Article(id=1329419404724515177, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329419378451394604, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202550352, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1748188800000, receivedDateStr=2025-05-26, revisedDate=1760544000000, revisedDateStr=2025-10-16, acceptedDate=1761840000000, acceptedDateStr=2025-10-31, onlineDate=1794887885504, onlineDateStr=2026-11-17, pubDate=1774972800000, pubDateStr=2026-04-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794887885504, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794887885504, creator=13701087609, updateTime=1794887885504, updator=13701087609, issue=Issue{id=1329419378451394604, tenantId=1146029695717560320, journalId=1324759914146529478, year='2026', volume='63', issue='4', pageStart='825', pageEnd='1093', issueExtLink='null', onlineDate='null', pubDate='1774972800000', pubDateStr='2026-04-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794887879240, creator='13701087609', updateTime=1794887879240, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=943, endPage=959, ext={EN=ArticleExt(id=1329419404904870250, articleId=1329419404724515177, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Review of Human-Scene Interactive Motion Generation, columnId=1325489891789910943, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence, runingTitle=null, highlight=null, articleAbstract=
The task of generating human–scene interaction motions involves multiple disciplines, including computer vision, computer graphics, and robotics. The primary goal of this task is to leverage deep learning algorithms to model and learn the relationships between humans and scenes from large-scale interaction motion data, thereby generating diverse human motions interacting with indoor scenes or objects within them. These motions include, for instance, obstacle-avoidance navigation, human–chair interaction, and object grasping. Compared with traditional physics-based simulation approaches, data-driven methods for interaction motion generation are free from reliance on physical simulation engines, providing higher computational efficiency and stronger generalization capability. As a result, these methods hold broad application prospects in areas such as game design, film production, and human–computer interaction. Nevertheless, current research on human–scene interaction motion generation has not yet formed a systematic review or synthesis. To address this gap, we systematically organize and explicate the core advancements in this domain. Specifically, we first introduce data representation methods for 3D humans and scenes. Building on this foundation, we then summarize the different types of interaction tasks and the associated technical challenges, while also presenting the key characteristics of relevant benchmark datasets and evaluation metrics. Finally, we highlight the limitations of existing technical approaches and discuss potential breakthrough directions and development paths for future research.
, authors=Yuchen Jing
1, 2, Yuhui Wen
2, *, Chenguang Li
2, Jian Yu
2, authorsList=Yuchen Jing, Yuhui Wen, Chenguang Li, Jian Yu, authorCompany=null, correspAuthors=Yuhui Wen, authorNote=
born in 2000. PhD candidate. Student member of CCF. His research interests include computer vision, 3D motion representation and generation, continuous learning, AI, and machine learning
was born in 1990. PhD, associate professor. Member of CCF. Her research interests include computer vision, computer graphics, and machine learning
born in 2002. PhD candidate. Student member of CCF. His research interests include computer vision, 3D motion representation and generation, and machine learning
born in 1969. PhD, professor, PhD supervisor. Fellow of CCF. His main research interests include artificial intelligence and machine learning
, 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=1329419407312400774, articleId=1329419404724515177, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=人与场景交互运动生成技术综述, columnId=1325489892104483745, journalTitle=计算机研究与发展, columnName=人工智能, runingTitle=null, highlight=null, articleAbstract=
人与场景交互运动生成任务涉及计算机视觉、计算机图形学和机器人控制学等多个领域。该任务旨在利用深度学习算法从大量交互运动数据中建模并学习人与场景的交互运动关系,生成人与室内场景或其中物体的各种交互运动,包括避障漫游、人椅交互和物体抓取等。相比于传统物理仿真方法,基于数据驱动的交互运动生成方法摆脱了对物理仿真引擎的依赖,具有更高的计算效率和更强的泛化能力,在游戏设计、影视制作和人机交互等领域具有广泛的应用前景。然而,当前对人与场景交互运动生成技术的研究尚未形成系统性归纳,系统梳理与阐述当前人体与场景交互运动生成技术的核心进展。首先阐释3维人体与场景的数据表示方法;其次在此基础上系统地归纳不同交互任务类型及技术挑战,详述相关基准数据集的核心特征及评估指标体系;最后总结现有技术路线的局限性并分析未来研究的突破方向与潜在发展路径。
, authors=景宇宸
1, 2, 温玉辉
2, *, 李晨光
2, 于剑
2, authorsList=景宇宸, 温玉辉, 李晨光, 于剑, authorCompany=null, correspAuthors=温玉辉, authorNote=
 |
2000年生。博士研究生。CCF学生会员。主要研究方向为计算机视觉、3维动作表示与生成、持续学习、人工智能、机器学习 |
 |
1990年生。博士,副教授。CCF会员。主要研究方向为计算机视觉、计算机图形学、机器学习 |
 |
2002年生。博士研究生。CCF学生会员。主要研究方向为计算机视觉、3维动作表示与生成、机器学习 |
 |
1969年生。博士,教授,博士生导师。CCF会士。主要研究方向为人工智能、机器学习 |
, 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=q0FOm/5Kj+62i/HT5SKLgg==, magXml=RwOhlmR8ODN2w1yczkpY3g==, pdfUrl=null, pdf=KDz+2DEW+r4VhY9g88IDWw==, pdfFileSize=3294717, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=rqu6xzbwuy67G1v1iy2M7A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=U34rq6h+ditueng6NLsPxw==, mapNumber=null, fund=null)}, authors=[Author(id=1329419407719248270, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=25110183@bjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419407798940049, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419407719248270, language=EN, stringName=Yuchen Jing, firstName=Yuchen, middleName=null, lastName=Jing, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1State Key Laboratory of Advanced Rail Autonomous Operation (Beijing Jiaotong University), Beijing 100044
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 2000. PhD candidate. Student member of CCF. His research interests include computer vision, 3D motion representation and generation, continuous learning, AI, and machine learning
"}, bioImg=null, bioContent=
born in 2000. PhD candidate. Student member of CCF. His research interests include computer vision, 3D motion representation and generation, continuous learning, AI, and machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419407874437522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419407719248270, language=CN, stringName=景宇宸, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1先进轨道交通自主运行全国重点实验室(北京交通大学) 北京 100044
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"vdrzDLDSeQSCH30aFP1z8g==","content":"
2000年生。博士研究生。CCF学生会员。主要研究方向为计算机视觉、3维动作表示与生成、持续学习、人工智能、机器学习
"}, bioImg=vdrzDLDSeQSCH30aFP1z8g==, bioContent=
