Keynote Speaker Ⅰ

Prof. Mingyi He

Northwestern Polytechnical University, China

 

Biography: Mingyi He received a BEng. and MEng. from Northwestern Polytechnical University (NPU) in 1982 and 1985, respectively, and a Ph.D. from Xidian University, China, in 1994.
Dr He has been with the School of Electronics and Information, NPU, where he is currently the Leading Professor for NPU signal and information processing. He is the Founder and Director of Shaanxi Key Laboratory of Information Acquisition and Processing and the Director and Chief Scientist of the Center for Earth Observation Research. He was a visiting professor at the University of Adelaide and the University of Sydney, Australia. He conducted a number of national projects and international joint research projects or joint graduate programs (such as 863 HiTech programs and NSFC key project in China; Rockwell International Collins project in the USA; joint education programs and research with the University of Adelaide and NPU, and an international R&D Center with MENSI, France). He has published more than 300 papers in the IEEE Trans. Pattern Analysis and Machine Intelligence, Geoscience and Remote Sensing, International Journal of Computer Vision, Signal Processing, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ICIP, IGARSS, ChinaSIP, ICIEA, etc. He is the author or coauthor of five books (including Digital Image Processing: Science Press, 2008 and Neural Network and Signal Processing Systems: NPU Press, 1998), etc. He has made valuable contributions to hyperspectral image processing, computer vision and image processing, neural networks and intelligent information processing, with notable applications to X-ray image processing for luggage inspection, laser-finder test system for airborne systems, and hyperspectral image processing applications, etc.
Prof. He has been a member of the Advisor Committee of China National Council for Higher Education on Electronics and Information, a member of the Chinese lunar exploration expert group, the vice-director of the Spectral Imaging Earth Observation Committee of China Committee of International Digital Earth Society, the vice-president of Space Remote Sensing Society in Chinese Society of Astronautics (CSA), and the vice-chairman of the Institution of Engineering and Technology (IET) at Xi'an Network, the vice-president and SIP committee chairman of Shaanxi Institute of Electronics. He has served in a number of international conferences (such as general co-chair of IEEE ICIEA'09, co-chair of the ICIEA'13 TPC, general chair of IEEE SPS sponsored ChinaSIP 2014). He was the recipient of the IEEE CVPR 2012 Best Paper Award and is recognized as the '2012 Chinese Scientist of the Year' and was awarded 10 scientific prizes from China and the governmental lifelong subsidy for outstanding contribution to higher education and scientific research by the State Council of China since 1993.

 

 

 

Keynote Speaker Ⅱ

Prof. Guangzhi Wang

Tsinghua University, China

 

Biography: Professor Wang Guangzhi's laboratory focuses on medical image processing and computer-assisted surgery. Addressing clinical needs, it develops cutting-edge technologies in medical image analysis, multimodal image fusion, surgical planning, surgical navigation, surgical robots, and motion tracking. The laboratory has formed new methods, devices, and paradigms for assisted diagnosis, treatment, evaluation, and rehabilitation based on medical imaging, which have been translated and applied in a variety of medical device products. These innovations help doctors achieve precise, minimally invasive, and high-quality diagnosis and treatment, and the developed innovative products have been widely used in clinical practice.

 

Speech Title: Multimodal Information Perception and Intelligent Processing in Image-Guided Stereotactic Neurosurgery

 

Abstract: In recent years, intelligent medical devices, such as surgical robots, have made great progress and have become the most concerned high-end medical instruments. Innovative products continue to emerge and expand the application field. 
The report will analyze the role of robot intelligent assistance in image-guided surgery application scenarios, and take our research experience of neurosurgical robots as an example to discuss how to improve the accuracy, convenience, and autonomy of surgical robots with the help of multimodal information perception in clinical applications from the perspective of multi-level perception and decision-making.

 

 

 

Keynote Speaker Ⅲ

Prof. Tae-Kyun (T-K) Kim

KAIST AGI Research Institute, South Korea

 

