Call for Papers

Artificial Intelligence (AI) has already fueled many academic fields as well as industries. In the area of art creation, AI has demonstrated its great potential and gained increasing popularity. People are greatly impressed by AI painting, composing, writing, and designing. AI has not only exhibited a certain degree of creativity, but also helped in uncovering the principles and mechanisms of creativity and imagination from the perspective of neuroscience, cognitive science and psychology.

This is the 3^rd AIART workshop to be held on MIPR and it aims to bring forward cutting-edge technologies and most recent advances in the area of AI art in terms of the enabling creation, analysis and understanding technologies. The theme topic of the workshop will be AI creativity. And we plan to organize a Special Issue on a renowned SCI journal. We sincerely invite high-quality papers presenting or addressing issues related to AI art, including but not limited to the following topics:

• Theory and practice of AI creativity
• Neuroscience, cognitive science and psychology for AI art
• AI for painting generation
• AI for music/sound synthesis, composing, matching and instrument digital design
• AI for poem composing and synthesis
• AI for typography and graphic design
• AI for fashion, makeup and virtual human
• AI for aesthetics understanding, analysis, assessment and prediction
• AI for affective computing of artworks
• Authentication and copyright issues of AI artworks

Paper Submission

The workshop will accept regular papers (6 pages), and demo papers (4 pages). Selected submissions could be invited to submit to journal special issues.

More information: https://mipr2021.org/pages/submission_instructions/

Submission address: https://cmt3.research.microsoft.com/AIART2021/Submission/Index

Keynotes (1/5)

Keynote 1

Speaker:

Ying-Qing Xu

Title:

Stylized Cartoon and Animation

Time:

9:00 – 9:30, September 10, 2021

Abstract:

Computational Aesthetic is the more and more popular topic in recent years. How to use artificial intelligence to create and generate such as painting, poetry, music, graphics, fashion, etc., is not only a challenge, but also attracts many people's attention. In this talk, I would like to introduce how to automatically generate cartoon and animation that is part of my previous work at Microsoft Research Asia.

Biography:

Prof. Dr. Ying-Qing Xu is a professor of Academy of Arts & Design, Tsinghua University, Beijing China. At Tsinghua University, he serves as a director of the Future Lab, a director of the Lab for Lifelong Learning, and deputy dean of the Institute for Accessibility Development. His research interesting includes the natural user interface design, immersive perception & interaction, tangible perception & interaction, and e-heritage. Before joined Tsinghua University, he was a Lead Researcher of Microsoft Research Asia where he had worked for 12 years since January 1999. Dr. Xu has published over 100 peer-reviewed research papers and granted patents. He is a fellow of CCF (China Computer Federation), a member of CAA (China Artists Association), and a senior member of IEEE (Institute of Electrical and Electronics Engineers).

Keynotes (3/5)

Keynote 3

Speaker:

Shangfei Wang

Title:

Facial Action Unit Recognition under Non-Full Annotation

Time:

12:00 – 12:30, September 10, 2021

Abstract:

Facial behavior analysis is one of the fastest growing research areas in affective computing and computer vision. We may infer people’s emotions from their facial behavior. There are two commonly used ways to describe facial behavior: facial expression and facial action unit (AU). Facial expression is an intuitive description of facial behavior, most commonly identified as one or more of six expressions (i.e., anger, disgust, fear, happiness, sadness, and surprise). However, the number and definition of expressions are not universally agreed upon by researchers. AUs are patterns of muscular activation as defined in Ekman’s facial action coding system (FACS). Compared to expressions, which describe global facial behavior, AUs describe facial behavior in more detail and subtlety. The successful recognition of AUs could greatly assist the analysis of human facial behavior and expression. Traditional supervised AU detection methods need a large number of AU-annotated facial images. However, AUs should be annotated by experts. AU labelling is time consuming and expensive. Therefore, we want to reduce reliance on AU labels for AU recognition. This talk will present our recent works on facial action unit recognition under non-full annotations.

Biography:

Shangfei Wang received her BS in Electronic Engineering from Anhui University, Hefei, Anhui, China, in 1996. She received her MS in circuits and systems, and the PhD in signal and information processing from University of Science and Technology of China (USTC), Hefei, Anhui, China, in 1999 and 2002. From 2004 to 2005, she was a postdoctoral research fellow in Kyushu University, Japan. Between 2011 and 2012, Dr. Wang was a visiting scholar at Rensselaer Polytechnic Institute in Troy, NY, USA. She is currently a Professor of School of Computer Science and Technology, USTC. Her research interests cover affective computing and pattern recognition. She has authored or co-authored over 100 publications.