2000年生。博士研究生。CCF学生会员。主要研究方向为计算机视觉、3维动作表示与生成、持续学习、人工智能、机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419407517921671, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, xref=1, ext=[AuthorCompanyExt(id=1329419407530504584, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407517921671, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Advanced Rail Autonomous Operation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1329419407538893193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407517921671, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1先进轨道交通自主运行全国重点实验室(北京交通大学) 北京 100044)]), AuthorCompany(id=1329419407618584970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, xref=2, ext=[AuthorCompanyExt(id=1329419407631167883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1329419407652139404, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1329419407941546388, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yhwen1@bjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329419408021238166, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419407941546388, language=EN, stringName=Yuhui Wen, firstName=Yuhui, middleName=null, lastName=Wen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, *, address=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044, bio={"content":"
was born in 1990. PhD, associate professor. Member of CCF. Her research interests include computer vision, computer graphics, and machine learning
"}, bioImg=null, bioContent=
was born in 1990. PhD, associate professor. Member of CCF. Her research interests include computer vision, computer graphics, and machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419408096735639, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419407941546388, language=CN, stringName=温玉辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, *, address=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"O/AbOX3VXXKvpTpexNJACw==","content":"
1990年生。博士,副教授。CCF会员。主要研究方向为计算机视觉、计算机图形学、机器学习
"}, bioImg=O/AbOX3VXXKvpTpexNJACw==, bioContent=
1990年生。博士,副教授。CCF会员。主要研究方向为计算机视觉、计算机图形学、机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419407618584970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, xref=2, ext=[AuthorCompanyExt(id=1329419407631167883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1329419407652139404, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1329419408159650201, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, 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=1329419408226759067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419408159650201, language=EN, stringName=Chenguang Li, firstName=Chenguang, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 2002. PhD candidate. Student member of CCF. His research interests include computer vision, 3D motion representation and generation, and machine learning
"}, bioImg=null, bioContent=
born in 2002. PhD candidate. Student member of CCF. His research interests include computer vision, 3D motion representation and generation, and machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419408310645148, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419408159650201, language=CN, stringName=李晨光, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"yLPPv6YIXQvXZ2P1yF57mQ==","content":"
2002年生。博士研究生。CCF学生会员。主要研究方向为计算机视觉、3维动作表示与生成、机器学习
"}, bioImg=yLPPv6YIXQvXZ2P1yF57mQ==, bioContent=
2002年生。博士研究生。CCF学生会员。主要研究方向为计算机视觉、3维动作表示与生成、机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419407618584970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, xref=2, ext=[AuthorCompanyExt(id=1329419407631167883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1329419407652139404, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1329419408394531230, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, orderNo=3, 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=1329419408478417313, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419408394531230, language=EN, stringName=Jian Yu, firstName=Jian, middleName=null, lastName=Yu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1969. PhD, professor, PhD supervisor. Fellow of CCF. His main research interests include artificial intelligence and machine learning
"}, bioImg=null, bioContent=
born in 1969. PhD, professor, PhD supervisor. Fellow of CCF. His main research interests include artificial intelligence and machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419408549720482, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, authorId=1329419408394531230, language=CN, stringName=于剑, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"t8X7s6r7wCrGcpIVDTuQJA==","content":"
1969年生。博士,教授,博士生导师。CCF会士。主要研究方向为人工智能、机器学习
"}, bioImg=t8X7s6r7wCrGcpIVDTuQJA==, bioContent=
1969年生。博士,教授,博士生导师。CCF会士。主要研究方向为人工智能、机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419407618584970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, xref=2, ext=[AuthorCompanyExt(id=1329419407631167883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1329419407652139404, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044)])])], keywords=[Keyword(id=1329419408646189475, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, orderNo=1, keyword=human motion generation), Keyword(id=1329419408717492644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, orderNo=2, keyword=interaction data), Keyword(id=1329419408792990117, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, orderNo=3, keyword=scene interaction), Keyword(id=1329419408860098983, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, orderNo=4, keyword=data driven), Keyword(id=1329419408923013544, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, orderNo=5, keyword=literature review), Keyword(id=1329419408985928105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, orderNo=1, keyword=人体运动生成), Keyword(id=1329419409044648362, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, orderNo=2, keyword=交互数据), Keyword(id=1329419409103368619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, orderNo=3, keyword=场景交互), Keyword(id=1329419409183060397, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, orderNo=4, keyword=数据驱动), Keyword(id=1329419409254363566, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, orderNo=5, keyword=研究综述)], refs=[Reference(id=1329419411330544078, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, 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=Cervantes P, Sekikawa Y, Sato I, et al. Implicit neural representations for variable length human motion generation[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 356−372, articleTitle=null, refAbstract=null), Reference(id=1329419411397652943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, 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=Petrovich M, Black M J, Varol G. Action-conditioned 3D human motion synthesis with Transformer VAE[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 10965−10975, articleTitle=null, refAbstract=null), Reference(id=1329419411473150417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, 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=Barsoum E, Kender J, Liu Z. HP-GAN: Probabilistic 3D human motion prediction via GAN[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition Workshops. Piscataway, NJ: IEEE, 2018: 