KEYNOTE SPEAKERS

 

 

 

Mingyi He, Northwestern Polytechnical University, China

 

Mingyi He, CIE Fellow, CSIG Fellow, Vice president of APSIPA, Professor of Northwestern Polytechnical University (NPU).
Dr He received his B.E. degree and M.E. degree from NPU in 1982 and 1985 respectively, and Ph. Degree in 1994 from Xidian University. Since 1985, he has been with the Department/School of Electronics and Information, NPU, where he has been a full professor since 1996 and appointed as a Chief Professor of signal and information processing (SIP) in 1998. He was the department chair of electronics and information engineering (2003-2012), the founding director for IAP (Information Acquisition and Processing) of Shaanxi Key Lab and director of IAP international research center, director and chief scientist of NPU Center for earth observation research. He was visiting professor of Adelaide university and Sydney university, Australia. His research interests focus on advanced machine vision and intelligent processing, including signal and image processing, computer vision, integrated image and graphics processing, hyper-spectral remote sensing, 3D information acquisition and processing, and neural network artificial intelligence. Prof. He is the recipient of 2012 CVPR best paper award, 2017 APSIPA best deep/machine learning paper award. He has obtained 11 scientific prizes, 3 teaching prizes from China (ministry and province government). He is a recipient of the government lifelong subsidy from the state council of China in (1993--), 2012 Scientific Chinese, 2017 Baosteel outstanding teacher award. He also received awards from the IEEE Signal Processing Society in 2014, APSIPA in 2019, the Chinese Institute of Electronics in 2018 and 2020, China Remote Sensing Committee in 2023. He has acted as the general chair or the TPC (co)chair for a number of international conferences. He had addressed a number of keynote talks or invited plenary talks. He is/was an Associate Editor or guest editor for IEEE TGRS, IEEE Jstars, APSIPA T-SIP, RS, JIG, SP etc.

(Onsite Talk) Speech Title: Integrated Image and Graphic Intelligent Processing via Hyperspectral Multi-viewing

Image and graphical information accounts for about 80% of the information perceived by human beings. Image processing and graphical processing have become predominant in information processing, which are also two important aspects in the fields of machine vision and graphics. Image processing primarily involves techniques and methods for imaging, analyzing, enhancing, and improving images. It entails manipulating image data to enhance image quality, extract information, improve visual effects, and assist in discriminating or understanding observed objects with physical properties. Graphics processing, on the other hand, focuses on the points, lines, surfaces, volumes, lighting, and their interrelations within image data, primarily involving the generation, editing, and display of 2D and 3D graphics. Although both fields rely on computers and graphic displays for operation, there are significant differences in content, technology, and purpose, and they have traditionally been studied separately. In specialized applications such as aerospace engineering, there is an urgent need to investigate the integrated geometric relationships (graphics) and physical properties (images) within image data for complex 3D reconstruction and object recognition.
This report presents the research and practice of the speaker’s team in recent years in the integrated observation of graphics (geometric information) and images (physical information), 3D scene reconstruction, and intelligent processing of images and graphics. This talk includes the research background, multi-view 3D geometric information acquisition, hyperspectral physical information acquisition, learning-based integrated intelligent processing of hyperspectral multi-viewing images, and applications. This work reflects the refinement of addressing significant engineering development technologies to fundamental scientific problems, encompassing relevant scientific discoveries and the establishment of innovative theoretical methods, showcasing a successful case of “from 1 to 0” research in integrated image and graphics processing. Further topics in the area are also discussed.

 

 

 

Ruigang Yang, IEEE Fellow

Shanghai Jiao Tong University, China

 

Ruigang Yang is currently a full professor at Shanghai Jiaotong University China. He received his Ph.D. in Computer Science from the University of North Carolina at Chapel Hill in 2003. He has received a CAREER Award from the National Foundation of the United States. He was a tenured professor in the Department of Computer Science at the University of Kentucky, and the director of the Robotics and Autonomous Driving Laboratory at Baidu Research Institute. Dr. Yang has published more than 150 papers in top journals and conferences in the field of computer vision and graphics, including IJCV, IEEE T-PAMI, SIGGRAPH, CVPR, and ICCV, with more than 20,000 Google Scholar citations and an H-index of 74. His primary research areas are in computer vision, robotics, and AR/VR.  He is a Fellow of IEEE. 

