Nantes, France
July 04, 2025
Jointly with ICME
2025
Recent advances brought by AI-Generated Content (AIGC) have been an innovative engine for digital content generation, drawing more and more attention from both academia and industry. Across creative fields, AI has sparked new genres and experimentations in painting, music, film, storytelling, fashion and design. Researchers explore the concept of co-creation with AI systems as well as the ethical implications of AI generated images and texts. AI has been applied to art historical research and media studies. The aesthetic value of AI generated content and AI’s impact on art appreciation have also been a contended subject in recent scholarship. AI has not only exhibited creative potential, but also stimulated research from diverse perspectives of neuroscience, cognitive science, psychology, literature, art history, media and communication studies. Despite all these promising features of AI for Art, we still have to face the many challenges such as the biases in AI models, lack of transparency and explainability in algorithms, and copyright issues of training data and AI art works.
This is the 7th AIART workshop to be held in conjunction with ICME 2025 in Nantes, France, and it aims to bring forward cutting-edge technologies and most recent advances in the area of AI art as well as perspectives from neuroscience, cognitive science, psychology, literature, art history, media and communication studies.
The theme topic of AIART 2025 will be AI and Human Co-creativity. We plan to invite 5 keynote speakers to present their insightful perspectives on AI art.
We sincerely invite high-quality papers presenting or addressing issues related to AI art, including but not limited to the following topics:
Additionally, Best Paper Award will be given.
AIART 2025 is also launching a demo track for artists to showcase their creative artworks in the form of in-person art gallery. The demo track will provide a great opportunity for people to experience interactive artworks and communicate creative ideas. The submission guideline for the demo track follows that of the main ICME conference: https://2025.ieeeicme.org/author-information-and-submission-instructions/.
Supplemental files larger than 10M should be sent to wangyin@aifc.ngo via WeTransfer.
Paper Submission
Authors should prepare their manuscript according to the Guide for Authors of ICME available at Author Information and Submission Instructions: https://2025.ieeeicme.org/author-information-and-submission-instructions/
Submission address: https://cmt3.research.microsoft.com/ICMEW2025
Submissions due
|
April 1st, 2025
|
Workshop date
|
July 04, 2025
|
Keynote 1
Speaker:
Changwen Chen
Title:
Aesthetics Reasoning based on Multimodal LLM
Time:
TBD
Abstract:
The rapid progress of generative art has democratized the creation of visually pleasing imagery. However, achieving genuine artistic impact, a nature that can resonate with viewers on a deeper, more meaningful level, requires a sophisticated aesthetic sensibility. This sensibility involves a multi-faceted reasoning process that extends beyond simple visual appeal, has often been overlooked by current computational models. This talk presents an initial endeavor to capture such a complex process by investigating how the reasoning capability of Multimodal LLMs (MLLMs) can be effectively elicited for aesthetic judgment. Our recent research reveals a critical challenge: MLLMs exhibit a tendency towards hallucinations during aesthetic reasoning, characterized by subjective opinions and unsubstantiated artistic interpretations. We shall demonstrate that these limitations can be overcome by employing an evidence-based, objective reasoning process, as substantiated by the proposed baseline algorithm, ArtCoT. MLLMs prompted by this principle produce multi-faceted and in-depth aesthetic reasoning that aligns significantly better with human judgment. These findings have direct applications in areas such as AI art tutoring and as reward models for generative art. We hope the proposed aesthetics reasoning framework can ultimately pave the way for constructing AI systems that can truly understand, appreciate, and contribute to artistic pieces just like the human aesthetic judgment.
Biography:
Chang Wen Chen is currently Chair Professor of Visual Computing at The Hong Kong Polytechnic University. Before his current position, he served as Dean of the School of Science and Engineering at The Chinese University of Hong Kong, Shenzhen, from 2017 to 2020, and concurrently as Deputy Director at Peng Cheng Laboratory from 2018 to 2021. Previously, he was an Empire Innovation Professor at the State University of New York at Buffalo (SUNY) from 2008 to 2021 and the Allan Henry Endowed Chair Professor at the Florida Institute of Technology from 2003 to 2007. He received his BS degree from the University of Science and Technology of China in 1983, an MS degree from the University of Southern California in 1986, and his PhD degree from the University of Illinois at Urbana-Champaign (UIUC) in 1992.
