概要
人工智能生成内容(AIGC)是近年来人工智能(AI)领域一个研究热点,它有望取代人类以较低成本高效率执行内容生成工作,如音乐、绘画、多模态内容生成、新闻文章、总结报告、股评摘要,以至元宇宙中的内容生成和数字人。AIGC为未来AI发展和实现提供了一条新的技术路径。
在此背景下,《信息与电子工程前沿(英文)》期刊组织了一期关于AIGC最新进展的特刊。本期特刊关注AIGC理论、算法、应用及相关领域。通过吸引高质量论文,我们希望帮助学术界和工业界研究人员更深入了解AIGC背后的基本理论及其潜在应用,激励更多研究人员加入并推进AIGC领域的研究。因此,我们就以下主题(但不限于)征集论文:(1)AI生成音乐;(2)AI生成绘画;(3)AI对话模型;(4)AI新闻摘要;(5)AI与元宇宙;(6)AI与数字人;(7)AI图像编辑;(8)AI生成短视频;(9)AI生成多媒体内容;(10)ChatGPT相关工作。经严格评审,选出12篇论文,包括1篇评论、1篇观点、3篇综述、6篇研究和1篇通讯。我们将其划分为3个主要部分:ChatGPT、扩散模型、提示学习和多模态。
总体而言,本期特刊涵盖了与AIGC开发和应用相关的广泛研究主题,包括人工智能图像/文本生成、三维内容创建、以用户为中心的图形设计、特定风格的音乐生成,以及与因果表征学习、高阶扩散模型相关的工作。此外,还详细调研了概率扩散模型、提示学习和ChatGPT。
最后,感谢所有作者对本期特刊的支持,特别感谢所有评审人对专刊投稿富有见地的意见和有益建议。
Article PDF
Author information
Authors and Affiliations
Corresponding author
Additional information
Junping ZHANG is a professor with the School of Computer Science, Fudan University. He received the BS degree in automation from Xiangtan University, China, in 1992, the MS degree in control theory and control engineering from Hunan University, China, in 2000, and the PhD degree in intelligent systems and pattern recognition from the Institution of Automation, Chinese Academy of Sciences, in 2003. He has more than 100 publications in major journals and international conferences, including IEEE TPAMI, IEEE TNNLS, IEEE TCYB, NeurIPS, ICCV, CVPR, ICML, and IJCAI. He has been an associate editor of IEEE Intell Syst since 2009. His research interests include machine learning, image processing, biometric authentication, and intelligent transportation systems.
Lingyun SUN is a professor at Zhejiang University. He is the director of the International Design Institute, Ng Teng Fong Chaired Professor, and the director of the ZJU–SUTD Innovation, Design and Entrepreneurship Alliance. He has over 100 publications in leading academic journals and international conferences, including Des Sci, AAAI, and ACM CHI. His projects have won many awards, including the SAIL award in 2021. His research interests include design intelligence, generative AI, and information and interaction design.
Cong JIN is an associate professor with the School of Information and Communication Engineering, Communication University of China. She received the BE, MAS, and PhD degrees in communication and information systems from Communication University of China in 2010, 2013, and 2021, respectively. She has been presiding over an undertaking of the youth, general, and key projects of the National Natural Science Foundation, the Xiaomi Joint Fund of the Beijing Natural Science Foundation, and National Key Research and Development Projects. She has published more than 40 papers in IEEE Trans, ACM MM, and other international journals and conferences. She has served as a session chair or a program committee member for several major international conferences and as an associate editor or reviewer for several leading journals. Her research interests include hybrid man–machine performance, reinforcement learning, and music AI.
Junbin GAO is a professor of big data analytics at the University of Sydney Business School, University of Sydney, and was a professor in computer science at the School of Computing and Mathematics, Charles Sturt University, Australia. He graduated from Huazhong University of Science and Technology (HUST), China, in 1982 with a BS degree in computational mathematics and obtained his PhD degree from Dalian University of Technology, China, in 1991. He was a lecturer in computer science from 2001 to 2005 at University of New England, Australia. From 1982 to 2001 he was an associate lecturer, lecturer, associate professor, and professor in the Department of Mathematics, HUST. He has published more than 160 papers in major journals and international conferences, including IEEE TPAMI, IEEE TNNLS, IEEE TCYB, NeurIPS, CVPR, ICML, AAAI, and IJCAI. His main research interests include machine learning, data analytics, Bayesian learning and inference, and image analysis.
