Speakers

Prof. Guangjie Han

IEEE Fellow, IET/IEE Fellow, AAIA Fellow

Hohai University, China

Bio: Guangjie Han (Fellow, IEEE) is currently a Professor with the Department of Internet of Things Engineering, Hohai University, Changzhou, China. He received his Ph.D. degree from Northeastern University, Shenyang, China, in 2004. In February 2008, he finished his work as a Postdoctoral Researcher with the Department of Computer Science, Chonnam National University, Gwangju, Korea. From October 2010 to October 2011, he was a Visiting Research Scholar with Osaka University, Suita, Japan. From January 2017 to February 2017, he was a Visiting Professor with City University of Hong Kong, China. From July 2017 to July 2020, he was a Distinguished Professor with Dalian University of Technology, China. His current research interests include Internet of Things, Industrial Internet, Machine Learning and Artificial Intelligence, Mobile Computing, Security and Privacy. Dr. Han has over 500 peer-reviewed journal and conference papers, in addition to 160 granted and pending patents. Currently, his H-index is 59 and i10-index is 249 in Google Citation (Google Scholar). The total citation count of his papers raises above 12900+ times.

Dr. Han is a Fellow of the UK Institution of Engineering and Technology (FIET). He has served on the Editorial Boards of up to 10 international journals, including the IEEE Systems, IEEE/CCA JAS, IEEE Network, etc. He has guest-edited several special issues in IEEE Journals and Magazines, including the IEEE JSAC, IEEE Communications, IEEE Wireless Communications, IEEE Transactions on Industrial Informatics, Computer Networks, etc. Dr. Han has also served as chair of organizing and technical committees in many international conferences.He has been awarded 2020 IEEE Systems Journal Annual Best Paper Award and the 2017-2019 IEEE ACCESS Outstanding Associate Editor Award. He is a Fellow of IEEE.

报告题目：“软件定义”重构水下多智能体网络：若干研究进展与思考

摘要：水下多智能体协同技术、水下群体智能技术的飞速发展促使以水下自主航行器集群为代表的水下智能装备集群在海洋工程、海洋科学研究等领域得到广泛应用，并终将赋能海洋网络化、数字化和透明化发展。然而，海洋环境的复杂性使水下智能体集群在协同执行水下任务时通信困难、协同性弱、危险性强，成为制约水下智能体集群技术及应用发展的关键性因素。鉴于此，本报告引入水下多智能体网络的概念，以支持水下智能体集群间的自主通信。在此基础上，引入“软件定义网络”技术，重构水下多智能体网络的基础架构，解耦网络的控制决策与任务操作平面，以支持软件定义式的水下协同操作，提升网络可编程性及可扩展性。然后，结合本实验室团队在该方向的研究成果，介绍如何利用软件定义网络技术，重构水下多智能体网络的数据路由架构、编队航行架构以及自主学习决策架构。本报告旨在提供一种研究思路，重新审视与构建水下多智能体系统的协同控制机制，构建“软件定义智慧海洋”，以助力逐梦深蓝、向海而行。

Prof. Xiangjian He

University of Nottingham Ningbo, China

Bio: Professor Xiangjian (Sean) He received his PhD in Computer Science from the University of Technology Sydney in 1999. He is currently the Deputy Head of Computer Science School and the Director of Computer Vision and Intelligent Perception Laboratory at the University of Nottingham Ningbo China (UNNC).

He is in list of the 'World Top 2% Scientists' reported by Stanford University in 2022.

He was the Professor of Computer Science and the Leader of Computer Vision and Pattern Recognition Laboratory at the Global Big Data Technologies Centre (GBDTC) at the University of Technology Sydney (UTS) from 2011-2022.  He was an IEEE Signal Processing Society Student Committee member. He was involved in a team receiving a UTS Chancellor's Award for Research Excellence through Collaboration in 2018. He has been awarded 'Internationally Registered Technology Specialist' by International Technology Institute (ITI). He led the UTS and Hong Kong Polytechnic University (PolyU) joint research project teams winning the 1st Runner-Up prize for the 2017 VIP Cup, and the champion for the 2019 VIP Cup, awarded by IEEE Signal Processing Society. In 2021, the team, PolyUTS, led by Prof Lam of PolyU and co-led by Prof He of UTS again won the 1st Runner-Up award for the 2021 VIP Cup.