1418−1427, articleTitle=null, refAbstract=null), Reference(id=1329419411544453586, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, 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=Shafir Y, Tevet G, Kapon R, et al. Human motion diffusion as a generative prior[J]. arXiv preprint, arXiv: 2303.01418, 2023, articleTitle=null, refAbstract=null), Reference(id=1329419411603173844, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, 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=Park S I, Shin H J, Shin S Y. On-line locomotion generation based on motion blending[C]//Proc of the ACM SIGGRAPH/Eurographics Symp on Computer Animation. New York: ACM, 2002: 105−111, articleTitle=null, refAbstract=null), Reference(id=1329419411670282709, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Shum H P H, Komura T, Shiraishi M, et al. Interaction patches for multi-character animation[J]. ACM Transactions on Graphics, 2008, 27(5): 1−8, articleTitle=null, refAbstract=null), Reference(id=1329419411733197270, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Agrawal S, van de Panne M. Task-based locomotion[J]. ACM Transactions on Graphics, 2016. https://dl.acm.org/doi/10.1145/2897824.2925893, articleTitle=null, refAbstract=null), Reference(id=1329419411804500440, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Starke S, Zhang H, Komura T, et al. Neural state machine for character-scene interactions[J]. ACM Transactions on Graphics, 2019, 38(6): 1−14, articleTitle=null, refAbstract=null), Reference(id=1329419411900969433, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Holden D, Komura T, Saito J. Phase-functioned neural networks for character control[J]. ACM Transactions on Graphics, 2017, 36(4): 1−13, articleTitle=null, refAbstract=null), Reference(id=1329419411972272602, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Hassan M, Ghosh P, Tesch J, et al. Populating 3D scenes by learning human-scene interaction[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 14703−14713, articleTitle=null, refAbstract=null), Reference(id=1329419412056158683, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Xueting, Liu Sifei, Kim K, et al. Putting humans in a scene: Learning affordance in 3D indoor environments[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 12360−12368, articleTitle=null, refAbstract=null), Reference(id=1329419412127461852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Siwei, Zhang Yan, Ma Qianli, et al. PLACE: Proximity learning of articulation and contact in 3D environments[C]//Proc of the Int Conf on 3D Vision. Piscataway, NJ: IEEE, 2020: 642−651, articleTitle=null, refAbstract=null), Reference(id=1329419412194570717, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yan, Hassan M, Neumann H, et al. Generating 3D people in scenes without people[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 6194−6204, articleTitle=null, refAbstract=null), Reference(id=1329419412265873887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Kaifeng, Wang Shaofei, Zhang Yan, et al. Compositional human-scene interaction synthesis with semantic control[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 311−327, articleTitle=null, refAbstract=null), Reference(id=1329419412358148576, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jiashun, Xu Huazhe, Xu Jingwei, et al. Synthesizing long-term 3D human motion and interaction in 3D scenes[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 9396−9406, articleTitle=null, refAbstract=null), Reference(id=1329419412429451745, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jingbo, Yan Sijie, Dai Bo, et al. Scene-aware generative network for human motion synthesis[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 12206−12215, articleTitle=null, refAbstract=null), Reference(id=1329419412509143522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Hassan M, Ceylan D, Villegas R, et al. Stochastic scene-aware motion prediction[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 11374−11384, articleTitle=null, refAbstract=null), Reference(id=1329419412580446691, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jingbo, Rong Yu, Liu Jingyuan, et al. Towards diverse and natural scene-aware 3D human motion synthesis[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 20428−20437, articleTitle=null, refAbstract=null), Reference(id=1329419412647555556, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Zan, Chen Yixin, Liu Tengyu, et al. HUMANISE: Language-conditioned human motion generation in 3D scenes[C]//Proc of the 36th Int Conf on Neural Information Processing Systems Advances in Neural Information Processing Systems. New York: Curran Associate, 2022: 14959−14971, articleTitle=null, refAbstract=null), Reference(id=1329419412714664421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=杜韬, 胡瑞珍, 刘利斌, 等. 室内场景拟人交互研究进展[J]. 中国图象图形学报, 2024, 29(6): 1575−1606, articleTitle=null, refAbstract=null), Reference(id=1329419412790161895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Tao, Hu Ruizhen, Liu Libin, et al. Research progress in human-like indoor scene interaction[J]. Journal of Image and Graphics, 2024, 29(6): 1575−1606 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419412865659368, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Wentao Ma Xiaoxuan, Ro D, et al. Human motion generation: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(4): 2430−2449, articleTitle=null, refAbstract=null), Reference(id=1329419412928573929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Badler N I, Phillips C B, Webber B L. Simulating Humans: Computer Graphics Animation and Control[M]. New York: Oxford University Press, 1993, articleTitle=null, refAbstract=null), Reference(id=1329419412991488490, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Kucuk S, Bingul Z. Robot kinematics: Forward and Inverse kinematics[M]. London, UK: INTECH Open Access Publisher, 2006, articleTitle=null, refAbstract=null), Reference(id=1329419413054403052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, 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): 851−866, articleTitle=null, refAbstract=null), Reference(id=1329419413117317613, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Romero J, Tzionas D, Black M J. Embodied hands: Modeling and capturing hands and bodies together[J]. ACM Transactions on Graphics, 2017, 36(6): 1−17, articleTitle=null, refAbstract=null), Reference(id=1329419413180232174, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Pavlakos G, Choutas V, Ghorbani N, et al. Expressive body capture: 3D hands, face, and body from a single image[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 10967−10977, articleTitle=null, refAbstract=null), Reference(id=1329419413247341039, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Prokudin S, Lassner C, Romero J. Efficient learning on point clouds with basis point sets[C]//Proc of the IEEE/CVF Int Conf on Computer Vision Workshop. Piscataway, NJ: IEEE, 2019: 