ISCAS 2024 Tutorial:


New Era of Artificial Intelligence:
Unleashing the Power of Large Models in Visual Applications

(selected for IEEE CASS Continuing Education)


Dates: Sunday May 19, 13:30 - 17:00 (UTC+8).
Location: Gemini 2, Resorts World Convention Centre, Singapore.
Format: Onsite (registration needed).




Overview


In today's rapidly advancing technological landscape, the significance of large-scale vision generative and foundation models has never been more pronounced. These models represent a pivotal leap forward in our ability to understand and manipulate visual information. With applications spanning from creative fields like art and entertainment to critical domains like medical imaging and autonomous systems, these models have the potential to revolutionize how we interact with and interpret visual data.

However, the transition from theoretical excellence to practical implementation in the real world is fraught with intricacies. Closing the gap between their inherent potential and tangible applications remains a significant challenge. This raises the pivotal question: how can we systematically construct and effectively employ these large models, and can they, in turn, serve as a wellspring of inspiration and support for other tasks, such as image processing and multi-model applications? This tutorial is designed to offer a clear roadmap, illuminating both the promise and potential challenges associated with leveraging large-scale models to address diverse challenges across various domains.





Speakers


Jiaying Liu
Peking University
Wen-Huang Cheng
National Taiwan University
Shuai Yang
Peking University





Schedule

Title Speaker
Introduction Wen-Huang Cheng
Specializing Large Models for Domain-Specific Vision Tasks [tutorial slides🔥]
Large vision models, fine-tuning, visual-prompt tuning, visual instruction tuning.
Wen-Huang Cheng
AIGC for Image and Video Generation [tutorial slides🔥]
Preliminary of diffusion model, image diffusion model, video diffusion model.
Shuai Yang
Employing Diffusion Models for Low-level Vision [tutorial slides🔥]
Diffusion for image restoration/low-light enhancement, unified restoration & enhancement.
Jiaying Liu




About Us

Jiaying Liu
Peking University

Jiaying Liu received the PhD degree (Hons.) in computer science from Peking University, Beijing China, in 2010. She is currently an associate professor with Peking University Boya Young fellow with the Wangxuan Institute of Computer Technology, Peking University. She has authored more than 100 technical articles in refereed journals and proceedings, and holds 50 granted patents. Her current research interests include multimedia signal processing, compression, and computer vision. She is a senior member of CSIG and CCF. She was a visiting scholar with the University of Southern California, Los Angeles, from 2007 to 2008. She was a visiting researcher with the Microsoft Research Asia in 2015 supported by the Star Track Young Faculties Award. She has served as a member of Multimedia Systems and Applications Technical Committee (MSA TC), and Visual Signal Processing and Communications Technical Committee (VSPC TC) in IEEE Circuits and Systems Society. She received the IEEE ICME-2020 Best Paper Award and IEEE MMSP-2015 Top10 percent Paper Award. She has also served as the associate editor of the IEEE Trans. on Image Processing, the IEEE Trans. on Circuit System for Video Technology and Elsevier JVCI, the technical program chair of IEEE ICME-2021/ACM ICMR-2021, the publicity chair of IEEE ICME-2020/ICIP-2019, and the area chair of CVPR-2021/ECCV-2020/ICCV-2019. She was the APSIPA distinguished lecturer (2016-2017).

Wen-Huang Cheng
National Taiwan University

Wen-Huang Cheng is University Distinguished Chair Professor with the Department of Computer Science and Information Engineering, National Taiwan University. His current research interests include multimedia, computer vision, and machine learning. He has actively participated in international events and played important leading roles in prestigious journals and conferences and professional organizations, including Editor-in-Chief for IEEE CTSoc News on Consumer Technology, Senior Editor for IEEE Consumer Electronics Magazine, Associate Editor for IEEE Transactions on Multimedia (T-MM), General Chair for ACM MMAsia (2023), IEEE ICME (2022) and ACM ICMR (2021), Chair for IEEE Multimedia Systems and Applications (MSA) technical committee, governing board member for IAPR. He has received numerous research and service awards, including the Best Paper Award of 2021 IEEE ICME and the Outstanding Associate Editor Award of IEEE T-MM (2021 and 2020, twice). He is IEEE Fellow, IET Fellow, and ACM Distinguished Member.

Shuai Yang
Peking University

Shuai Yang received the B.S. and Ph.D. degrees (Hons.) in computer science from Peking University, Beijing, China, in 2015 and 2020, respectively. He is currently an assistant professor with the Wangxuan Institute of Computer Technology, Peking University. His current research interests include image stylization, image translation and image editing. He was a Research Assistant Professor with the S-Lab, Nanyang Technological University, Singapore, from Mar. 2023 to Feb. 2024. He was a postdoctoral research fellow at Nanyang Technological University, from Oct. 2020 to Feb. 2023. He was a Visiting Scholar with the Texas A&M University, from Sep. 2018 to Sep. 2019. He was a Visiting Student with the National Institute of Informatics, Japan, from Mar. 2017 to Aug. 2017. He received the IEEE ICME 2020 Best Paper Awards and IEEE MMSP 2015 Top10 percent Paper Awards. He has served as the area chair of BMVC 2023.



Citation


@MISC{New_ISCAS2014,
 title = {New Era of Artificial Intelligence: Unleashing the Power of Large Models in Visual Applications},
 author = {Liu, Jiaying and Cheng, Wen-Huang and Yang, Shuai},
 year = {2024},
 month = {May},
 howpublished = {\url{https://williamyang1991.github.io/projects/ISCAS2024/index.html}},
}





More Information


For more information and resources, please visit our group page:

STRUCT@PKU