Speakers

Cheng-Lin Liu is a Professor at the National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences, and now the Director of the Laboratory. He is a vice president of the Institute of Automation, a vice dean of the School of Artificial Intelligence, University of Chinese Academy of Sciences. He received the PhD degree in pattern recognition and intelligent control from the Chinese Academy of Sciences, Beijing, China, in 1995. He was a postdoctoral fellow in Korea and Japan from March 1996 to March 1999. From 1999 to 2004, he was a researcher at the Central Research Laboratory, Hitachi, Ltd., Tokyo, Japan. His research interests include pattern recognition, machine learning and document image analysis. He has published over 300 technical papers in journals and conferences. He is an Associate Editor-in-Chief of Pattern Recognition Journal and Acta Automatica Sinica, an Associate Editor of International Journal on Document Analysis and Recognition, Cognitive Computation, IEEE/CAA Journal of Automatica Sinica, Machine Intelligence Research, CAAI Trans. Intelligence Technology, CAAI Artificial Intelligence Research and Chinese Journal of Image and Graphics. He is a Fellow of the CAA, CAAI, the IAPR and the IEEE.

Title: Confident Learning for Classification in Open World

Abstract: Traditional methods of pattern classification and machine learning usually assume closed world: the input pattern falls within a fixed set of classes. However, in open world, the input pattern may be out of the know classes, be noise, or ambiguous to be classified. This raises the problems of open set classification, out-of-distribution and ambiguity rejection. Meanwhile, the change of class set raises the problem of class incremental learning. These problems have received increasing attention in recent years, but are often considered separately. My group attempts to build a unified classification and confident learning framework to consider open set classification, OOD and ambiguity rejection jointly, and has proposed some effective methods for open set classification, confidence estimation and rejection.

Jian Yang

  Nanjing University of Science and Technology

Jian Yang received the PhD degree from Nanjing University of Science and Technology (NUST), on the subject of pattern recognition and intelligence systems in 2002. In 2003, he was a Postdoctoral researcher at the University of Zaragoza. From 2004 to 2006, he was a Postdoctoral Fellow at Biometrics Centre of Hong Kong Polytechnic University. From 2006 to 2007, he was a Postdoctoral Fellow at Department of Computer Science of New Jersey Institute of Technology. Now, he is a Chang-Jiang professor in the School of Computer Science and Engineering of NUST. He is the author of more than 200 scientific papers in pattern recognition and computer vision. His papers have been cited over 30000 times in the Scholar Google. His research interests include pattern recognition, computer vision and machine learning. Currently, he is/was an associate editor of Pattern Recognition, Pattern Recognition Letters, IEEE Trans. Neural Networks and Learning Systems, and Neurocomputing. He is a Fellow of IAPR. 

Title: Point Clouds based Visual Perception

Abstract: With the development of 3D sensors such as LiDAR, point clouds data become more and more popular. In this talk, we will present a series of visual perception for point clouds data processing. We first design an easy-to-hard training strategy based on curriculum learning for LiDAR-based object detection, and develop a 3D Siamese Transformer network for single object tracking on point clouds. Then, we present a pyramid point cloud Transformer for large-scale place recognition. Further, we give an efficient LiDAR point cloud oversegmentation network. Finally, we present a SE(3) diffusion model-based point cloud registration method for robust 6D object pose estimation. 

Shuzhi Sam Ge

  National University of Singapore

Shuzhi Sam Ge, Fellows of SAEng，IEEE, IFAC, IET, CAA，Professor, Department of Electrical and Computer Engineering, PI Member of Institute for Functional Intelligent Materials, the National University of Singapore.  Founder of Institute for Future (IFF), Qingdao University, China. He Serves as President Elect of Asian Control Association, 2022-2024, IFAC executive officers as Council Member, 2023-2026, Steering Committee Chair of International Conference on Social Robotics. He served as Vice President of Technical Activities and Membership Activities, 2009-2012, Member of Board of Governors, 2007-2009, and Chair of Technical Committee on Intelligent Control, 2005-2008, of IEEE Control Systems Society. He was the recipient of many award including National Technology Award from Singapore, IEEE Control Systems Society Distinguished Member Award, AI Grand Challenge Award from AI SG. His research interests include robotics, intelligent systems, and intelligent materials. He has (co)-authored nine books, and over 800 international journal and conference papers, with high H index (110) and citations (58,000). 