3072−3081, articleTitle=null, refAbstract=null), Reference(id=1329419413314449904, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Park J J, Florence P, Straub J, et al. Deepsdf: Learning continuous signed distance functions for shape representation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 165−174, articleTitle=null, refAbstract=null), Reference(id=1329419413368975857, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Mescheder L, Oechsle M, Niemeyer M, et al. Occupancy networks: Learning 3D reconstruction in function space[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 4455−4465, articleTitle=null, refAbstract=null), Reference(id=1329419413436084722, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, 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=1329419413494804980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Araújo J P, Li J, Vetrivel K, et al. CIRCLE: Capture in rich contextual environments[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 21211−21221, articleTitle=null, refAbstract=null), Reference(id=1329419413557719541, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Zhe, Gao Hang, Mangalam K, et al. Long-term human motion prediction with scene context[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 387−404, articleTitle=null, refAbstract=null), Reference(id=1329419413620634102, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Wenfeng, Zhang Xinyu, Li Shuai, et al. HOIAnimator: Generating text-prompt human-object animations using novel perceptive diffusion models[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognitio. Piscataway, NJ: IEEE, 2024: 811−820, articleTitle=null, refAbstract=null), Reference(id=1329419413679354359, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Cen Zhi, Pi Huaijin, Peng Sida, et al. Generating human motion in 3D scenes from text descriptions[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 1855−1866, articleTitle=null, refAbstract=null), Reference(id=1329419413759046136, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Taheri O, Choutas V, Black M J, et al. GOAL: Generating 4D whole-body motion for hand-object grasping[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 13253−13263, articleTitle=null, refAbstract=null), Reference(id=1329419413855515130, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=彭淑娟, 周兵, 柳欣, 等. 人体运动生成中的深度学习模型综述[J]. 计算机辅助设计与图形学学报, 2018, 30(6): 1166−1176, articleTitle=null, refAbstract=null), Reference(id=1329419413931012603, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Shujuan, Zhou Bing, Liu Xin, et al. Recent advances in deep learning model for human motion generation[J]. Journal of Computer-Aided Design & Computer Graphic, 2018, 30(6): 1166−1176 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419413993927164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Corona E, Pumarola A, Alenya G, et al. Context-aware human motion prediction[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 6990−7999, articleTitle=null, refAbstract=null), Reference(id=1329419414061036029, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiaohan, Bhatnagar B L, Starke S, et al. Couch: Towards controllable human-chair interactions[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 518−535, articleTitle=null, refAbstract=null), Reference(id=1329419414140727807, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Mao Wei, Liu miaomiao, Hartley R I, et al. Contact-aware human motion forecasting[C]//Proc of the 36th Int Conf on Neural Information Processing Systems Advances in Neural Information Processing Systems. New York: Curran Associate, 2022: 7356−7367, articleTitle=null, refAbstract=null), Reference(id=1329419414203642368, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Elman J L. Finding structure in time[J]. Cognitive Science, 1990, 14(2): 179−211, articleTitle=null, refAbstract=null), Reference(id=1329419414258168321, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 135−1780, articleTitle=null, refAbstract=null), Reference(id=1329419414312694274, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Cho K, van Merrienboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proc of the Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2014: 1724−1734, articleTitle=null, refAbstract=null), Reference(id=1329419414379803139, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proc of the 28th Int Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2014: 2672−2680, articleTitle=null, refAbstract=null), Reference(id=1329419414455300612, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Kingma D P, Welling M. Auto-encoding variational Bayes[J]. arXiv preprint, arXiv: 1312.6114, 2013, articleTitle=null, refAbstract=null), Reference(id=1329419414530798086, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models[C]//Proc of the 34th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2020: 6840−6851, articleTitle=null, refAbstract=null), Reference(id=1329419414593712647, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Veličković P, Cucurull G, Casanova A, et al. Graph attention networks[J]. arXiv preprint, arXiv: 1710.10903, 2017, articleTitle=null, refAbstract=null), Reference(id=1329419414660821512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Martinez J, Black M J, Romero J. On human motion prediction using recurrent neural networks[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 4674−4683, articleTitle=null, refAbstract=null), Reference(id=1329419414723736073, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Eigen D, Ranzato M A, Sutskever I. Learning factored representations in a deep mixture of experts[J]. arXiv preprint, arXiv: 1312.4313, 2013, articleTitle=null, refAbstract=null), Reference(id=1329419414790844938, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A. Attention is all you need[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2017: 6000−6010, articleTitle=null, refAbstract=null), Reference(id=1329419414849565196, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Sijie, Li Zhizhong, Xiong Yuanjun, et al. Convolutional sequence generation for skeleton-based action synthesis[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 4393−4401, articleTitle=null, refAbstract=null), Reference(id=1329419414908285453, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Sohn K, Lee H, Yan X. Learning structured output representation using deep conditional generative models[C]//Proc of the 29th Int Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2015: 3483–3491, articleTitle=null, refAbstract=null), Reference(id=1329419414962811406, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Tianhan, Takano W. Graph stacked hourglass networks for 3D human pose estimation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE , 2021: 16100−16109, articleTitle=null, refAbstract=null), Reference(id=1329419415038308879, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Hochreiter S. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735−1780, articleTitle=null, refAbstract=null), Reference(id=1329419415105417744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Yan, Wang Jiahao, Zhang Yan, et al. SAGA: Stochastic whole-body grasping with contact[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 257−274, articleTitle=null, refAbstract=null), Reference(id=1329419415159943698, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Ghosh A, Dabral R, Golyanik V, et al. IMoS: Intent-driven full-body motion synthesis for human-object interactions[J]. Computer Graphics Forum, 2023, 42(2): 1−12, articleTitle=null, refAbstract=null), Reference(id=1329419415256412691, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=57, 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. New York: ACM, 2021: 8748−8763, articleTitle=null, refAbstract=null), Reference(id=1329419415327715860, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Siyuan, Wang Zan, Li Puhao, et al. Diffusion-based generation, optimization, and planning in 3D scenes[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 13253−13263, articleTitle=null, refAbstract=null), Reference(id=1329419415382241813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Jiaman, Wu Jiajun, Liu C K. Object motion guided human motion synthesis[J]. ACM Transactions on Graphics, 2023, 42(6): 1−11, articleTitle=null, refAbstract=null), Reference(id=1329419415466127894, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Nan, Zhang Zhiyuan, Li Hongjie, et al. Scaling up dynamic human-scene interaction modeling[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 1737−1747, articleTitle=null, refAbstract=null), Reference(id=1329419415550013975, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Ze, Zhang Zheng, Cao Yue, et al. Group-free 3D object detection via transformers[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 2929−2938, articleTitle=null, refAbstract=null), Reference(id=1329419415608734233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Achlioptas P, Abdelreheem A, Xia Fei, et al. Referit3d: Neural listeners for fine-grained 3D object identification in real world scenes[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 422−440, articleTitle=null, refAbstract=null), Reference(id=1329419415675843098, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Zan, Chen Yixin, Jia Baoxiong, et al. Move as you say interact as you can: Language-guided human motion generation with scene affordance[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 433−444, articleTitle=null, refAbstract=null), Reference(id=1329419415734563355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi Hongwei, Thies J, Black M J, et al. Generating human interaction motions in scenes with text control[C]//Proc of the 18th European Conf on Computer Vision. Berlin: Springer, 2024: 246−263, articleTitle=null, refAbstract=null), Reference(id=1329419415797477916, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yan, Tang Siyu. The wanderings of odysseus in 3D scenes[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 20449−20459, articleTitle=null, refAbstract=null), Reference(id=1329419415864586781, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Kaifeng, Zhang Yan, Wang Shaofei, et al. Synthesizing diverse human motions in 3D indoor scenes[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 14692−14703, articleTitle=null, refAbstract=null), Reference(id=1329419415940084254, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Jiaman, Clegg A, Mottaghi R, et al. Controllable human-object interaction synthesis[C]//Proc of the 18th European Conf on Computer Vision. Berlin: Springer, 2024: 54−72, articleTitle=null, refAbstract=null), Reference(id=1329419415998804512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Zeng Lingan, Huang Guohong, Wei Yilin, et al. ChainHOI: Joint-based kinematic chain modeling for human-object interaction generation[J]. arXiv preprint, arXiv: 2503.13130, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419416057524769, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Karunratanakul K, Yang Jinlong, Zhang Yan, et al. Grasping field: Learning implicit representations for human grasps[C]//Proc of the Int Conf on 3D Vision. Piscataway, NJ: IEEE, 2020: 333−344, articleTitle=null, refAbstract=null), Reference(id=1329419416116245026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Christen S, Hampali S, Sener F, et al. Diffh2o: Diffusion-based synthesis of hand-object interactions from textual descriptions[C]//Proc of the SIGGRAPH Asia Conf. New York: ACM, 2024: 1−11, articleTitle=null, refAbstract=null), Reference(id=1329419416179159587, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Bohg J, Morales A, Asfour T, et al. Data-driven grasp synthesis−A survey[J]. IEEE Transactions on Robotics, 2013, 30(2): 289−309, articleTitle=null, refAbstract=null), Reference(id=1329419416263045669, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Napier J R. The prehensile movements of the human hand[C]//Proc of the Classic Papers in Orthopaedics. Berlin: Springer, 2014: 343−345, articleTitle=null, refAbstract=null), Reference(id=1329419416334348839, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Hsiao K, Lozano-Perez T. Imitation learning of whole-body grasps[C]//Proc of the IEEE/RSJ Int Conf on Intelligent Robots and Systems. Piscataway, NJ: IEEE, 2006: 5657−5662, articleTitle=null, refAbstract=null), Reference(id=1329419416393069096, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Taheri O, Ghorbani N, Black M J, et al. GRAB: A dataset of whole-body human grasping of objects[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 581−600, articleTitle=null, refAbstract=null), Reference(id=1329419416460177961, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Bhatnagar B L, Xie X, Petrov I A, et al. BEHAVE: Dataset and method for tracking human object interactions[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 15914−15925, articleTitle=null, refAbstract=null), Reference(id=1329419416544064042, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Sirui, Li Zhengyuan, Wang Yuxiong, et al. InterDiff: Generating 3D human-object interactions with physics-informed diffusion[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 14928−14940, articleTitle=null, refAbstract=null), Reference(id=1329419416602784300, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yinghao, Taheri O, Black M J, et al. InterCap: Joint markerless 3D tracking of humans and objects in interaction[C]//Proc of the 44th DAGM German Conf. Berlin: Springer, 2024, 132: 2551−2566, articleTitle=null, refAbstract=null), Reference(id=1329419416674087469, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Ahuja C, Lee D W, Nakano Y I, et al. Style transfer for co-speech gesture animation: A multi-speaker conditional-mixture approach[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springe, 2020: 248−265, articleTitle=null, refAbstract=null), Reference(id=1329419416745390638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Xi, Li Gen, Kuo