►►Plenary Session

▲Prof. Li Ma
     ——Opening Speech and Conference Welcome
 

▲Prof. Jianfei Cai
     ——Deep Learning Based 3D Human Analysis with Limited Labels
 

▲Prof. Lijun Wang
     ——Ai Super Resolution Techniques and Its Applications
 

▲Prof. Jixin Ma
     ——About the Dividing Instant Problem (DIP)
 

►►Parallel Session
 

		Session Title: Data Science and Key Technology
		Session Chair:   Prof. Jixin Ma, University of Greenwich, UK
		Best Paper Presenter: Jianfeng Wang, Tsinghua University, China T009: DPA: Demand-based Partition and Data Allocation for Hybrid On-chip Memory

Session Title: Intelligent Algorithm and Calculation Method
Session Chair: Prof. Yanjun Li, Henan University of Technology, China
Best Paper Presenter:  Zhu Tang, National University of Defense Technology, China T063: Network Encrypted Traffic Classification Based on Secondary Voting Enhanced Random Forest

		Session Title: Computer Vision and Image Processing
		Session Chair:   Prof. Jianhua Wu, Nanchang University, China
		Best Paper Presenter: Yida Yin, High School Affiliated to Shanghai Jiao Tong University, China T024: Partial View Segmentation: A Novel Approach to the Brain Tumor Segmentation

Session Title: Modern Information Theory and Signal Processing
Session Chair: Assoc. Prof. Zongling Li, China Academy of Space Technology, China
Best Paper Presenter:  Jie Zhan, Beijing Institute of Technology, China T003: On the Design of Jitter Free Symbol Synchronization Lock Detector

		Session Title: Information Network and Application Technology
		Session Chair:   Dr. Diallo Bassoma, Southwest Jiaotong University, China
		Best Paper Presenter: Qingwei Yang, National University of Defense Technology, China T1007: Sparse Aperture based Radar Observation Resource Allocation Algorithm for Space Target 3D Imaging

Session Title: Computer Science and Information Engineering
Session Chair: Dr. Ghufran Ahmad Khan, Southwest Jiaotong University, China
Best Paper Presenter:  Xinjing Qin, Dalian University of Technology, China T054: Mobile handheld devices and embedded in things Picking System

✺  Congratulations to the Winners of the Best Presentation Awards 2020  ✺

Speakers of CVIT2020:

Prof. Shigang Chen (IEEE Fellow)

University of Florida, USA

Biography: Dr. Shigang Chen (sgchen@cise.ufl.edu) is a professor with Department of Computer and Information Science and Engineering at University of Florida. He received his B.S. degree in computer science from University of Science and Technology of China in 1993. He received M.S. and Ph.D. degrees in computer science from University of Illinois at Urbana-Champaign in 1996 and 1999, respectively. After graduation, he had worked with Cisco Systems for three years before joining University of Florida in 2002. His research interests include Internet of things, big data, cybersecurity, RFID technologies, intelligent cyber-transportation systems, etc. He published over 200 peer-reviewed journal/conference papers. He received the NSF CAREER Award and several best paper awards. He holds 13 US patents, and many of them were used in software products. He served as an associate editor for IEEE Transactions on Mobile Computing, IEEE/ACM Transactions on Networking and a number of other journals. He served in various chair positions or as committee members for numerous conferences. He holds the University of Florida Research Foundation Professorship and the University of Florida Term Professorship. He is a Fellow of IEEE and an ACM Distringuished Scientist.

Title: Privacy in Data Collection and Sharing
Abstract: In the era of big data and the Internet of things, the world has been experiencing an unprecedented growth in data availability and ever more sophisticated data analytic applications. However, technological advance in modern data collection and sharing comes with a societal price -- in the loss of privacy. In this talk, we address the issue of privacy protection in medical big data and IoT. We discuss various technical methods and research challenges with two promising privacy solutions under application contexts though they are applicable beyond those contexts: (1) For medical data sharing, we discuss multi-staged matrix masking algorithms to provide full privacy protection of medical data for its entire lifecycle in an effort for free global exchange of masked medical data with full statistical utility and provable patient privacy; (2) for IoT security, we develop extremely light-weight ciphers and strongly-anonymous security protocols that support applications of smart tags and smart transportation systems to collect sophisticated transportation traffic data without violating drivers' location privacy.

Prof. Lijun Wang,  Ph.D，  

North China University of Technology, China

Biography: Dr. Wang received his Ph.D degree from Beijing University of Posts and Telecommunications. He spent three years as postdoctoral fellow at Northwestern University, USA. After then, he had served as a senior research scientist in the R&D laboratory of Corning Incorporated, a Fortune 500 company in US for many years.  Dr. Wang is a accomplished scholar in the fields of ultra-high-speed fiber optic network, nonlinear optics and optoelectronic technologies. He has published more than 50 papers on top academic journals and received more than 20 patents. Dr. Wang is now a national special expert and consultant expert of Beijing municipal government. He is also the Chairman of AR/VR Technical Committee, International Information Display Society (SID) . His main research interests include Next Generation Display, Virtual and Augmented Reality (VR/AR) as well as Quantum Computing and Communication Technology.
 