Title: On Stability, Robustness and Performance of Systems in Mechatronics, Robotics and Artificial Intelligence

Abstract: Stability, Robustness, and Performance (SRP) are three important issues for any systems in mechatronics, robotics, and artificial intelligence (MRAI). The lecture begins first by presenting the evolution of mechatronics, robotics, and artificial intelligence systems in its complexity, and basic concepts of stability, robustness, and performance in systems. Then, model based approaches are presented on the Tri-foci: SRP for our works in mechatronics. Further, with the introduction of neural networks (NN) modelling, model based and NN based approaches are presented our work in robotic research. Though NNs are a very powerful in modelling, most artificial intelligence systems lack stability, robustness, and guaranteed performance from a dynamical system perspective by considering the vulnerability of neural networks. Existing methods typically model machine learning as an open-loop control system, which results in performance degradation when adversarial attacks cause a data distribution shift. Therefore, integrating closed-loop control into machine learning can provide a theoretical analysis of the stability and robustness of deep neural networks. Finally, we share on our thoughts work in stability, robustness, and performance of artificial intelligence, and call for collaboration in fostering SRP artificial intelligence systems in a rapidly evolving landscape.

CESARE ALIPPI

  Politecnico di Milano and Università della Svizzera italiana

CESARE ALIPPI received the degree in electronic engineering cum laude in 1990 and the PhD in 1995 from Politecnico di Milano, Italy. Currently, he is a Professor with the Politecnico di Milano, Milano, Italy and Università della Svizzera italiana, Lugano, Switzerland. He is a visiting professor at the Guangdong University of Technology, Guangzhou, China. He has been a visiting researcher at UCL (UK), MIT (USA), ESPCI (F), CASIA (RC), A*STAR (SIN).

Alippi is an IEEE Fellow, an ELLIS Fellow and an AAIA Fellow, Board of Governors member of the International Neural Network Society, Past Vice-President education and Administrative Committee member of the IEEE Computational Intelligence Society, past associate editor of the IEEE Transactions on Emerging topics in computational intelligence, the IEEE Computational Intelligence Magazine, the IEEE-Transactions on Instrumentation and Measurements, the IEEE-Transactions on Neural Networks. 

He received the 2024 IEEE CIS Enrique Ruspini Meritorious Award, the 2018 IEEE CIS Outstanding Computational Intelligence Magazine Award, the 2016 Gabor award from the International Neural Networks Society and the 2013 IEEE CIS Outstanding Transactions on Neural Networks and Learning Systems Paper Award, the IBM Faculty award, the 2004 IEEE Instrumentation and Measurement Society Young Engineer Award.

Current research activity addresses adaptation and learning in non-stationary environments, graph-based learning and Intelligence for embedded, IoT and cyber-physical systems.

He holds 8 patents, has published one monograph book (translated in Chinese), 7 edited books and more than 250 papers in international journals and conference proceedings.

Title: Forecasting and graph-based predictors

Abstract: Humans have always been fascinated by the future and designed methods and methodologies to investigate it. In addition to traditional prediction methods, both linear and non-linear, the recent literature is proposing methods exploiting relational information to provide graph-based inference. The relevance of the topic emerges from the fact that the relational property is latent in many application, as graphs with their information entities and relational dependencies are everywhere.

The keynote will open views on the forecasting task as well as on current research in deep graph-based predictions. Deep predictive family of models where, in addition to “space” we exploit those relations emerging from the time dimension will be presented and discussed. 

Changxiang Shen

  The Chinese Academy of Engineering

Changxiang Shen, an academician of China Academy of Engineering, graduated from Zhejiang University with a major in applied mathematics in 1965. He is engaged in research on computer information system, cryptographic engineering, information security architecture, system software security (secure operating system, secure database, etc.) and network security. He has successively completed more than 20 major scientific research projects and achieved a series of important achievements. He has won 2 first prizes, 2 second prizes and 3 third prizes for national scientific and technological progress and more than 10 military scientific and technological progress prizes. These achievements have great creativity in information processing and security technology, and many of them have reached the world advanced level. They have been widely used in the whole army and achieved remarkable benefits, making breakthroughs in information security and confidentiality in China. He has made outstanding contributions to scientific and technological innovation, consultation and demonstration, discipline and specialty construction and talent training in the field of network security.

Title: Building Artificial Intelligence Security Line with Active Immune Trusted Computing

Abstract: Artificial intelligence not only empowers human society to accelerate its development, but also generates more security risks. The report proposes that the artificial intelligence security defense line should be built with active immune trusted computing by means of trusted computing 3.0 product chain, seizing the commanding heights of core technologies, maintaining new standards such as 2.0 and new infrastructure.