Yenling, et al. Reconstructing action-conditioned human-object interactions using commonsense knowledge priors[C]//Proc of the Int Conf on 3D Vision. Piscataway, NJ: IEEE, 2022: 353−362, articleTitle=null, refAbstract=null), Reference(id=1329419416799916591, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Sung K, Shirley P, Rosenberg B R. Experiencing aspects of games programming in an introductory computer graphics class[J]. ACM SIGCSE Bulletin, 2007, 39(1): 249−253, articleTitle=null, refAbstract=null), Reference(id=1329419416862831152, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Hanser E, Mc Kevitt P, Lunney T, et al. Scenemaker: Intelligent multimodal visualisation of natural language scripts[C]//Proc of the 20th Irish Conf on Artificial Intelligence and Cognitive Science. Berlin: Springer, 2009: 144−153, articleTitle=null, refAbstract=null), Reference(id=1329419416921551409, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Charles R Q, Su Hao, Kaichun M, et al. PointNet: Deep learning on point sets for 3D classification and segmentation[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 77−85, articleTitle=null, refAbstract=null), Reference(id=1329419416988660274, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Hengshuang, Jiang Li, Jia Jiaya, et al. Point Transformer[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 16239−16248, articleTitle=null, refAbstract=null), Reference(id=1329419417064157748, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Hart P E, Nilsson N J, Raphael B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics, 1968, 4(2): 100−107, articleTitle=null, refAbstract=null), Reference(id=1329419417156432437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Tevet G, Gordon B, Hertz A, et al. Motionclip: Exposing human motion generation to clip space[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 358−374, articleTitle=null, refAbstract=null), Reference(id=1329419417219346999, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Biao, Chen Xin, Liu Wen, et al. Motiongpt: Human motion as a foreign language[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. New York: Curran Associates 2023: 20067−20079, articleTitle=null, refAbstract=null), Reference(id=1329419417286455864, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Chuan, Mu Yuxuan, Javed M G, et al. Momask: Generative masked modeling of 3D human motions[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 1900−1910, articleTitle=null, refAbstract=null), Reference(id=1329419417366147641, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Kenton J D M W C, Toutanova L K. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proc of the NAACL-HLT. Stroudsburg, PA: ACL, 2019: 4171−4186, articleTitle=null, refAbstract=null), Reference(id=1329419417424867899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Mandery C, Terlemez Ö, Do M, et al. The KIT whole-body human motion database[C]//Proc of the Int Conf on Advanced Robotics. Piscataway, NJ: IEEE, 2015: 329−336, articleTitle=null, refAbstract=null), Reference(id=1329419417487782460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Savva M, Chang A X, Hanrahan P, et al. PiGraphs: Learning interaction snapshots from observations[J]. ACM Transactions on Graphics, 2016. https://dl.acm.org/doi/10.1145/2897824.2925867, articleTitle=null, refAbstract=null), Reference(id=1329419417550697021, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Nießner M, Zollhöfer M, Izadi S, et al. Real-time 3D reconstruction at scale using voxel hashing[J]. ACM Transactions on Graphics, 2013, 32(6): 1−11, articleTitle=null, refAbstract=null), Reference(id=1329419417626194494, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Hassan M, Choutas V, Tzionas D, et al. Resolving 3D human pose ambiguities with 3D scene constraints[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 2282−2292, articleTitle=null, refAbstract=null), Reference(id=1329419417684914752, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Monszpart A, Guerrero P, Ceylan D, et al. iMapper: Interaction-guided scene mapping from monocular videos[J]. ACM Transactions on Graphics, 2019, 38(4): 1−15, articleTitle=null, refAbstract=null), Reference(id=1329419417747829313, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Guzov V, Mir A, Sattler T, et al. Human poseitioning system (HPS): 3D human pose estimation and self-localization in large scenes from body-mounted sensors[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 4318−4329, articleTitle=null, refAbstract=null), Reference(id=1329419417814938178, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Juliani A, Berges V P, Teng E, et al. Unity: A general platform for intelligent agents[J]. arXiv preprint, arXiv: 1809.02627, 2018, articleTitle=null, refAbstract=null), Reference(id=1329419417886241348, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Mahmood N, Ghorbani N, Troje N F, et al. AMASS: Archive of motion capture as surface shapes[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 5441−5450, articleTitle=null, refAbstract=null), Reference(id=1329419417940767301, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai A, Chang A X, Savva M, et al. ScanNet: Richly-annotated 3D reconstructions of indoor scenes[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 5828−5839, articleTitle=null, refAbstract=null), Reference(id=1329419418012070470, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Nan, Liu Tengyu, Cao Zhexuan, et al. Full-body articulated human-object interaction[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 9331−9342, articleTitle=null, refAbstract=null), Reference(id=1329419418074985031, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Chang A, Dai A, Funkhouser T, et al. Matterport3D: Learning from RGB-D data in indoor environments[C]//Proc of Int Conf on 3D Vision. Piscataway, NJ: IEEE, 2017: 667−676, articleTitle=null, refAbstract=null), Reference(id=1329419418146288200, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Straub J, Whelan T, Ma Lingni, et al. The Replica dataset: A digital replica of indoor spaces[J]. arXiv preprint, arXiv: 1906.05797, 2019, articleTitle=null, refAbstract=null), Reference(id=1329419418209202762, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Ionescu C, Papava D, Olaru V, et al. Human3.6m: Large scale datasets and predictive methods for 3D human sensing in natural environments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 36(7): 1325−1339, articleTitle=null, refAbstract=null), Reference(id=1329419418280505931, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Zhongang, Ren Daxuan, Zeng Ailing, et al. HuMMan: Multi-modal 4D human dataset for versatile sensing and modeling[C]//Proc of the European Conf on Computer Vision. Berlin: Springer, 2022: 557−577, articleTitle=null, refAbstract=null), Reference(id=1329419418347614796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Jing, Zeng Ailing, Lu Shunlin, et al. Motion-x: A large-scale 