Xiaobing LI is a professor with the Central Conservatory of Music, the director of the Department of AI Music and Music Information Technology, the chair of the China Computer Federation (CCF) Computational Art Branch, the chair of the Chinese Association for Artificial Intelligence (CAAI) Art and the Artificial Intelligence Commission, a leading talent in philosophy and social sciences under the Ten Thousand Talent Program, a member of the Four-Batch Talent Project, and the Chief Expert of Major Projects of the National Social Science Foundation of China. Graduating from the Composition Department of the Central Conservatory of Music, he studied under the guide of Prof. Zuqiang WU. He has won domestic and international awards such as the Chinese Golden Bell Award for Music, the Wenhua Award of the Ministry of Culture, the Wenhua Composition Award, the First Prize of the National Opera and Dance Drama, and the National Five One Project Award. In 2008, he held the large-scale real-life concert at the Great Wall. In 2019, he held the large-scale real-life Concert of the Future at the Yan’an Luxun Academy of Fine Art.
Jiebo LUO is currently the Albert Arendt Hopeman Professor of Engineering and professor of computer science with University of Rochester, USA, which he joined in 2011 after a prolific career of 15 years with Kodak Research Laboratories. He has authored over 600 technical papers and holds more than 90 US patents. He has been involved in many technical conferences, including serving as a program co-chair of ACM Multimedia 2010, IEEE CVPR 2012, ACM ICMR 2016, and IEEE ICIP 2017, and as a general co-chair of ACM Multimedia 2018 and IEEE ICME 2024. He was on the editorial boards of IEEE TPAMI, IEEE TMM, IEEE TCSVT, IEEE Trans Big Data, ACM TIST, Patt Recogn, and Intell Med. He was the Editor-in-Chief of IEEE TMM during 2020–2022. He is a fellow of NAI, ACM, AAAI, IEEE, SPIE, and IAPR. His research interests include computer vision, natural language processing, machine learning, data mining, computational social science, and digital health.
Zhigeng PAN is a professor at Nanjing University of Information Science and Technology, China. He received the PhD degree in 1993. He has been a full professor with Zhejiang University since 1996. He has published more than 100 technical papers in important journals and conferences, including IEEE TPAMI, TVCG, IEEE MM, ACM MM, and IEEE VR. He is a member of ACM SIGGRAPH. He is also a program co-chair of CASA 2011, SIGGRAPH Asia 2011 (Sketches and Posters), IEEE VR 2013, and SIGGRAPH Asia 2016 (Symposium on Education), and a conference co-chair of VRCAI 2012, VRCAI 2013, VRCAI 2015, and CW 2016. He is the Editor-in-Chief of Metaverse. His research interests include virtual reality, computer graphics, and human–computer interaction.
Ying TANG is a full professor and the Undergraduate Program Chair of Electrical and Computer Engineering at Rowan University, USA. She received the BS and MS degrees from Northeastern University, China, in 1996 and 1998, respectively, and the PhD degree from the New Jersey Institute of Technology, USA in 2001. Her work has been continuously supported by NSF, EPA, US Army, DOT, private foundations, and industry. She has three US patents, and over 230 peer-reviewed publications, including 77 journal articles, two edited books, and six book/encyclopedia chapters. She is presently an associate editor of IEEE TSMCS, IEEE TIV, IEEE TCSS, and Disc Artif Intell. Her research interests include cyber-physical social systems, extended reality, intelligent learning environments, modeling and adaptive control for computer-integrated systems, and sustainable production automation.
Jingdong WANG is chief scientist for computer vision with Baidu. Before joining Baidu, he was a senior principal research manager with Microsoft Research Asia. His representative works include deep high-resolution network (HRNet), object-contextual representations for semantic segmentation (OCRNet), and neighborhood graph search (SPTAG) for large-scale vector search. He has been serving or served as an associate editor of IEEE TPAMI, IJCV, ACM TOMM, IEEE TMM, and IEEE TCSVT, and as an area chair of leading conferences in vision, multimedia, and AI, such as CVPR, ICCV, NeurIPS, ECCV, ACM MM, IJCAI, and AAAI. He was elected as an ACM distinguished member, a fellow of IAPR, and a fellow of IEEE, for his contributions to visual content understanding and retrieval. His areas of interest are computer vision, deep learning, and multimedia search.
Rights and permissions
About this article
Cite this article
Zhang, J., Sun, L., Jin, C. et al. Recent advances in artificial intelligence generated content. Front Inform Technol Electron Eng 25, 1–5 (2024). https://doi.org/10.1631/FITEE.2410000
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2410000