视频 | 任意 | CNN | √ | | 2D关键点 |
| 2022 | DAM[29] | 视频 | 任意 | CNN | √ | | 2D关键点 |
| 2022 | HifiHead[30] | 视频 | 特定 | GANs | √ | | 3DMM |
| 2022 | LIA[38] | 视频 | 特定 | GANs | | √ | |
| 2023 | MetaPortrait[31] | 视频 | 任意 | GANs | √ | | landmarks |
| 2023 | Wang等人[32] | 音频 | 任意 | CNN | √ | | landmarks |
| 2023 | StyleMask[39] | 视频 | 特定 | GANs | | √ | |
| 2023 | MCNET[40] | 视频 | 任意 | CNN | | √ | |
| 2023 | FADM[43] | 视频 | 任意 | Diffusion | √ | | 3D关键点 |
| 2023 | Difftalk[44] | 音频 | 任意 | Diffusion | √ | | landmarks |
| 2023 | DAE-Talker[45] | 音频 | 特定 | Diffusion | | √ | |
| 2023 | Diffused Heads[124] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | LivePortrait[33] | 视频 | 任意 | CNN | √ | | 3D关键点 |
| 2024 | DiffusionAct [41] | 视频 | 任意 | Diffusion | | √ | |
| 2024 | X-Portrait[42] | 视频 | 任意 | Diffusion | | √ | |
| 2024 | AniFaceDiff[46] | 视频 | 任意 | Diffusion | √ | | 3D关键点 |
| 2024 | Follow-Your-Emoji[47] | 视频 | 任意 | Diffusion | √ | | 3D关键点 |
| 2024 | VASA-1[48] | 音频 | 任意 | Diffusion | | √ | |
| 2024 | EchoMimic[49] | 音频 | 任意 | Diffusion | √ | | landmarks |
| 2024 | EMO[50] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | Hallo[51] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | Loopy[52] | 音频 | 任意 | Diffusion | | | 端到端 |
| 2024 | Hallo2[53] | 音频 | 任意 | Diffusion | | | 端到端 |
), ArticleFig(id=1329419810431152911, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=EN, label=Table 3, caption=
Summary of Talking Head Generation Technologies Driven by Conditions
, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 模型 | 驱动信息 | 基础模型 | 中间表达 | 表情驱动 | 头部驱动 | 姿态驱动 |
|---|
| 2020 | MEAD[79] | 音频、表情图像 | GANs | landmarks | √ | | |
| 2021 | Wu等人[86] | 音频、风格视频 | GANs | 3DMM | √ | √ | |
| 2022 | Sinha等人[80] | 音频、表情标签 | GANs | landmarks | √ | | |
| 2022 | EAMM[81] | 音频、情绪视频 | LSTM | 隐向量 | √ | | |
| 2022 | GC-AVT[87] | 音频、视频 | Transformer | 隐向量 | √ | √ | |
| 2023 | EMOPortraits[82] | 音频、表情图像 | CNN | 隐向量 | √ | √ | √ |
| 2023 | EAT[83] | 音频、情绪标签 | GANs | 3D隐式关键点 | √ | | |
| 2023 | Dream-Talk[84] | 音频、情绪标签 | Diffusion | blendshapes | √ | | |
| 2023 | 文献[85] | 音频、情绪标签 | GANs | | √ | | |
| 2023 | StyleTalk[88] | 音频、视频 | GANs | 3DMM | √ | | |
| 2024 | SAAS[89] | 音频、视频 | GANs | 3DMM | √ | √ | |
| 2024 | Style2Talker[90] | 音频、情绪文本、艺术图像 | Diffusion,GANs | 3DMM | √ | | |
| 2024 | StyleTalk++[91] | 音频、视频 | GANs | 3DMM | √ | √ | |
), ArticleFig(id=1329419810582147856, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419803737043635, language=CN, label=表3, caption=
条件驱动说话人生成技术汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 模型 | 驱动信息 | 基础模型 | 中间表达 | 表情驱动 | 头部驱动 | 姿态驱动 |
|---|
| 2020 | MEAD[79] | 音频、表情图像 | GANs | landmarks | √ | | |
| 2021 | Wu等人[86] | 音频、风格视频 | GANs | 3DMM | √ | √ | |
| 2022 | Sinha等人[80] | 音频、表情标签 | GANs | landmarks | √ | | |
| 2022 | EAMM[81] | 音频、情绪视频 | LSTM | 隐向量 | √ | | |
| 2022 | GC-AVT[87] | 音频、视频 | Transformer | 隐向量 | √ | √ | |
| 2023 | EMOPortraits[82] | 音频、表情图像 | CNN | 隐向量 | √ | √ | √ |
| 2023 | EAT[83] | 音频、情绪标签 | GANs | 3D隐式关键点 | √ | | |
| 2023 | Dream-Talk[84] | 音频、情绪标签 | Diffusion | blendshapes | √ | | |
| 2023 | 文献[85] | 音频、情绪标签 | GANs | | √ | | |
| 2023 | StyleTalk[88] | 音频、视频 | GANs | 3DMM | √ | | |
| 2024 | SAAS[89] | 音频、视频 | GANs | 3DMM | √ | √ | |
| 2024 | Style2Talker[90] | 音频、情绪文本、艺术图像 | Diffusion,GANs | 3DMM | √ | | |
| 2024 | StyleTalk++[91] | 音频、视频 | GANs | 3DMM | √ | √ | |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550560, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550560, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202550560, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202550560, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1780243200000, fullTextJson=null, articleText=null, reference=null)