Keynotes (5/5)

Keynote 5

Speaker:

Nick Bryan-Kinns

Title:

XAIArt: eXplainable Artificial Intelligence and the Arts

Time:

15:45 – 16:15, September 10, 2021

Abstract:

The field of eXplainable Artificial Intelligence (XAI) has become a hot topic examining how machine learning models such as neural nets and deep learning techniques can be made more understandable to humans. In particular, how these opaque, non-intuitive, and difficult to understand AI models can be explained. For example, how to provide human understandable explanations of why an AI system made a particular medical diagnosis, how the AI models in an autonomous vehicle work, and what data an AI system uses to generate insights about consumer behaviour.
In this talk I will explore what XAI might mean for AI and art creation by exploring the potential of XAI for music creation. Combining music making and XAI presents a conundrum: what does it mean to understand an AI when co-creating music together? When we co-create music with humans we partly rely on an intuitive understanding of each others’ musical intention and practice to be able to mutually engage with each other, to spark off each other, get in the groove, and lose ourselves in the creative moment. What does this mean when we co-create with an AI? I will explore some current trends in AI and music to illustrate how AI models are being explained, or more often not explained, and suggest some ways in which we might design XAI systems to help humans to better get the gist of what an AI is doing when we co-create together.

Biography:

Nick Bryan-Kinns is Professor of Interaction Design and Director of the EPSRC+AHRC Media and Arts Technology Centre for Doctoral Training at Queen Mary University of London (QMUL). He is Guest Professor at Huazhong University of Science and Technology, Distinguished Professor at Wuhan University of Technology, China, and was a Visiting Professor of Interaction Design at Hunan University, China. He is Director of EECS International Joint Ventures, lead for International Partnerships for the AI and Music Centre for Doctoral Training, and leads the Sonic Interaction Design Lab in the Centre for Digital Music at QMUL. Bryan-Kinns is a Fellow of the Royal Society of Arts, Fellow of the British Computer Society, and Senior Member of the Association of Computing Machinery (ACM). Bryan-Kinns has published award winning international journal and conference papers on his extensively funded user experience research on participatory design, collaboration, mutual engagement, interactive art, cross-modal interaction, and tangible interfaces. Awards include winner of the AT&T and NYU Connect Ability Challenge 2015, and winner of QMUL Public Engagement Awards 2015 and 2017. His research is reported in publications such as the New Scientist, and media outlets such as BBC, and exhibited at venues such as the Science Museum, London. Bryan-Kinns was Deputy Dean for Science and Engineering at QMUL and held a Royal Academy of Engineering Industrial Secondment in recognition of his work on commercialising academic research. He was a Z-Kubator Development Programme Mentor, Zurich University of the Arts, and was a panel member for the National Science Foundation’s CreativeIT funding panel, and provided expert consultation for the European Commission’s funding of Creativity and ICT. He was Chair of the Steering Committee for the ACM Creativity and Cognition Conference series and was the founding chair of the ACM Creativity, Cognition and Art Community. He chaired the ACM Creativity and Cognition conference 2009, and co-chaired the British Computer Society (BCS) international HCI conference 2006. Prof. Bryan-Kinns is a recipient of the ACM and BCS Recognition of Service Awards. In 1998 he was awarded a Ph.D. in Human Computer Interaction from the University of London.

Technical Program Committee (Tentative)

• Baoqiang Han, China Conservatory of Music, China
• Baoyang Chen, Central Academy of Fine Arts, China
• Beici Liang, Tencent Music Entertainment Group, China
• Bing Li, King Abdullah University of Science and Technology, Saudi Arabia
• Changsheng Xu, Institute of Automation, Chinese Academy of Sciences, China
• Dongmei Jiang, Northwestern Polytechnical University, China
• Haifeng Li, Harbin Institute of Technology, China
• Haipeng Mi, Tsinghua University, China
• Jia Jia, Tsinghua University, China
• Jianyu Fan, Microsoft, Canada
• John See, Multimedia University, Malaysia
• Junping Zhang, Fudan University, China
• Kejun Zhang, Zhejiang University, China
• Lai-Kuan Wong, Multimedia University, Malaysia
• Lei Xie, Northwestern Polytechnical University, China
• Lin Gan, Tianjin University, China
• Long Ye, China University of Communication, China
• Mei Han, Ping An Technology Art institute, USA
• Ming Zhang, Nanjing Art College, China
• Philippe Pasquier, Simon Fraser University, Canada
• Qin Jin, Renmin University, China
• Rebecca Fiebrink, University of London, UK
• Rongfeng Li, Beijing University of Posts and Telecommunications, China
• Rui Wang, Institute of Information Engineering, Chinese Academy of Sciences, China
• Ruihua Song, Renmin University, China
• Shasha Mao, Xidian University, China
• Shiqi Wang, City University of Hong Kong, China
• Si Liu, Beihang University, China
• Simon Lui, Tencent Music Entertainment Group, China
• Weiming Dong, Institute of Automation, Chinese Academy of Sciences, China
• Wei-Ta Chu, National Chung Cheng University, Taiwan
• Wei Li, Fudan University, China
• Weiwei Zhang, Dalian Maritime University, China
• Xi Shao, Nanjing University of Posts and Telecommunications, China
• Xiaoyan Sun, University of Science and Technology of China, China
• Xinfeng Zhang, University of Chinese Academy of Sciences, China
• Yi Qin, Shanghai Conservatory of Music, China

History

• AIART 2019: https://aiart2019.github.io/
• AIART 2020: https://aiart2020.github.io/