3D expressive whole-body human motion dataset[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. New York: Curran Associate, 2023: 25268−25280, articleTitle=null, refAbstract=null), Reference(id=1329419418431500878, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Chuan, Zuo Xinxin, Wang Sen, et al. Action2motion: Conditioned generation of 3D human motions[C]//Proc of the 28th ACM Int Conf on Multimedia. New York: ACM, 2020: 2021−2029, articleTitle=null, refAbstract=null), Reference(id=1329419418494415439, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Ao Tenglong, Zhang Zeyi, Liu Libin. GestureDiffuCLIP: Gesture diffusion model with clip latents[J]. ACM Transactions on Graphics, 2023, 42(4): 1−18, articleTitle=null, refAbstract=null), Reference(id=1329419418565718608, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Sichen, Wu Zhiyong, Li Minglei, et al. DiffuseStyleGesture: Stylized audio-driven co-speech gesture generation with diffusion models[C]//Proc of the 3rd Int Joint Conf on Artificial Intelligence. Berlin: Springer, 2023 5860−5868, articleTitle=null, refAbstract=null), Reference(id=1329419418616050258, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=李晨光, 温玉辉, 景宇宸, 等. 体型感知的音乐驱动舞蹈动作风格化生成[J/OL]. 计算机辅助设计与图形学学报, 2024[2025-03-02]. https: //www.jcad.cn/cn/article/pdf/preview/10.3724/SP.J.1089.2024-00492.pdf, articleTitle=null, refAbstract=null), Reference(id=1329419418674770515, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Chenguang, Wen Yuhui, Jing Yuchen, et al. Shape-aware stylized dance motion generation driven by music[J/OL]. Journal of Computer-Aided Design & Computer Graphics, 2024[2025-03-02]. https://www.jcad.cn/cn/article/pdf/preview/10.3724/SP.J.1089.2024-00492.pdf (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419418741879380, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Sichen, Xu Zunnan, Xue Haiwei, et al. Freetalker: Controllable speech and text-driven gesture generation based on diffusion models for enhanced speaker naturalness[C]//Proc of the IEEE Int Conf on Acoustics, Speech and Signal Processing. Piscataway, NJ: IEEE, 2024: 7945−7949, articleTitle=null, refAbstract=null), Reference(id=1329419418825765462, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Bohong Li Yumeng, Ding Yaoxiang, et al. Enabling synergistic full-body control in prompt-based co-speech motion generation[C]//Proc of the 32nd ACM Int Conf on Multimedia. New York: ACM, 2024: 6774−6783, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329419407517921671, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, xref=1, ext=[AuthorCompanyExt(id=1329419407530504584, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407517921671, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Advanced Rail Autonomous Operation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1329419407538893193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407517921671, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1先进轨道交通自主运行全国重点实验室(北京交通大学) 北京 100044)]), AuthorCompany(id=1329419407618584970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, xref=2, ext=[AuthorCompanyExt(id=1329419407631167883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1329419407652139404, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, companyId=1329419407618584970, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2交通数据挖掘与具身智能北京市重点实验室(北京交通大学) 北京 100044)])], figs=[ArticleFig(id=1329419409367609775, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 1, caption=
Conditional human motion generation method, figureFileSmall=NXj022XU0PJY+ufNl1pS2w==, figureFileBig=rqu6xzbwuy67G1v1iy2M7A==, tableContent=null), ArticleFig(id=1329419409430524337, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图1, caption=
条件人体动作生成方法, figureFileSmall=NXj022XU0PJY+ufNl1pS2w==, figureFileBig=rqu6xzbwuy67G1v1iy2M7A==, tableContent=null), ArticleFig(id=1329419409640239537, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 2, caption=
Overview of the discriminator[16], figureFileSmall=sY+2GVUrV6eGuOjIVjfMTg==, figureFileBig=y8GK3+IEdWqBY2+agaJmEQ==, tableContent=null), ArticleFig(id=1329419409724125620, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图2, caption=
鉴别器概述[16], figureFileSmall=sY+2GVUrV6eGuOjIVjfMTg==, figureFileBig=y8GK3+IEdWqBY2+agaJmEQ==, tableContent=null), ArticleFig(id=1329419409791234485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 3, caption=
Three-stage network architecture[32], figureFileSmall=/F+MaRxmUBdcRKyqU/kJ4w==, figureFileBig=Y/nwAvLv0sEgj5CftS0kKg==, tableContent=null), ArticleFig(id=1329419409858343350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图3, caption=
3阶段网络架构[32], figureFileSmall=/F+MaRxmUBdcRKyqU/kJ4w==, figureFileBig=Y/nwAvLv0sEgj5CftS0kKg==, tableContent=null), ArticleFig(id=1329419409938035127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 4, caption=
HUMANISE network architecture[19], figureFileSmall=vLUo7I1NnGT8xPuTwxz6sA==, figureFileBig=lK9qE+U63Pb8DABiJGVlqg==, tableContent=null), ArticleFig(id=1329419410063864250, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图4, caption=
HUMANISE网络架构[19], figureFileSmall=vLUo7I1NnGT8xPuTwxz6sA==, figureFileBig=lK9qE+U63Pb8DABiJGVlqg==, tableContent=null), ArticleFig(id=1329419410151944635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 5, caption=
Network architecture[62], figureFileSmall=Ufejs/G8gnYQ+iw+uJP10A==, figureFileBig=yyOki6REB915NvOS1G7AMw==, tableContent=null), ArticleFig(id=1329419410256802236, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图5, caption=
网络架构[62], figureFileSmall=Ufejs/G8gnYQ+iw+uJP10A==, figureFileBig=yyOki6REB915NvOS1G7AMw==, tableContent=null), ArticleFig(id=1329419410315522493, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 6, caption=
Development process of action generation technology based on scene interaction, figureFileSmall=vckSTDAQHi0xbpN1UJtFRw==, figureFileBig=AsEcZp3SzUpnFGW/eQCD3w==, tableContent=null), ArticleFig(id=1329419410420380095, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图6, caption=
基于场景交互的动作生成技术发展历程, figureFileSmall=vckSTDAQHi0xbpN1UJtFRw==, figureFileBig=AsEcZp3SzUpnFGW/eQCD3w==, tableContent=null), ArticleFig(id=1329419410491683264, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 7, caption=
Effectiveness illustration of interaction motion generation models, figureFileSmall=2Ry64/sa4CA3NLU9K0E4ow==, figureFileBig=QgJnkIchFR4mr9qIpdOYJQ==, tableContent=null), ArticleFig(id=1329419410550403521, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图7, caption=
交互运动生成模型效果示意图, figureFileSmall=2Ry64/sa4CA3NLU9K0E4ow==, figureFileBig=QgJnkIchFR4mr9qIpdOYJQ==, tableContent=null), ArticleFig(id=1329419410625900994, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 8, caption=
Illustration of dynamic-static interaction tasks, figureFileSmall=ziHOnVGoncXj9KWHELL/SQ==, figureFileBig=0xqJTHGCDWvgSzGl+4Zonw==, tableContent=null), ArticleFig(id=1329419410684621251, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图8, caption=