He has served as Editor-in-Chief for IEEE Trans. Multimedia (2014-2016) and for IEEE Trans. Circuits and Systems for Video Technology (2006-2009). He has received many professional achievement awards, including ten (10) Best Paper Awards or Best Student Paper Awards, the prestigious Alexander von Humboldt Award in 2010, the SUNY Chancellor’s Award for Excellence in Scholarship and Creative Activities in 2016, the UIUC ECE Distinguished Alumni Award in 2019, and the ACM SIGMM Outstanding Technical Achievement Award in 2024. He is an IEEE Fellow, a SPIE Fellow, and a Member of Academia Europaea.
Keynote 2
Speaker:
Xinyuan Cai
Title:
After the Dawn: Challenges and Strategies for AI-Driven Creative Education
Time:
TBD
Abstract:
With the rapid advancement of artificial intelligence technologies, creative education now stands at the threshold of a profound transformation. After the Dawn: Challenges and Strategies for AI-Driven Creative Education explores the deep impacts of AI on art and design education, while uncovering the underlying challenges and potential pathways for reform. This is not merely a response to technological intervention in teaching, but a redefinition of the very concept of “creativity.”
This talk unfolds across three dimensions. First, it reviews the practical applications of AI in artistic creation, design tools, and educational platforms in the current era, revealing its advantages in improving efficiency and expanding the boundaries of creative thinking. Taking large language models such as DeepSeek and ARTI Designer as examples, we observe how these tools are capable of generating stylistically distinct and logically coherent textual and visual outputs, becoming “new collaborators” in the creative process. Second, the lecture delves into the structural issues AI brings to creative education—such as the weakening of students’ originality, increased technological dependency, shifts in the role of educators, and imbalances in assessment systems. Meanwhile, we must also confront the cognitive biases and semantic inaccuracies exhibited by models like DeepSeek in educational contexts, underscoring the urgent need for ethical frameworks and critical literacy. Finally, the lecture proposes a set of systematic strategies and recommendations—ranging from curriculum redesign, AI ethics education, interdisciplinary collaboration mechanisms, to re-training programs for educators—to help higher education institutions build a more open, flexible, and sustainable AI-driven creative education system.
“After the Dawn” symbolizes not only the illumination brought by technology, but also the clarity and choices faced by educators and learners in the age of intelligence. This talk aims to inspire deep reflection on the future direction of creative education and to promote the formation of an innovative educational paradigm that embraces technology while upholding humanistic values.
Biography:
Dr. Cai Xinyuan, Ph.D. Supervisor, Professor, Nationally Distinguished Expert.
He is the Dean of the Design School at Huazhong University of Science and Technology, the Director of the Key Laboratory of Lighting Interactive Service and Technology, Ministry of Culture and Tourism, the Director of the Hubei Provincial Engineering Research Centre of Digital Light and Shadow Technology, the Chairman of ARTI Collaborative Platform of AI Art Education CHINA, and a member of the Teaching Steering Committee of Animation and Digital Media Major of the Ministry of Education.
Dr. Cai has long been engaged in teaching and research in the fields of digital media art theory and education, digital light and shadow art environment and landscape, artificial intelligence art and design. He has presided over more than 20 national key projects. He has successively completed many national, provincial and municipal major cultural and technological integration projects, such as the 70th anniversary of the National Day ‘Shining Hubei’ colourful car, Wuhan Yangtze River light show, and so on. He led the construction of ‘ARTI designer XL’ ARTI Art Design Supercomputing Platform to promote the development of artificial intelligence art education. His research and practice have promoted the deep integration of art, science and technology and culture, and played an important leading role in the field of design innovation in the era of intelligence.
Keynote 3
Speaker:
Jing Dong
Title:
Reflections and Outlook on Generative Artificial Intelligence ——From the Security and Ethics Perspective
Time:
TBD
Abstract:
Generative Artificial Intelligence (Generative AI), powered by Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), is rapidly reshaping the landscape of artificial intelligence. State-of-the-art models such as GPT-4, DeepSeek, Claude, and DALL-E 3 demonstrate significant progress in generative capabilities, enabling breakthroughs in creative content synthesis, logical inference, automated decision-making, and domain-specific applications. However, the accelerated deployment of these systems has also exposed critical security vulnerabilities and ethical concerns, including the risks of misuse, deepfakes, phishing scams, data privacy breaches, and model security. It has raised unexpected concerns from individuals, organizations, communities and even nations. As Generative AI continues to evolve and integrate into various applications and sectors, the need for robust mechanisms to ensure the safety, trustworthiness, and ethical use of generative models has become increasingly urgent. This talk will focus on security and ethics threats, state-of-the-art solutions and future challenges of the generative AI , especially for visual information.
