| Prof. Jiayi MaWuhan University Dr. Jiayi Ma is a Full Professor at the School of Robotics, Wuhan University. He has been selected for the National High-Level Young Talents Program, with research interests in computer vision and information fusion. He has published over 300 papers in top-tier journals and conferences, including CVPR, ICCV, IEEE TPAMI, IJCV, and Cell. He has received the Hsue-shen Tsien Paper Award and the Information Fusion Best Paper Award. His research has garnered over 44,000 citations on Google Scholar, with an H-index of 96. He is a recipient of the Hubei Province Natural Science First Prize (first author) and currently serves as Co-Editor-in-Chief of Information Fusion and as an Associate Editor or Youth Editor of several journals such as IEEE TIP, IEEE/CAA JAS, and The Innovation. Title: Application-Oriented Multimodal Image Fusion Abstract: Image fusion aims to integrate complementary information from different source images into a single fused image that comprehensively represents the imaging scene, thereby significantly enhancing capabilities in object recognition, scene perception, and environmental understanding. This talk focuses on application-oriented multimodal image fusion, analyzing the current challenges and development opportunities in this field while systematically introducing several representative methods. The discussion focuses on directions such as unregistered multimodal image fusion, image fusion guided by the synergy of high- and low-level vision tasks, and image fusion with degradation robustness and text-controllable capabilities. Additionally, by investigating typical application scenarios, the talk demonstrates its practical value and broad application prospects. |
| Prof. Zhongyuan WangWuhan University Wang Zhongyuan, a professor at the School of Computer Science, Wuhan University, specializes in multimedia information processing and its applications in social security. He has led multiple national and provincial-level research projects, authored over 50 academic papers, with several being recognized as ESI Highly Cited Papers. Under his guidance, students have achieved top honors, including first place in the International TRECVID Competition, the Best Paper Award from the International Association for Biometrics, and the Nomination Award for Outstanding Doctoral Dissertation from the China Society of Image and Graphics. His research contributions have been honored with the Hubei Province First Prize for Technological Invention and the Guangdong Province First Prize for Scientific and Technological Progress. Title:Trustworthy Face Recognition in Social Security Abstract: Trusted face recognition is a crucial supporting technology in social governance. Recognizing faces with mask occlusion presents greater challenges compared to conventional face recognition. This report introduces several effective methods for mask-occluded face recognition from the perspectives of facial samples and recognition models. Furthermore, in response to the threats posed by Deepfake technology to authentic identity verification, the report elaborates on technical approaches and their effectiveness in combating AI-driven identity fraud in cyberspace, aiming to safeguard identity security. |
| Prof. Leyuan LiuCentral China Normal University Leyuan Liu is a Doctoral Supervisor and Professor at Central China Normal University. His primary research interests encompass computer vision and computer graphics, AI-assisted special education, the educational metaverse, and educational robotics. Professor Liu has led more than ten projects funded by organizations such as the National Natural Science Foundation of China, the National Key Research and Development Program of China, and the Hubei Provincial Natural Science Foundation, and has also been a key participant in several major national initiatives. He has published over eighty research papers in leading journals, including IEEE Transactions on Multimedia, and at top-tier AI conferences such as CVPR, ECCV, and ACM MM. He holds more than twenty authorized Chinese patents and has received multiple academic honors, including the First Prize of the Hubei Provincial Science and Technology Progress Award (2020), the Second Prize of the Hubei Provincial Award for Outstanding Achievements in Social Science (2018 & 2020), and the First Prize of the Hubei Provincial Award for Excellent Papers in Natural Science (2012). Title: High-Fidelity Twin Digital Human Generation Technology and Its Application in Autism Intervention Abstract: Autism spectrum disorder (ASD) is a pervasive neuro-developmental condition in children, primarily characterized by impairments in social interaction and language ability. In recent years, extensive research has sought to integrate artificial intelligence technologies into autism intervention. However, due to impairments in the mirror neuron system of children with ASD, existing approaches often rely on third-person surrogate agents, which limits their intervention effectiveness. This report introduces a novel approach that applies high-fidelity twin digital humans to autism intervention by constructing first-person digital self-avatars for children with ASD, thereby mitigating the impact of mirror neuron system deficits. The report first presents the background and motivation for this approach, then elaborates on the core technologies of high-fidelity digital human generation, including single-image 3D head reconstruction and texture synthesis, 3D human pose estimation and reconstruction, diffusion-based high-quality texture generation, and voice cloning. On the application side, it highlights a metaverse-based intervention system designed for children with ASD, where personalized digital avatars and customized voices create immersive, individualized, and controllable environments. Empirical studies validate the appropriateness and potential of this technology in autism intervention. Finally, the report discusses future prospects of high-fidelity twin digital humans in education, rehabilitation, and interdisciplinary integration. |
| Prof. Junjun JiangHarbin Institute of Technology Junjun Jiang is a Tenured Professor and Ph.D. supervisor at the School of Computer Science, Harbin Institute of Technology, and currently serves as Associate Dean of the School of Artificial Intelligence. He was selected into the National Youth Talent Program. He received his Ph.D. degree from the School of Computer Science, Wuhan University, in December 2014, and worked as a Specially Appointed Researcher at the National Institute of Informatics, Japan, from 2016 to 2018. His research interests mainly include image processing, computer vision, and deep learning. He has published over 100 papers in IEEE Transactions journals and CCF-A conferences, with more than 24,000 citations on Google Scholar and an H-index of 70. He has been recognized as a Highly Cited Researcher and ranked among the top 0.05% of scientists worldwide. He serves as an Editorial Board Member of Information Fusion (Best Editor Award, 2024), and as a Youth Editorial Board Member of Fundamental Research and IEEE/CAA JAS. He is a recipient of the Wu Wenjun AI Outstanding Youth Award and the CCF Excellent Doctoral Dissertation Award. He has led projects funded by the National Key R&D Program of China and the National Natural Science Foundation of China (key, general, and youth programs). Title: Multimodal Information Fusion and Intelligent Perception Abstract: In recent years, driven by the rise and rapid advancement of deep learning, supervised learning based on large-scale annotated datasets has achieved breakthrough performance in specific computer vision tasks within closed environments. Meanwhile, these methods are approaching performance saturation and face increasing challenges when applied to real-world, open-world settings. In response to the critical need for multimodal visual fusion and perception in real-world scenarios, our research focuses on key issues such as few-shot learning, weak supervision, multi-source heterogeneity, and cross-domain adaptation. This line of work aims to provide technical support for intelligent perception and autonomous decision-making in unmanned systems operating in complex environments. This talk will primarily highlight our team’s recent research progress on multimodal information fusion and perception under open-world conditions. |