动静交互任务示意图, figureFileSmall=ziHOnVGoncXj9KWHELL/SQ==, figureFileBig=0xqJTHGCDWvgSzGl+4Zonw==, tableContent=null), ArticleFig(id=1329419410739147204, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Figure 9, caption=
Collision model of cylinder between human and object[16], figureFileSmall=Jx1c6gb7Jm0xvIKHzqK/WA==, figureFileBig=B1+wGuo5AFfJsagpYqEMsQ==, tableContent=null), ArticleFig(id=1329419410806256070, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=图9, caption=
人与物体的圆柱体碰撞模型[16], figureFileSmall=Jx1c6gb7Jm0xvIKHzqK/WA==, figureFileBig=B1+wGuo5AFfJsagpYqEMsQ==, tableContent=null), ArticleFig(id=1329419410877559239, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Table 1, caption=
Effectiveness Comparison of Different Human-Scene Interaction Motion Generation Models
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 模型框架 | 无碰撞分数↑ | 接触分数↑ |
|---|
| HUMANISE[19] | CVAE | 99.77 | 84.07 |
| 文献[39] | Regression | 98.38 | 92.16 |
| 文献[62] | Diffusion | 99.69 | 96.02 |
), ArticleFig(id=1329419410936279496, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=表1, caption=
不同人与场景交互运动生成模型的效果对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 模型框架 | 无碰撞分数↑ | 接触分数↑ |
|---|
| HUMANISE[19] | CVAE | 99.77 | 84.07 |
| 文献[39] | Regression | 98.38 | 92.16 |
| 文献[62] | Diffusion | 99.69 | 96.02 |
), ArticleFig(id=1329419410990805449, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Table 2, caption=
Summary of Human-Scene Interaction Motion Methods
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 数据表示 | 模型 | 数据集 | 开源情况 |
|---|
| 文献[37] | Kpts.(3D) | Regression | CMU-Mocap, WBHM | √ |
| 文献[32] | Kpts.(3D) | VAE | GTA-IM, PROX | × |
| 文献[15] | Rot. | VAE | Matterport3D, PROX | √ |
| 文献[16] | Kpts.(3D) | GAN | GTA-IM, PROX | × |
| 文献[17] | Rot. | VAE | SAMP | √ |
| 文献[18] | Rot. | VAE | Matterport3D, PROX | × |
| 文献[64] | Kpts.(3D) | RL | AMASS | √ |
| 文献[35] | Rot. | VAE | GRAB | √ |
| 文献[54] | Kpts.(3D) | VAE | GRAB | √ |
| 文献[38] | Rot. | Regression | Couch | √ |
| 文献[39] | Kpts.(3D) | Regression | GTA-IM, PROX | √ |
| 文献[19] | Rot. | VAE | HUMANISE, PROX | √ |
| 文献[55] | Rot. | VAE | GRAB | √ |
| 文献[57] | Rot. | Diffusion | PROX | √ |
| 文献[31] | Rot. | Regression | CIRCLE | × |
| 文献[65] | Kpts.(3D) | RL, VAE | AMASS, SAMP | √ |
| 文献[58] | Kpts.(3D) | Diffusion | OMOMO | √ |
| 文献[59] | Kpts.(3D) | Diffusion | TRUMANS | √ |
| 文献[34] | Rot. | Diffusion | AMASS, HUMANISE | 仅推理 |
| 文献[62] | Rot. | Diffusion | HumanML3D, HUMANISE | √ |
| 文献[33] | Rot. | Diffusion | Behave, InterCap | × |
| 文献[63] | Kpts.(3D) | Diffusion | SAMP, 3D-FRONT | 仅推理 |
| 文献[66] | Rot. | Diffusion | OMOMO, 3D-FUTURE | √ |
| 文献[67] | Kpts.(3D) | Diffusion | BEHAVE, OMOMO | × |
), ArticleFig(id=1329419411066302922, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=表2, caption=
人与场景交互运动方法汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 数据表示 | 模型 | 数据集 | 开源情况 |
|---|
| 文献[37] | Kpts.(3D) | Regression | CMU-Mocap, WBHM | √ |
| 文献[32] | Kpts.(3D) | VAE | GTA-IM, PROX | × |
| 文献[15] | Rot. | VAE | Matterport3D, PROX | √ |
| 文献[16] | Kpts.(3D) | GAN | GTA-IM, PROX | × |
| 文献[17] | Rot. | VAE | SAMP | √ |
| 文献[18] | Rot. | VAE | Matterport3D, PROX | × |
| 文献[64] | Kpts.(3D) | RL | AMASS | √ |
| 文献[35] | Rot. | VAE | GRAB | √ |
| 文献[54] | Kpts.(3D) | VAE | GRAB | √ |
| 文献[38] | Rot. | Regression | Couch | √ |
| 文献[39] | Kpts.(3D) | Regression | GTA-IM, PROX | √ |
| 文献[19] | Rot. | VAE | HUMANISE, PROX | √ |
| 文献[55] | Rot. | VAE | GRAB | √ |
| 文献[57] | Rot. | Diffusion | PROX | √ |
| 文献[31] | Rot. | Regression | CIRCLE | × |
| 文献[65] | Kpts.(3D) | RL, VAE | AMASS, SAMP | √ |
| 文献[58] | Kpts.(3D) | Diffusion | OMOMO | √ |
| 文献[59] | Kpts.(3D) | Diffusion | TRUMANS | √ |
| 文献[34] | Rot. | Diffusion | AMASS, HUMANISE | 仅推理 |
| 文献[62] | Rot. | Diffusion | HumanML3D, HUMANISE | √ |
| 文献[33] | Rot. | Diffusion | Behave, InterCap | × |
| 文献[63] | Kpts.(3D) | Diffusion | SAMP, 3D-FRONT | 仅推理 |
| 文献[66] | Rot. | Diffusion | OMOMO, 3D-FUTURE | √ |
| 文献[67] | Kpts.(3D) | Diffusion | BEHAVE, OMOMO | × |
), ArticleFig(id=1329419411137606092, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=EN, label=Table 3, caption=
Summary of Interactive Dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 收集方式 | 数据表示 | 受试者人数 | 序列数 | 帧数 | 时间/h | 其他信息 |
|---|
| WBHM | Marker-based | Rot. | 43 | 3704 | 0.7×106 | 7.68 | 41个物体 |
| PiGraph | Markerless | Kpts.(3D) | 5 | 63 | 0.1×106 | 2 | 49个场景和物体 |
| PROX | Markerless | Rot. | 20 | 60 | 0.1×106 | 1 | 12个场景 |
| i3DB | Pseudo-labeling | Kpts.(3D) | 1 | | | | 15个场景 |
| GTA-IM | Marker-based | Kpts.(3D) | 50 | 119 | 1×106 | | 10个场景 |
| GRAB | Marker-based | Rot. | 10 | 1334 | 1.6×106 | 3.8 | 51个物体 |
| HPS | Marker-based | Rot. | 7 | | 0.3×106 | | 8个大场景 |
| SAMP | Marker-based | Rot. | 1 | | 0.185×106 | 0.83 | 7个物体 |
| COUCH | Marker-based | Rot. | 6 | >500 | | 3 | 3个椅子 |
| HUMANISE | Marker-based | Rot. | | 19600 | 1.2×106 | | 643个场景 |
| BEHAVE | Markerless | Rot. | 8 | 321 | 0.015×106 | 4.2 | 20个物体 |
| CIRCLE | Marker-based | Rot. | 5 | >7000 | 4.3×106 | 10 | 9个场景 |
| OMOMO | Marker-based | Rot. | 17 | 16900 | 4.3×106 | 10.1 | 15个物体 |
| CHAIRS | Marker-based | Rot. | 46 | 1390 | 1.8×106 | 17.3 | 81个物体 |
| InterCap | Markerless | Rot. | 10 | 223 | 0.067×106 | 0.62 | 10个物体 |
| TRUMANS | Markerless | Rot. | 7 | | 1.6×106 | 15 | 120个场景和物体 |
), ArticleFig(id=1329419411204714957, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419404724515177, language=CN, label=表3, caption=
交互数据集汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 收集方式 | 数据表示 | 受试者人数 | 序列数 | 帧数 | 时间/h | 其他信息 |
|---|
| WBHM | Marker-based | Rot. | 43 | 3704 | 0.7×106 | 7.68 | 41个物体 |
| PiGraph | Markerless | Kpts.(3D) | 5 | 63 | 0.1×106 | 2 | 49个场景和物体 |
| PROX | Markerless | Rot. | 20 | 60 | 0.1×106 | 1 | 12个场景 |
| i3DB | Pseudo-labeling | Kpts.(3D) | 1 | | | | 15个场景 |
| GTA-IM | Marker-based | Kpts.(3D) | 50 | 119 | 1×106 | | 10个场景 |
| GRAB | Marker-based | Rot. | 10 | 1334 | 1.6×106 | 3.8 | 51个物体 |
| HPS | Marker-based | Rot. | 7 | | 0.3×106 | | 8个大场景 |
| SAMP | Marker-based | Rot. | 1 | | 0.185×106 | 0.83 | 7个物体 |
| COUCH | Marker-based | Rot. | 6 | >500 | | 3 | 3个椅子 |
| HUMANISE | Marker-based | Rot. | | 19600 | 1.2×106 | | 643个场景 |
| BEHAVE | Markerless | Rot. | 8 | 321 | 0.015×106 | 4.2 | 20个物体 |
| CIRCLE | Marker-based | Rot. | 5 | >7000 | 4.3×106 | 10 | 9个场景 |
| OMOMO | Marker-based | Rot. | 17 | 16900 | 4.3×106 | 10.1 | 15个物体 |
| CHAIRS | Marker-based | Rot. | 46 | 1390 | 1.8×106 | 17.3 | 81个物体 |
| InterCap | Markerless | Rot. | 10 | 223 | 0.067×106 | 0.62 | 10个物体 |
| TRUMANS | Markerless | Rot. | 7 | | 1.6×106 | 15 | 120个场景和物体 |
)], 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/issn1000-1239.202550352, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550352, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202550352, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202550352, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1774972800000, fullTextJson=null, articleText=null, reference=null)