Biography: Tae-Kyun (T-K) Kim is Professor and the director of Computer Vision and Learning Lab at School of Computing, KAIST since 2020, and has been an adjunct reader of Imperial College London (ICL), UK for 2020-2024. He led Computer Vision and Learning Lab at Imperial College during 2010-2020. He obtained his PhD from Univ. of Cambridge in 2008 and Junior Research Fellowship (governing body) of Sidney Sussex College, Univ. of Cambridge during 2007-2010. His BSc and MSc are from KAIST in 1998 and 2000, he worked at Samsung AIT for 2000-2004 (military duty). His research interests primarily lie in machine (deep) learning for 3D computer vision, generative AI and AI with Physics, including: articulated 3D hand/body reconstruction, face analysis and recognition, 6D object pose estimation, activity recognition, object detection/tracking, active robot vision, which lead to novel active and interactive visual sensing. He has co-authored over 120 academic papers in top-tier conferences and journals in the field, and has co-organised series of HANDS workshops and 6D Object Pose workshops (in conjunction with CVPR/ICCV/ECCV) since 2015 to 2020. He was the general chair of BMVC17 in London, the program co-chair of BMVC23, and is Associate Editor of IEEE Trans on PAMI, Pattern Recognition Journal, Image and Vision Computing Journal. He regularly serves as an (Senior) Area Chair for top-tier vision/ML conferences. He received KUKA best service robotics paper award at ICRA 2014, and 2016 best paper award by the ASCE Journal of Computing, and the best paper finalist at CVPR 2020, and his co-authored algorithm for face image representation is an international standard of MPEG-7 ISO/IEC.

 

Speech Title: World Model: Spatial Physical Generative AI 

 

Abstract: Recent advances in generative AI have produced impressive language, image, and video models, yet these systems often lack a grounded understanding of 3D space, motion, interaction, and physical causality. This talk explores a path beyond large language models toward spatial and physical artificial general intelligence through physics-grounded world models. It presents our recent work on physically realistic digital humans, deformable hand–object interactions, and simulation-guided video generation, including MPMAvatar, PhysHanDI, and 3DPhysVideo. By integrating differentiable physical simulation, 3D scene reconstruction, and generative video models, these approaches improve physical consistency, controllability, and generalization across objects, materials, and interactions. The talk also introduces the Goldberg Machine Test as a grand challenge for evaluating compositional and long-horizon physical intelligence. Together, these developments suggest that combining learned representations with explicit physical reasoning is essential for building world models capable of supporting embodied AI and, ultimately, spatial physical AGI.

 

 

Keynote Speaker Ⅳ

Prof. Sung-Bae Cho

Yonsei University, South Korea

IEEE Fellow

 

Biography: Sung-Bae Cho received Ph.D. degree in computer science from KAIST (Korea Advanced Institute of Science and Technology) in 1993. He was an invited researcher of Human Information Processing research laboratories at ATR (Advanced Telecommunications Research) institute, Japan, from 1993 to 1995, a visiting scholar at University of New South Wales, Australia, in 1998, a visiting professor at University of British Columbia, Canada, from 2005 to 2006, and at King Mongkut’s University of Technology at Thonburi, Thailand, in 2013. Since 1995, he has been a professor in department of computer science, Yonsei University, a Underwood distinguished professor from 2021, and a Yonsei Fellow from 2023. His research interests include neural networks, pattern recognition, intelligent man-machine interfaces, evolutionary computation, and artificial agent. Dr. Cho was the recipient of the Richard E. Merwin prize from IEEE Computer Society in 1993. He received several distinguished investigator awards from Korea Information Science Society in 2015, and Gaheon Sindoricoh in 2017. He is also a recipient of service merit medal from Korean government in 2022, Yonsei academic award in 2026, and Sudang prize in 2026. Currently he is the Fellow of IEEE, AAIA, APNNS, KAST (Korean Academy of Science and Technology), and NAEK (National Academy of Engineering of Korea), and a member of Presidential Council on National Artificial Intelligence Strategy in Korea.

 

Speech Title: Exploiting Artificial Intelligence with Non-Euclidean Representation Learning for Video Anomaly Detection

 

Abstract: Large language models open another renaissance of artificial intelligence (AI) that is a long dream of human-beings. Nowadays, they are recognized not only as one of promising techniques of AI, but also as a game changer for everyday life. In this talk, I will give the general overview of AI, and explore the transformative role of AI in addressing the problem of video anomaly detection (VAD). 
Unsupervised VAD methods often train on normal videos using proxy tasks such as frame reconstruction or next-frame prediction and detect anomalies through reconstruction errors. However, optimizing such proxy tasks in Euclidean latent spaces tends to capture low-level statistics or spurious correlations, making the model brittle to rare but normal appearances and scene-dependent behaviors. I will present an unsupervised VAD method that models normal patterns as a scene-dependent manifold in a hyperbolic space, and show the superiority to 26 recent methods with experiments on three benchmark datasets, UCSDPed2, CUHKAvenue, and ShanghaiTechCampus.