Prof. Bin Liu

Dalian University of Technology, China

Biography:  Bin Liu, a professor at Dalian University of Technology, a doctoral supervisor, a visiting professor at Dalian University Affiliated Hospital, a member of the Higher Education Committee of the Ministry of Education, the director and technical leader of the Key Laboratory of Medical Simulation Technology in Liaoning Province, a standing committee member of the Chinese Research Hospital Society's Neuroregeneration and Repair Professional Committee, a member of the 3D Printing Technology Branch of the China Biomedical Technology Association, a standing committee member of the Liaoning Anti-Cancer Association, a branch committee member of the Liaoning Anti-Cancer Association, the deputy director of the Bone Tumor and Cell Biology Research Special Committee of the Liaoning Cell Biology Society, the deputy director of the Digital Medicine Special Committee of the Liaoning Cell Biology Society, and the standing committee member of the Advanced Medical-Engineering Integration Technology Special Committee of the Liaoning Cell Biology Society. His main research directions include computer vision and graphics images, intelligent medical image processing and analysis, computer-assisted three-dimensional preoperative planning and simulation. He has led 1 project of the National Key Research and Development Program of the Ministry of Science and Technology for the "14th Five-Year Plan", 4 projects of the National Natural Science Foundation of China, and over 20 provincial and ministerial-level, and commissioned projects. He has published over 70 international journal papers as the first author or corresponding author, and has obtained over 30 national invention patents as the first complete person, and over 40 software copyrights. He serves as a member of the editorial board of several international journals such as "The International Journal of Medical Robotics and Computer Assisted Surgery", and is an expert in the review of key projects of the National Natural Science Foundation of China, special projects, face projects, and young projects.

Speech Title: Mesh Model Registration via Deep Mapping by Local Projection for Optical Scanning-Based Reverse Engineering

Abstract: For mesh model obtained by optical scanning in reverse engineering, sub models registration to be the complete model is a key step. However, currently widely used registration methods may need well initial position condition. Moreover, in some common adverse conditions (e.g. with large angle differences, with incomplete common parts), they cannot achieve registration for sub models. We solve these issues from a direct matching viewpoint and present a robust and straightforward learning based registration method for 3D mesh models with any initial position conditions. Comparing with other classic methods, it not only can achieve registration with any initial angle difference, but also can complete registration with inclusion relation and common parts.

Prof. Zhenghao Shi

Xi'an University of Technology, China

Biography:  Zhenghao Shi, Ph.D., Professor and Doctoral Supervisor, Member of the Academic Committee of Xi'an University of Technology, Distinguished Member of CCF, "500 Elite Talents" of Taizhou City, Zhejiang Province, Chair of the Computer Vision Technology Professional Committee of the Shaanxi Computer Federation, Deputy Chair of the Biomedical Intelligent Computing Professional Committee of the Shaanxi Computer Federation, and Leader of the Research Team on Intelligent Image Processing and Application at Xi'an University of Technology. His main research interests include machine vision, medical image processing, and machine learning. He has published or accepted 40 academic papers as the first author or corresponding author. He has been awarded the Second Prize of Shaanxi Provincial Science and Technology Progress Award (ranking first), the Second Prize of Xi'an Science and Technology Progress Award (ranking first), and the Second Prize of Shaanxi Higher Education Science and Technology Award (ranking first) twice

Speech Title: Low light image processing methods: from prior to deep learning

Abstract: In practical applications, the enhancement processing of low light and low illumination images has always faced the problem of low efficiency and low quality. This report will introduce the research progress of this issue based on our practical experience in this field in the past two years, with a focus on reporting our work and achievements in using deep learning methods for low light image enhancement.

Prof. Xiangjie Kong

Zhejiang University of Technology

Biography: Dr. Xiangjie Kong is currently a Full Professor and Vice Dean in the College of Computer Science & Technology, Zhejiang University of Technology (ZJUT), China. Previously, he was an Associate Professor in School of Software, Dalian University of Technology (DUT), China, where he was the Head of the Department of Cyber Engineering. He is the Founding Director of City Science of Social Computing Lab (The CSSC Lab) (http://cssclab.cn/). He is/was on the Editorial Boards of 6 International journals. He has served as the General Chair or Program Chair of more than 10 conferences. Dr. Kong has authored/co-authored over 300 scientific papers in international journals and conferences including IEEE TKDE, IJCAI, ACL, IEEE TMC, ACM CSUR, ACM TKDD, IEEE TNSE, IEEE TII, IEEE TITS, IEEE NETW, IEEE COMMUN MAG, IEEE TVT, IEEE IOJ, IEEE TSMC, IEEE TETC, IEEE TASE, IEEE TCSS, ACM TSON, ACM TSAS, WWWJ, etc.. 5 of his papers is selected as ESI- Hot Paper (Top 1‰), and 20 papers are ESI-Highly Cited Papers (Top 1%).  His research has been reported by Nature Index and other medias. He has been invited as Reviewers for numerous prestigious journals including IEEE TKDE, IEEE TMC, IEEE TNNLS, IEEE TNSE, IEEE TII, IEEE IOTJ, IEEE COMMUN MAG, IEEE NETW, IEEE TITS, TCJ, JASIST, etc.. Dr. Kong has authored/co-authored three books (in Chinese). He has contributed to the development of 24 copyrighted software systems and 30 filed patents. He has an h-index of 58 and i10-index of 171, and a total of more than 13000 citations to his work according to Google Scholar. He is named in the 2019 – 2025 world’s top 2% of Scientists List published by Stanford University. He is named in the 2022-2024 Best Computer Science Scientists List published by Research.com. Dr. Kong received IEEE Vehicular Technology Society 2020 Best Land Transportation Paper Award, IEEE CSCWD 2024 Best Paper Award, and The Natural Science Fund of Zhejiang Province for Distinguished Young Scholars. He has been invited as Keynote Speaker at more thant 10 international conferences, and delivered a number of Invited Talks at international conferences and many universities worldwide.  His research interests include big data, network science, and computational social science. He is a Distinguished Member of CCF, a Senior Member of IEEE, a Full Member of Sigma Xi, and a Member of ACM.

Speech Title: Visual Object Tracking across Modalities

Abstract: Visual Object Tracking (VOT) is a fundamental task in computer vision, essential for applications such as intelligent surveillance, autonomous driving, and robotic navigation. Over the past decades, VOT has rapidly transitioned from traditional methods based on handcrafted features to deep learning-based approaches, significantly enhancing its accuracy and robustness. Benefiting from the rapid development of deep learning and multi-modal sensing technologies, VOT is evolving to handle increasingly complex and dynamic environments. In applications like autonomous driving, where robust perception under varying weather and lighting is crucial, or inintelligent surveillance requiring reliable tracking across sensor types, multi-modal VOT plays a key role in ensuring accurate and resilient object tracking. This presentation provides a comprehensive overview of Visual Object Tracking across different data modalities, covering its foundational theories, state-of-the-art methods, evaluation benchmarks, and future research directions. 

Keynote Speaker 4

Assoc. Prof. Aslina Baharum

Taylor's University, Malaysia

Biography:  Ts. Dr Aslina Baharum is an Associate Professor and UX Researcher at The Design School, Faculty of Innovation & Technology, Taylor's University. Previously, she was an Associate Professor at the School of Engineering and Technology, Sunway University, and  Senior Lecturers at Universiti Teknologi MARA (UiTM), and Universiti Malaysia Sabah (UMS). She also has industry experiences where she worked as an IT Officer for the Forest Research Institute of Malaysia (FRIM). She had experienced more than 20 years in the IT field. She received a PhD in Visual Informatics (UKM), a Master Science degree in IT (UiTM) and graduated Bachelor of Science (Hons.) in E-Commerce from UMS. She is a member of the Young Scientists Network - Academy of Science Malaysia, Senior Member IEEE, and certified Professional Technologist from MBOT, and served as MBOT/MQA auditor. 

She won several medals in research and innovation showcases and was awarded several publication awards, teaching awards, Excellence Service award, and UMS Researchers Awards. She has co-authored and editor books, published several books of chapters (>20), technical papers in conferences and peer-reviewed and indexed journals (>60) papers. She also served as editor for several journals, scholarly contributed as a committee, editorial team and reviewers, and given several invited/ plenary talks at conferences. 

Her research interests include UX/UI, HCI/Interaction Design, Product & Service Design, Software Engineering & Mobile Development, Information Visualization & Analytics, Multimedia, ICT, IS and Entre/Technopreneurship. Her workshops and talks covered Entrepreneurship, Video/Image Editing, E-Commerce/Digital Marketing, AR/VR/MR/XR in STEM, Design Thinking and etc. She is also a Certified Professional Entrepreneurial Educator, Executive Entrepreneurial Leaders and HRDF Professional Trainer.

Speech Title: From Vision to Experience: Human-Centered AI in Advanced Imaging and Intelligent Systems

Abstract: The rapid evolution of advanced imaging technologies and intelligent computing systems is redefining how machines interpret and interact with the world. While significant progress has been made in areas such as object detection, 3D vision, and biomedical imaging, the translation of these capabilities into meaningful user experiences remains a key challenge. This keynote emphasizes the transition from vision to experience, highlighting the importance of embedding human-centered AI principles into the design of next-generation imaging and intelligent systems. By integrating AI-UX methodologies with cutting-edge developments in computer vision, the talk demonstrates how technical performance can be aligned with usability, trust, and user satisfaction. Focusing on interdisciplinary applications, including healthcare diagnostics, smart environments, and immersive technologies, this session presents design frameworks that prioritize user needs, cognitive ergonomics, and contextual awareness. It also explores emerging directions such as real-time interaction, edge AI, and explainable imaging systems that support more intuitive and responsive human-AI collaboration. The keynote concludes by outlining a vision for future intelligent systems that not only see and analyze but also understand, adapt, and enhance human experience, paving the way for more inclusive, ethical, and impactful AI-driven technologies.