 

(Onsite Talk) Speech Title: Overcoming the Sim2Real GAP: Real2Sim2Real, with applications to Autonamous Driving

A huge obstacle for AI, in particularly embodied AI, is data, collecting interaction data at the scale comparable to text is formidable. As such, many researchers aim to use simulation data to mitigate the data problem, however, the domain gap between simulation and real scene is still difficult to overcome in many embodied AI tasks. We propose a different solution: Real2Sim2Real, that is, we aim to capture real world data, virtualized it in simulation to generate many varities, then apply the learned policy in the real world. It possesses the authenticity in the real world with the diversity simulation can generate. We show its applications in autonamous drivng.

 


 

 

 

Hui Kong, University of Macau, China

 

Hui Kong is with the State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC), the Department of Electromechanical Engineering (EME), and the Department of Computer and Information Science (adjunct) of the University of Macau (UM). Before that, he was affiliated with NJUST, MIT, Ohio State University, Ecole Normale Superieure (ENS), Paris, France. He obtained his Ph.D. degree (2007) from the School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore. His research areas are sensing and perception for autonomous systems, mobile robotics, SLAM and multiview geometry in computer vision, etc. His research has been supported by the Science and Technology Development Fund of Macau (FDCT), the National Natual Science Foundation of China (NSFC), and several robotics companies. He serves as an associate editor of the International Journal of Computer Vision (IJCV)  and the International Journal of AI and Autonomous Systems (AIAS). He also serves on the Editorial Board of the Journal of Sensors.

Speech Title: Autonomous Robotic Mapping in Urban Environments

Abstract: In this talk, I will introduce a few recent trials in my team on autonomous robotic mapping in urban environment. First, I will present a local robotic exploration method in a totally unknown environment based on graph gain. Next, I will give a robotic mapping scheme guided by global prior information (e.g., Openstreetmap or OSM) to deal with the issues that exist in the local exploration methods. OSM-guided robot mapping approaches usually fail to achieve complete coverage of the whole environment when prior global information is not available in some areas. Therefore, I will introduce a drone-aided OSM completion method to generate a full OSM map for ground-robot mapping. For robotic mapping, map representation is extremely important where the map's memory consumption and representation ability of the environment are the vital factors for the reusability of the map. In the last part of the talk, I will talk about a map representation approach. To conclude, autonomous robot mapping in a totally unknown environment is very challenging. However, mapping efficiency and accuracy can be significantly boosted given some prior global information.

 

 

 

 

iNVITED SPEAKERS

 

 

Hua Zheng

Fujian Normal University, China


HUA ZHENG, male, born in 1975, Master’s student supervisor, he received the Ph.D. degree in optical engineering from Zhejiang University, Hangzhou, China, in 2007. From 2017 to 2018, he was a Visiting Scholar with the Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA. Since 2010, he has been an Associate Professor with the College of Photonic and Electronic Engineering, Fujian Normal University. Currently, he is a Vice President of Zhejiang University Fujian Alumni Association. He hosted and participated in 12 provincial and ministerial level projects, 5 Fujian Provincial Natural Science Foundation projects, 6 Fujian Provincial Department of Education projects, and 3 projects commissioned by enterprises and institutions. He has authored or co-authored over 40 papers and holds several patents. His research interests include image processing, weak signal detection, signal processing, wireless communication, embedded systems, and the design of optical intelligence instruments.

Speech Title: Performance Diagnosis of Oracle Database Systems Based on Image Encoding and VGG16 Model

Abstract: This paper proposes a novel multivariate performance diagnostic approach for the Oracle database systems to detect performance degradation and crashes during database operations and maintenance. It was based on three technologies: image encoding, image concatenation, and deep convolutional network. Instantaneous variation and magnitude information of the time series were acquired by Heatmap and Recurrence Plot (RP) from databases. Moreover, the Heatmap and RP were concatenated in order to fully extract complementary information. Finally, the concatenated images of Heatmap and RP were used to train the VGG16 model for database performance diagnosis. The quantitative analysis demonstrated a good increment of accuracy in Heatmap and RP based on the same deep learning networks compared with other image encodings of Gramian Angular Difference Field (GADF), Gramian Angular Summation Fields (GASF), and Markov Transition Fields (MTF). Meanwhile, concatenated images of Heatmap and RP can improve the accuracy by 1% compared to single Heatmap input. The result of the trained model applied to multivariate database diagnosis shows an accuracy of 95.3%. Thus, our method can more effectively and accurately diagnose the performance of the Oracle database systems.