Biography:
Dr. Jing Dong is currently a Full Professor/Researcher in the National Laboratory of Pattern Recognition in the Institute of Automation, Chinese Academy of Sciences (CASIA). She is a senior member of IEEE/CCF/CSIG. Her research interests include pattern recognition, image processing and image forensics. She has published more than 100 academic papers and chaired in many major national scientific projects and played a leading role in several national and international technical conferences.
She served as the IEEE Biometric Council Beijing Chapter Chair since 2019 and the IEEE R10 ExCom member since 2017. She was also the IEEE SPS Membership Development Director from 2022 to 2024.
She was awarded with the IBM Faculty Award (2016) and the ICPR Best Scientific Paper Award (2018), the CAAI Outstanding Individual Member Award (2019), the CSIG Outstanding Female Young Scientist Award (2020) , the CSIG Science and Technology Award (2021) 、the Wu Wenjun Artificial Intelligence Science and Technology Award (2021) and the CAI Innovation Award (1st Prize,2022) for her excellent contribution for the technical innovation and leadership for the community.
Keynote 4
Speaker:
Haonan Cheng
Title:
Audio Computing in Multimedia Intelligence: Methods, Applications, and Prospects
Time:
TBD
Abstract:
Audio computing technology in multimedia intelligence, as an intersection of artificial intelligence, physical acoustics and art, is undergoing a paradigm shift from traditional signal analysis to deep semantic understanding. In recent years, the boundaries of generative AI combined with audio continue to expand. The audio computing is reshaping the sensory dimensions of human-computer interaction from traditional audio recording to personalized music creation, and from ambient sound simulation to cross-modal content generation, which poses new security risks. This report focuses on the key methods, typical applications, and future trends of audio computing, with an emphasis on its critical role in intelligent creation, immersive experience, and content security.
Biography:
Haonan Cheng, associate researcher of the State Key Laboratory of Media Convergence and Communication, Communication University of China, mainly focuses on audio information processing, audio-visual cross modal generation and forgery detection.
She became the first technical expert in China to be awarded the Asia-Pacific Young Engineer Prize by ABU in 2024, and was selected for the Beijing National Governance and Young Talent Cultivation Program in 2025. In recent years, she has published more than 40 SCI/EI papers in IEEE TOG, TIFS, TASLP, SIGGRAPH, IEEE VR, IJCAI, AAAI, ACM MM, etc. She has been authorized 2 national invention patents, and won the Excellent Paper Award in the 5th CSIG China Media Forensics and Security Conference, and Best Poster Paper Award in the 20th International Forum on Digital Multimedia Communications. She was funded by more than 10 projects, including National Natural Science Foundation of China, National Key R&D Program, National Social Science Foundation of China, and Medium and Long-term Science and Technology Program for Radio, Television and Audiovisual Network, etc. She serves as a member of the Multimedia Specialized Committee of the Chinese Society of Image and Graphics, the Program Chair of the International Forum on Digital Multimedia Communications, the Forum Chair of the China Multimedia Conference, and the Session Chair of ACM MM and other international conferences.
Keynote 5
TBD
TBD
Beijing University of Technology
Beijing, China
ltmou@bjut.edu.cn
Dr. Luntian Mou is an Associate Professor with the School of Information Science and Technology, Beijing University of Technology, and also with Beijing Institute of Artificial Intelligence (BIAI). He received the Ph.D. degree in computer science from the University of Chinese Academy of Sciences, China in 2012. He served as a Postdoctoral Fellow at Peking University, from 2012 to 2014. And he was a Visiting Scholar with the University of California, Irvine, from 2019 to 2020. He initiated the IEEE Workshop on Artificial Intelligence for Art Creation (AIART) in 2019, and published a book titled Artificial Intelligence for Art Creation and Understanding in 2024. His current research interests include artificial intelligence, machine learning, multimedia computing, affective computing, and brain-like computing. He is the recipient of Beijing Municipal Science and Technology Advancement Award, and the recipient of China Highway Society Technology Invention Award, IEEE Outstanding Contribution to Standardization Award, and AVS Outstanding Contribution on 15th Anniversary Award. He serves as a Guest Editor for Machine Intelligence Research, and a Reviewer for many important international journals and conferences such as TIP, TAFFC, TMM, TCSVT, TITS, CVPR, AAAI, etc. And he serves as a Co-Chair of System subgroup in AVS workgroup. He is a Senior Member of IEEE, CCF, and CSIG, and a Member of ACM, and CAAI, and an Expert of MPEG China.
