2024 3rd International Conference on Machine Vision, Automatic Identification and Detection (MVAID 2024)

Keynote Speakers


Prof. Youfu Li, City University of Hong Kong, China(IEEE Fellow)

李友福 教授,香港城市大学

Experience: You-Fu Li received the B.S. and M.S. degrees in electrical engineering from Harbin Institute of Technology, China. He obtained the PhD degree in robotics from the Department of Engineering Science, University of Oxford in 1993. From 1993 to 1995 he was a research staff in the Department of Computer Science at the University of Wales, Aberystwyth, UK. He joined City University of Hong Kong in 1995 and is currently professor in the Department of Mechanical Engineering. His research interests include robot sensing, robot vision, and visual tracking. In these areas, he has received many awards including a Second Prize of Natural Science Research Award by the Ministry of Education of China, for the work on “Active 3D Computer Vision”, and IEEE Sensors Journal Best Paper Award by IEEE Sensors Council. He has served as an Associate Editor for IEEE Transactions on Automation Science and Engineering (T-ASE), Associate Editor for IEEE  Robotics and Automation Magazine (RAM), Editor for CEB, IEEE International Conference on Robotics and Automation (ICRA), and Guest Editor for IEEE  Robotics and Automation Magazine (RAM). He is a fellow of IEEE.

Title:  Towards Flexible Calibration for Machine Vision Systems

Abstract:  Visual sensing is important to many engineering applications including tracking for robotics. In this talk, I will present our research in visual sensing and tracking focusing on the issues in the calibration. For robotic applications, visual sensing in 3D is often needed, but the calibration remains tedious and inflexible with traditional approach. To this end, we have investigated the relevant issues for different visual sensing systems. A flexible calibration method desires the vision system parameters to be recalibrated automatically or with less operator interference whenever the configuration of the system is changed, but practically this is often hard to achieve. Various attempts were made in our previous works to enhance the flexibility in the visual sensing calibration. I will present some them including the work on omni-directional visual sensing and tracking. Another case to present is that of gaze tracking where the issues in the parallax errors and the tedious calibration procedures are addressed with our new calibration method developed. 


Prof. Zhuhong You, Northwestern Polytechnical University, China

尤著宏 教授,西北工业大学

Experience: You Zhuhong, professor and doctoral supervisor in the School of Computer Science of Northwestern Polytechnical University. He is a doctoral candidate of University of Science and Technology of China (USTC), a postdoctoral candidate of Tongji University and Hong Kong Polytechnic University, a recipient of the National Science Foundation for Outstanding Youth, a recipient of the 14th batch of National Specialized Experts of the Organization Department of the Central Committee of the CPC Central Committee (OCAC), a recipient of the National Science Foundation for Excellent Youth, and a recipient of the Xiangjiang Scholar Program of the Ministry of Human Resources and Social Affairs. He is also a recipient of the 14th batch of "National Special Experts" by the Ministry of Organization of China, the "Excellent Youth" Science Foundation of China, and the "Xiangjiang Scholars" program by the Ministry of Human Resources and Social Affairs. He is mainly engaged in the research of pattern recognition, big data analysis and bioinformatics, and has published in IEEE Repertoire, PLOS Computational Biology, Briefings in Bioinformatics, Bioinformatics and other domestic and international academic journals, as well as ISBRA, IJCNN, WCCI, BIBM, etc. He is also a member of the International Society of Bioinformatics, WCCI, BIBM and other international conferences, more than 350 research papers have been published, and more than 290 papers have been indexed by SCI. Among them, there are 192 SCI papers as first and corresponding authors, and 62 papers in the first region of Chinese Academy of Sciences. His papers have been cited nearly 15,000 times by international famous journals and conferences (Google Scholar), with H-index of 66, the highest number of citations for a single paper is 550, and 216 citations for a single paper are more than 10, 10 ESI highly cited papers, 3 hot papers, and he has been selected as one of the most highly cited scholars in the world for many times by Elsevier, Stanford University and the University of California at Los Angeles. He has been listed in Elsevier's "Highly Cited Scholars List" for many times, and is one of the top 2% scientists in the world in Stanford University. He has written one monograph and applied for 16 invention patents. He has been awarded the first prize of Provincial Natural Science Award (the 1st completer), the second prize of Natural Science Award of Ministry of Education (the 2nd completer), and the second prize of Natural Science Award of Chinese Society of Automation (the 3rd), and so on. He has served as an editorial board member and guest editorial board member of more than ten SCI journals and program committee member of many international conferences.

Title:  Biomolecular Association Detection and Application Based on Biomedical Knowledge Graph Embedding

Abstract:  One of the key issues in the field of biomedicine in the post-genomic era is to systematically understand and analyze the inter-molecular relationships among biomolecules. Complex life activities are undertaken by a variety of biochemical molecules, which interact with each other to maintain the normal physiological functions of the organism, and whose perturbations or disruptions will lead to malfunctions or complex diseases. Guided by the idea of reductionism, existing researches have conducted in-depth studies on the activities of single or very few kinds of molecules, but lack of global thinking on the network of multi-molecular interactions, ignoring its holistic and systematic nature. With the advancement of multi-omics technology, single-cell sequencing technology and other research methods, a large amount of biomedical big data on intermolecular correlations has been rapidly accumulated, which challenges the traditional analysis and mining methods, but also provides valuable data support for us to explore the complex biomolecular correlation networks. This report combines two artificial intelligence techniques, knowledge graph and recommender system, by learning the low-dimensional representations of various biomolecules in the knowledge graph and multimodal fusion with biomolecular attribute features, and proposes a predictive mining method of molecular association graph based on graph machine learning on different scales of molecular association graph, this study will systematically reveal and construct different scales of molecular association graphs from molecular level to biomedical system level. molecular association maps at different scales from the molecular level to the biomedical system level.