Keynotes
Intelligence and Mathematics: Posteriori and Priori
IEEE Fellow, AAIA Fellow; National Science Fund for Distinguished Young Scholars (2014), Changjiang Scholar (2016), Leading Talent of the National Ten-Thousand Talent Program (2017). Research directions: Information theory and coding, signal processing, multimedia communications, machine learning, etc.
Abstract
TBA
Hongkai Xiong
Professor, Shanghai Jiao Tong University
Guangjie Han
Multi-Dimensional Dynamic Trust Management Mechanism in Underwater Acoustic Sensor Networks
Guangjie Han is a professor, currently serving as the Dean of the School of Information Science and Engineering at Hohai University. He is an IEEE Fellow, IET/IEE Fellow, and AAIA Fellow. His main research interests include smart oceans, industrial IoT, artificial intelligence, networks, and security. In recent years, he has published more than 350 high-level SCI journal papers, including over 130 papers in the IEEE/ACM Trans. series, in international journals such as IEEE JSAC, IEEE TMC, IEEE TPDS, and IEEE TCC. His publications have been cited over 20000 times on Google Scholar, with an H-index of 75. He has authored three monographs and translated one book. He has led more than 30 provincial and ministerial-level research projects, including national key R&D programs and national natural science foundation key projects. He has been granted 130 national invention patents and 6 PCT international authorized patents. He has received numerous awards, including the second prize of the China Business Federation Science and Technology Award, the third prize of the Jiangsu Provincial Science and Technology Award, the second prize of the Liaoning Provincial Science and Technology Progress Award, and the Best Paper Award of the IEEE Systems Journal in 2020. For six consecutive years (2019-2024), he has been listed as one of the top 2% of scientists globally, as well as for the Chinese Highly Cited Researchers list for five consecutive years (2020-2024). Currently, he serves as an associate editor for more than ten international journals, including IEEE TII, IEEE TCCN, and IEEE Systems. He has been awarded the “333 High-level Talents in Jiangsu Province” (second level), the “Outstanding Contribution Young and Middle-aged Experts in Jiangsu Province,” the “Minjiang Scholar Lecture Professor,” and the “May 1st Labor Medal” of Changzhou City.
Abstract
The underwater acoustic sensor network (UASN) is a pivotal component in realizing the concept of a “smart ocean.” However, its potential remains underutilized in complex aquatic environments. The primary challenge lies in the absence of effective methods to ensure UASN security and reliable data transmission. This report presents our team’s research on the trust management mechanisms for UASNs. Our main research areas include: 1) an intrusion detection algorithm based on energy prediction model; 2) a multi-dimensional trust calculation algorithm grounded in fuzzy theory; 3) a trust evaluation algorithm utilizing cloud theory; and 4) a trust prediction algorithm driven by machine learning. These research outcomes hold significant theoretical and practical implications for advancing the security technologies and applications of UASNs.
Information probing and intelligent sensing for special environments
Yiguang Liu, Professor in college of computer science, Sichuan University. His current interest focuses on information probing and intelligent sensing, especially integrating optoelectronic/SAR/IR/photon signals to solve the problems of clearly seeing and definitely analyzing. Currently, he is leading the team to develop the key technologies of the field, and is trying to embed the modern mathematical and physical fundamentals into this field. Some achievements have been used in real applications. He has published more than 100 papers in renowned journals or conferences such as IEEE Trans./CVPR/ICCV/IROS、ACM MM、OSA OL、AIP APL.
Abstract
Information probing and intelligent sensing face the challenges due to weather and targets, etc. Thus, based on analyzing the features of visible/infrared/SAR signals, coupling and decoupling for probing technologies of multiple waves, and the models or methods capable of probing with single photon, have been discussed. Further, the probability using the technologies in aerospace challenging environments has been discussed.
Yiguang Liu
Professor, Sichuan University
Xi Peng
Sichuan University, Cheung Kong Professor, Deputy director of National Key Laboratory of Fundamental Algorithms and Models for Engineering Numerical Simulation
All-in-One Visual Restoration Fundamental Models
Xi Peng is the Cheung Kong Professor at the College of Computer Science, Sichuan University. His current interests mainly focus on machine learning and its applications in image processing, computer vision, multi-modal analysis. He has published over 100 academic papers on top-tier journals and conferences, including Nature Communications, ICML, NeurIPS, CVPR, ICCV, JMLR, TPAMI, IJCV. Prof. Peng serves as the associate editor, program chair and area chair for prominent journals and conferences
Abstract
Visual restoration, including both image and video restoration, has become a key research focus in low-level vision. Traditionally, most studies address visual restoration tasks, such as denoising, deblurring and dehazing, in a one-by-one manner. However, in real-world applications, degradations are often intertwined, and the degradation priors are not available. In other words, it is highly expected to develop more holistic approaches to restore high-quality visual content. All-in-One Visual Restoration aims to unify various restoration tasks into a single framework, enabling model simultaneously handle multiple degradation types and levels in a single model. This report concentrates on the recent advancements in all-in-one image and video restoration, highlighting blind all-in-one image / video restoration and openset image restoration. Furthermore, the report also provides insights into future directions for improving the efficiency and scalability of these all-in-one solutions.