Peking University
Beijing, China
gaof@pku.edu.cn
Dr. Feng Gao is an Assistant Professor with the School of Arts, Peking University. He has long researched in the disciplinary fields of AI and art, especially in AI painting. He co-initiated the international workshop of AIART. Currently, he is also enthusiastic in virtual human. He has demonstrated his AI painting system, called Daozi, in several workshops and drawn much attention.
Zhejiang University
Hangzhou, China
zhangkejun@zju.edu.cn
Dr. Kejun Zhang is a Professor with Zhejiang University, joint PhD supervisor on Design and Computer Science, Dean of Department of Industrial Design at College of Computer Science of Zhejiang University. He received his PhD degree from College of Computer Science and Technology, Zhejiang University in 2010. From 2008 to 2009, He was a visiting research scholar of University of Illinois at Urbana-Champaign, USA. In June 2013, he became a faculty of the College of Computer Science and Technology at Zhejiang University. His current research interests include Affective Computing,Design Science, Artificial Intelligence, Multimedia Computing and the understanding, modelling and innovation design of products and social management by computational means. He is now the PI of National Science Foundation of China, Co-PI of National Key Research and Development Program of China, and PIs of ten more other research programs. He has authored 4 books, more than 40 scientific papers.
Hong Kong University of Science and
Technology
(Guangzhou)
Guangzhou, China
zeyuwang@ust.hk
Dr. Zeyu Wang is an Assistant Professor of Computational Media and Arts (CMA) in the Information Hub at the Hong Kong University of Science and Technology (Guangzhou) and an Affiliate Assistant Professor in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology. He received a PhD from the Department of Computer Science at Yale University and a BS from the School of Artificial Intelligence at Peking University. He leads the Creative Intelligence and Synergy (CIS) Lab at HKUST(GZ) to study the intersection of Computer Graphics, Human-Computer Interaction, and Artificial Intelligence, with a focus on algorithms and systems for digital content creation. His current research topics include sketching, VR/AR/XR, and generative techniques, with applications in art, design, perception, and cultural heritage. His work has been recognized by an Adobe Research Fellowship, a Franke Interdisciplinary Research Fellowship, a Best Paper Award, and a Best Demo Honorable Mention Award.
Stanford University
California, USA
grwang@stanford.edu
Dr. Gerui Wang is a Lecturer at Stanford University Center for East Asian Studies, where she teaches classes on contemporary art, AI and posthumanism. Her research interests span arts, public policy, environment, and emerging technologies. She is a member of the Alan Turing Institute AI&Arts Research Group. With her background in art history, she has published in the Journal of Chinese History and Newsletter for International China Studies. Gerui's book Sustaining Landscapes: Governance and Ecology in Chinese Visual Culture is forthcoming in 2025. Her research briefs on AI, robotics, media, and society are frequently featured in public venues including Forbes, Alan Turing Institute's AI and Art Forum, Asia Times, and South China Morning Post. Gerui holds a doctorate in art history from the University of Michigan.
Tezign.com
Tongji University Design Artificial Intelligence Lab
Shanghai, China
lfan@tongji.edu.cn
Dr. Ling Fan is a Scholar and Entrepreneur to bridge machine intelligence with creativity. He is the founding chair and professor of Tongji University Design Artificial Intelligence Lab. Before, he held teaching position at the University of California at Berkeley and China Central Academy of Fine Arts. Dr. Fan co-founded Tezign.com, a leading technology start-up with the mission to build digital infrastructure for creative contents. Tezign is backed by top VCs like Sequoia Capital and Hearst Ventures. Dr. Fan is a World Economic Forum Young Global Leader, an Aspen Institute China Fellow, and Youth Committee member at the Future Forum. He is also a member of IEEE Global Council for Extended Intelligence. Dr. Fan received his doctoral degree from Harvard University and master's degree from Princeton University. He recently published From Universality of Computation to the Universality of Imagination, a book on how machine intelligence would influence human creativity.