 

XiWen Zhang

Beijing Language and Culture University, China

张习文, 北京语言大学
https://faculty.blcu.edu.cn/zxw/zh_CN/index.htm


XiWen Zhang is currently a full professor of Digital Media Department, School of Information Science, in the Beijing Language and Culture University.
Prof. Zhang worked as an associated professor from 2002 to 2007 at the Human-computer interaction Laboratory, Institute of Software, Chinese Academy of Sciences. From 2005 to 2006 he was a Post doctor advised by Prof. Michael R. Lyu in the Department of Computer Science and Engineering, the Chinese University of Hong Kong. From February to April in 2001 he was a Research Assistant by Dr. KeZhang Chen in the Department of Mechanical Engineering, the University of Hong Kong. From 2000 to 2002 he was a Post doctor advised by Prof. ShiJie Cai in the Computer Science and Technology department, Nanjing University.
Prof. Zhang's research interests include pattern recognition, computer vision, and human-computer interaction, as well as their applications in digital image, digital video, and digital ink. Prof. Zhang has published over 60 refereed journal and conference papers in his research areas. His SCI papers are published in Pattern Recognition, IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics, Computer-Aided Design. He has published more than twenty EI paper.
Prof. Zhang received his B.E. in Chemical equipment and machinery from Fushun Petroleum Institute (became Liaoning Shihua University since 2002) in 1995, and his Ph.D. advised by Prof. ZongYing Ou in Mechanical manufacturing and automation from Dalian University of Technology in 2000.

 

 

Yanfeng Li

Beijing Jiaotong University, China

李艳凤，北京交通大学
https://faculty.bjtu.edu.cn/8788/

Yanfeng Li received the B.S. degree in communication engineering and the Ph.D. degree in circuits and systems from Beijing Jiaotong University, Beijing, China, in 2010 and 2015, respectively.,She is currently a Professor with the School of Electronic and Information Engineering, Beijing Jiaotong University. Her research interests are in the areas of computer vision, deep learning, and pattern recognition.

北京交通大学电子信息工程学院副教授，主要从事信号与信息处理及模式识别研究

Speech Title: TBA
Abstract: TBA

 

 

Rong Li
University of Electronic Science and Technology of China, China

https://scholar.google.com/citations?hl=en&user=OUQUFgQAAAA

Rong Li is currently a research fellow at the School of Life Sciences and Technology, University of Electronic Science and Technology of China (UESTC). She was selected as a member of the "Hundred Talent Program" at UESTC and recognized as a young talent under the "Tianfu Qingcheng Plan" in Sichuan Province. She is the Deputy Director of the High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province. Dr. Li received her Ph.D. degree in Biomedical Engineering from UESTC in 2018, with part of her doctoral studies conducted at Yale University. Her research interests include complex brain network, brain image pattern recognition, and intelligent diagnosis and treatment technologies for brain diseases. Dr. Li has published 51 academic papers in relevant fields, including 24 SCI papers as the first/corresponding author, with 13 papers published in top journals such as NeuroImage, Epilepsia, Npj Parkinson's Disease, and the International Journal of Neural Systems. Her work has received 1097 Google Scholar citations. She has led one sub-project of the China Brain Project, three projects funded by the National Natural Science Foundation of China, and participated in key projects funded by the Ministry of Science and Technology of China and the National Natural Science Foundation of China.

 

Qian Zhang
Shandong University of Political Science & Law, China

Qian Zhang is a Professor in College of Cyber Science and Technology，Shandong University of Political Science & Law, China now. She received Ph.D degree in Dept. of Computer Science, Kyungwon University of South Korea, in 2010. From 2013.6-2017.5, She did research as a post doctor in Computer Science and Technology College, Shandong University. She is an assistant professor in IT college, Gachon University, South Korea from April first, 2018 until March 31,2020. Her research interests include Medical Image Processing, Machine Learning Algorithms, Multiview Geometry for 3D reconstruction in computer vision, and Intelligence Surveillance System in IoT. She has published referred over 30 journal and conference papers, 6 IoT books and one AI book in Chinese language.

 

Rong Chang
Beijing Institute of Graphic Communication

Dr. Rong Chang is an Associate Professor at the Beijing Institute of Graphic Communication, where she also serves as the head of the Institute of AI Aesthetics. Her primary research interests encompass AI aesthetics, human-AI interaction, cultural relic restoration through human-AI collaboration, and cultural heritage preservation facilitated by human-AI partnerships. Over the last five years, Dr. Rong Chang and her team have published over ten international papers focusing on the restoration of ancient Chinese paintings and the transformation of Chinese cultural heritage. Their work has been recognized with a best paper award.