Title: Ai Super Resolution Techniques and Its Applications
Abstract: Super-Resolution (SR) techniques are developed to upscaling low quality imagines or videos to high quality ones with better resolutions and details. The underlaying algorithm has evolved from traditional interpolation to deep learning. In this talk, we’ll discuss Ai based super resolution techniques, with especial focusing on our recent SR research works on processing VR imagines and panorama videos by developing a novel single frame and multi-frame joint network (SMJN)
Keywords:  Super-Resolution， Artificial Intelligence，Deep Learning，Virtual Reality, Panorama Video, Imagine Processing.
 

Prof. Jianfei Cai 

Monash University, Australia

Biography: Jianfei is a Professor at Faculty of IT, Monash University, where he currently serves as the Head for the Data Science & AI Department. Before that, he was a full professor, a cluster deputy director of Data Science & AI Research center (DSAIR), Head of Visual and Interactive Computing Division and Head of Computer Communications Division in Nanyang Technological University (NTU). His major research interests include visual computing, computer vision, and multimedia. He has published more than 200 technical papers in international conferences and journals. He is a co-recipient of paper awards in ACCV, ICCM, IEEE ICIP and MMSP. He has served as an Associate Editor for IEEE T-IP, T-MM, T-CSVT and Visual Computer as well as serving as Area Chair for ICCV, ECCV, ACM Multimedia, ICME and ICIP. He was the Chair of IEEE CAS VSPC-TC during 2016-2018. He had also served as the leading TPC Chair for IEEE ICME 2012.
 

Title: Deep Learning Based 3D Human Analysis with Limited Labels

Abstract: With the increasing computation capability and the increasing amount of labelled data available, deep learning technology has caused paradigm shift to the entire research community as well as to the whole IT industry. Despite the huge success of deep learning technology in various computer vision tasks such as image classification, object detection and semantic segmentation, its performance is still limited in the scenarios with large domain differences, with only a few or zero annotations, with hardware constraints, with multi-modal data, with 3D data, and with high reliability requirements, etc. In this talk, I will focus on the challenge of how to deal with deep learning based 3D human analysis tasks with limited labels. Particularly, I will introduce a series of my group’s works including real-time 3D face reconstruction with synthesized labels, weakly supervised 3D hand pose estimation, etc.

Prof. Jixin Ma

University of Greenwich, UK

Biography: Prof. Jixin Ma is a Reader of Computer Science in the Department of Computing and Information Systems, the Director of the Centre for Computer and Computational Science, and the Leader of Artificial Intelligence Research Group, at University of Greenwich, U.K. He is also a Visiting Professor of Beijing Normal University, Auhui University and Zhengzhou Light Industrial University, China. Dr Ma obtained his BSc and MSc of Mathematics in 1982 and 1988, respectively, and PhD of Computer Sciences in 1994. His main research areas include Artificial Intelligence, Software Engineering and Information Systems, with special interests in Temporal Logic, Temporal Databases, Reasoning about Action and Change, Case-Based Reasoning, Pattern Recognition and Graph Matching. He has published more than 100 research papers in international journals and conferences. Dr Ma has been the Editor of many international journals, including, "Computer and Systems", "Software Innovation", "Polibits", "Computer & Information Science", "Studies in Computational Intelligence", "Information & Communications Technology Law". He is also the Program Chair, Program Member and Invited Speakers of various international conferences, and has served as reviewers of many international journals and conferences. Dr Jixin Ma has been a Member of various international professional societies, including: British Computer Society, American Association of Artificial Intelligence, ICIS/IEEE, World Scientific and Engineering Society, UK Temporal Reasoning, Artificial Intelligence and Logic Group, and Special Group of Artificial Intelligence of BCS. In particular, Dr Ma has been acted as the Invited Keynote Speaker and Tutorial Presenter at many International Conferences/Symposiums/Workshops.

Title: About the Dividing Instant Problem (DIP)

Abstract: The so-called Dividing Instant problem (DIP) is an ancient historical puzzle encountered when attempting to represent what happens at the boundary instant which divides two successive states. The specification of such a problem requires a thorough exploration of the primitives of the temporal ontology and the corresponding time structure, as well as the conditions that the resulting temporal models must satisfy. The problem is closely related to the question of how to characterise the relationship between time periods with positive duration and time instants with no duration. It involves the characterisation of the "closed" and "open" nature of time intervals, i.e., whether time intervals include their ending-points or not. In the domain of Artificial Intelligence, the DIP may be treated as an issue of how to represent different assumptions (or hypotheses) about the DIP in a consistent way. This talk examines various temporal models including those based solely on points, those based solely on intervals, and those based on both points and intervals, and points out the corresponding DIP with regard to each of these temporal models. A classification of assumptions about the DIP is introduced with a solution to the corresponding DIP.