University of the Arts London
London, UK
n.bryankinns@arts.ac.uk
Dr. Nick Bryan-Kinns is a Professor of Creative Computing at the Creative Computing Institute, University of the Arts London. His research explores new approaches to interactive technologies for the Arts and the Creative Industries through Creative Computing. His current focus is on Human-Centered AI and eXplainable AI for the Arts. His research has made audio engineering more accessible and inclusive, championed the design of sustainable and ethical IoT and wearables, and engaged rural and urban communities with physical computing through craft and cultural heritage. Products of his research have been exhibited internationally including Ars Electronica (Austria) the V&A and the Science Museum (UK), made available online and as smartphone apps, used by artists and musicians in performances and art installations, and have been reported in public media outlets including the BBC and New Scientist. He is a Fellow of the Royal Society of Arts, Fellow of the British Computer Society (BCS), and Senior Member of the Association of Computing Machinery (ACM). He is a recipient of the ACM and BCS Recognition of Service Awards, and chaired the ACM Creativity and Cognition conference 2009, and the BCS international HCI conference 2006.
Australian Government
Australian Capital Territory, Australia
ambarish.natu@gmail.com
Dr. Ambarish Natu is with the Australian Government. After graduating from University of New South Wales, Sydney, Ambarish has held positions as a visiting researcher in Italy and Taiwan, worked for industry in United Kingdom and the United States of America and for the past ten years has been working in the Australian Government. For the past 17 years, Ambarish has led the development of five international standards under the auspices of the International Standards Organization (ISO) popularly known as JPEG (Joint Photographic Experts Group). He is the recipient of the ISO/IEC certificate for contributions to technology standards. Ambarish is highly active in the area of international standardization and voicing Australian concerns in the area of JPEG and MPEG (Motion Pictures Experts Group) standardization. He previously initiated an effort in the area of standardization relating to Privacy and Security in the Multimedia Context both within JPEG and MPEG standard bodies. In 2015, Ambarish was the recipient of the prestigious Neville Thiele Award and the Canberra Professional Engineer of the Year by Engineers Australia. Ambarish currently works as an ICT Specialist for the Australian Government. Ambarish is a Fellow of the Australian Computer Society and Engineers Australia. Ambarish also serves on the IVMSP TC and the Autonomous Systems Initiative of the IEEE Signal Processing Society. Ambarish has also been General Chair of DICTA 2018, ICME 2023 and TENSYMP 2023 in the past. Ambarish has keen interest in next generation data and analytics technologies that will change the course of the way we interact with in the world.
eBook Published: 29 August 2024
Imprint: CRC Press
DOI:
https://doi.org/10.1201/9781003406273
ABSTRACT
AI-Generated Content (AIGC) is a revolutionary engine for digital content generation. In the area of art, AI has achieved remarkable advancements. AI is capable of not only creating paintings or music comparable to human masterpieces, but it also understands and appreciates artwork. For professionals and amateurs, AI is an enabling tool and an opportunity to enjoy a new world of art.
This book aims to present the state-of-the-art AI technologies for art creation, understanding, and evaluation. The contents include a survey on cross-modal generation of visual and auditory content, explainable AI and music, AI-enabled robotic theater for Chinese folk art, AI for ancient Chinese music restoration and reproduction, AI for brainwave opera, artistic text style transfer, data-driven automatic choreography, Human-AI collaborative sketching, personalized music recommendation and generation based on emotion and memory (MemoMusic), understanding music and emotion from the brain, music question answering, emotional quality evaluation for generated music, and AI for image aesthetic evaluation.
The key features of the book are as follows:
This book is dedicated to the international cross-disciplinary AI Art community: professors, students, researchers, and engineers from AI (machine learning, computer vision, multimedia computing, affective computing, robotics, etc.), art (painting, music, dance, fashion, design, etc.), cognitive science, and psychology. General audiences can also benefit from this book.
Purchase Links: