Keynote Speakers
Title: Video Coding and Processing Based on Deep Learning
Abstract:
Brief Bio:
Pan Zhaoqing is a professor and doctoral supervisor at Tianjin University. Published over 60 academic papers in academic journals and conferences such as IEEE TIP, TMM, TCSVT, and hosted multiple national/provincial/ministerial level projects such as the National Natural Science Foundation's Outstanding Youth Science Fund, General Program, and Youth Program. Received the second prize of the Natural Science Award from the Ministry of Education (ranking 2) and the first prize of the Jiangsu Provincial Science and Technology Award (ranking 5). Selected from the Six Talent Summit High Level Talent Plan in Jiangsu Province, and the Beiyang Talent Plan of Tianjin University. Serve as an editorial board member, guest editor in chief, and program chairman for multiple international journals and conferences.
Title: 3D Face Dense Correspondence, Reconstruction and its Applications
Abstract:With the rapid development of artificial intelligence technology, more and more intelligent algorithms and models, such as surveillance object detection, face hallucination and super-resolution and deepfake face detection, are widely used in the field of public security criminal investigations. This talk introduces related technologies in 3D face dense correspondence algorithms, 3D face reconstruction models and 3D face-based applications in such scenarios. Specifically, it includes:(1) In terms of 3D face dense correspondence modeling, an automatic and landmark-free 3D face dense correspondence approach is proposed, which boosts point correspondence from global to local shape matching and can maintain the consistency of semantics and local geometric topological of 3D face; (2) For high-precision robust 3D face reconstruction, a lighting robust fitting approach of 3D morphable model face reconstruction is proposed, which uses the spherical harmonic lighting model instead of the Phong reflection model in the 3DMM algorithm to fit both diffuse reflection effects and specular effects, and thus generating a more realistic 3D face model; (3) In terms of 3D face-based applications, by incorporating 3D face information, the performance of algorithms for such tasks as face super-resolution reconstruction and deepfake face detection can be further improved.
Brief Bio:
Hu, Xiyuan received Ph.D degree in Institute of Automation, Chinese Academy of Sciences in 2011. After graduation, he became a member of High Technology Innovation Center (HITIC) in the Institute of Automation, CAS. Since June 2020, he became a full professor at the school of Computer Science and Engineering in Nanjing University of Science and Technology. He was a visiting scholar at Academia Sinica and Harvard University in 2012 and 2014, respectively. His research focus on multi-modal information fusion and understanding, and adaptive signal separation theory. He has published more than 80 journal and conference papers (such as Nature Communications, IEEE T-SP, IEEE T-MM, CVPR, ECCV, ACM MM, etc.) in these areas. He is coauthor of two books (Chinese Science Press and Tsinghua University Press). He served as Youth Director of Chinese Society for Imaging Science and Technology (CSIST) and Executive Committee Member of Forensic Evidence Quality Management Technical Committee of Forensic Science Association of China (FSAC). In 2020, he won First prize of science and technology award of the Ministry of Public Security of China. In 2019, he won Youth Science and Technology Award of Chinese Society for Imaging Science and Technology (CSIST) and Scientific and Technology Progress Award of Chinese Computer Federation (CCF).
Title: Green and Multiple Access Techniques for Future Wireless Networks
Abstract:Future wireless networks (5G, 6G and beyond) have diverse service requirements such as energy efficiency, low latency, massive connectivity, etc. How to design and develop efficient networking and multiple access techniques to meet such diverse requirements are important research areas for future wireless networks. This keynote talk summarises and presents some recent research work on these areas towards green networks and efficient multiple access techniques for future wireless networks.
Brief Bio:
Qiang Ni (M’04–SM’08) is currently a Professor and the Head of the Communication Systems Group, School of Computing and Communications, Lancaster University, Lancaster, U.K. His research interests include the area of future generation communications and networking, including green communications and networking, millimeter-wave wireless communications, cognitive radio network systems, non-orthogonal multiple access (NOMA), heterogeneous networks, 5G and 6G, SDN, cloud networks, energy harvesting, wireless information and power transfer, IoTs, cyber physical systems, AI and machine learning, big data analytics, and vehicular networks. He has authored or co-authored 300+ papers in these areas. He was an IEEE 802.11 Wireless Standard Working Group Voting Member and a contributor to various IEEE wireless standards.
Title: Multigranulation Modeling and Knowledge Discoveryfor Uncertain Big Data
Abstract:
Since big data often contains a significant amount of unstructured, imprecise and uncertain data, the granular computing based attribute reduction has played an important role in the underlying technologies of uncertainty reasoning and data mining for big data.
Granular computing aims to find a suitable level of granularity of given problems which can be adjusted according to the degree of fuzziness of the given problem. It can provide a powerful tool for multiple granularity and multiple-view data mining and knowledge processing. In this report, we will discuss key concepts and architectures related to the data mining and computational intelligence, information granules and multigranulation computing, and present two granular feature section frameworks based on co-evolutionary MapReduce/Spark. Meanwhile, we propose some effective multigranulation feature section algorithms for uncertain big data and discuss the multigranulation knowledge processing methods with deep learning. The related researches substantiate the effectiveness and accuracy of the proposal models and algorithms to solve uncertain big data problems. Furthermore, the proposed models and algorithms are well applied in large-scale medical images segmentation, which indicates their great potential for disorder prediction. Some discussions will be given on the future work and outlook for multigranulation knowledge processing for uncertain big data issues.
In the end, some experiences and suggestions will be provided about how to submit high-quality papers to IEEE Transactions and Elsevier Journals, from Associate Editor or Editorial Board Member profile.
Brief Bio:
Weiping Ding (M’16-SM’19) received the Ph.D. degree in Computer Science, Nanjing University of Aeronautics and Astronautics, Nanjing, China, in 2013. From 2014 to 2015, he is a Postdoctoral Researcher at the Brain Research Center, National Chiao Tung University, Hsinchu, Taiwan. In 2016, He was a Visiting Scholar at National University of Singapore, Singapore. From 2017 to 2018, he was a Visiting Professor at University of Technology Sydney, Ultimo, NSW, Australia. Now he is a professor of School of Information Science and Technology, Nantong University, China. His research interests include deep neural networks, multimodal machine learning, granular computing and medical images analysis. He has published over 250 articles, including 92 IEEE Transactions papers, such as IEEE Transactions on Fuzzy Systems, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, IEEE Transactions on Evolutionary Computation,IEEE Transactions on Systems, Man, and Cybernetics: Systems, IEEE Transactions on Intelligent Transportation Systems, and so on.His fifteen authored/co-authored papers have been selected as ESI Highly Cited Papers.He has co-authored four books. He has holds 27 approved invention patents, including two U.S. patents and one Australian patent. He serves as the Associate Editor/Editorial Board member of IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Fuzzy Systems, IEEE/CAA Journal of Automatica Sinica, IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Intelligent Vehicles, IEEE Transactions on Emerging Topics in Computational Intelligence, IEEE Transactions on Artificial Intelligence, Information Fusion, Information Sciences, Neurocomputing, Applied Soft Computing, and so on. He is the Leading Guest Editor of Special Issues in several prestigious journals, including IEEE Transactions on Evolutionary Computation, IEEE Transactions on Fuzzy Systems, and Information Fusion. He is the Co-Editor-in-Chief of both Journal of Artificial Intelligence and Systems and Journal of Artificial Intelligence Advances.