He has been carrying out research mainly in the areas of computer vision, data analytics and machine learning in the previous years. He has recently been leading his research teams for deep-learning-based research for human behavious recognition, human counting and density estimation, tiny object detection, biomedical applications, saliency detection, natural language processing, cybersecurity, face and face expression recognition, road sign detection, license plate recognition, etc. He has played various chair roles in many international conferences such as ACM MM, MMM, ICDAR, IEEE BigDataSE, IEEE BigDataService, IEEE TrustCom, IEEE CIT, IEEE AVSS, IEEE ICPR and IEEE ICARCV.

Report Title: Salient Object Detection

Abstract: Salient object detection aims to mimic the human visual system and cognition mechanisms to identify and segment salient objects. However, due to the complexity of these mechanisms, current methods are not perfect. Accuracy and robustness need to be further improved, particularly in complex scenes with multiple objects and background clutter. In this talk, two methods are presented. The first approach estimates depth information from monocular RGB images and leverage the intermediate depth features to enhance the saliency detection performance in a deep neural network framework. Although many other RGB-D saliency models have also been proposed, they require to acquire depth data, which are expensive and not easy to obtain. The second approach adopts the boundary sensibility, content integrity, iterative refinement, and frequency decomposition mechanisms. A multi-level hybrid loss is designed to guide the network to learn pixel-level, region-level, and object-level features. Comprehensive evaluations on challenging benchmark datasets show the achievements of state-of-the-art results of the proposed approaches.

Prof. Chunyi Chen

Changchun University of Science and Technology, China

Bio: Chunyi Chen is Professor, PhD, and PhD supervisor at School of Computer Science and Technology, Changchun University of Science and Technology. His main research interests cover panoramic stereo modelling and processing, wireless optical communication, information security, and new film imaging and display. He has undertaken many research projects supported by the National Natural Science Foundation of China; the National Science and Technology Support Program; the National Key R&D Program; the 863 Program; the 973 Program; Chinese Postdoctoral Science Foundation; the Jilin Provincial Science and Technology Development Program; and the Chongqing Natural Science Foundation. A number of his research findings have been applied in the field of cultural theme parks, virtual museum exhibition, long-distance optical information transmission, etc. He is Member of the Virtual Reality Committee, China Society of Image and Graphics, Director of Society of Image and Graphics, and Director of Jilin Association of Robot.

Report Title: Removing redundant computation in 3D scene rendering using limitations of human visual perception

Abstract: Rendering of realistic 3D scenes is crucial for applications such as movie production, virtual reality, computer games, and so on. Realism and speed are two important factors that need to be carefully considered in designing a rendering system of realistic 3D scenes. Generally, the demand for high realism causes slow rendering, and the demand for high rendering speed leads to low realism. The human visual system is the ultimate consumer of most imagery produced by realistic 3D scene rendering. In fact, it is unnecessary to render the visual details of 3D scenes that cannot be perceived by the human visual system. The rendering of 3D scenes can be accelerated by removing the unnecessary operations that only contribute to producing the imperceptible visual details, and meanwhile the visually perceived realism of the 3D scenes does not deteriorate. In this speech, firstly the theory of human visual perception will be briefly introduced; then the approaches to removing the unnecessary redundant computation in 3D scene rendering will be delivered; finally, the experimental results obtained by the speaker’s group will be presented and discussed. 

Shenyang Aerospace University, China

Bio: Liang Zhao, Professor, Executive Deputy Dean of the School of Computer Science, Shenyang Aerospace University. CCF Senior Member. Selected as one of the top 2% Global Scientists at Stanford University in 2022 and a Invitational Fellow of the Japan Society for the Promotion of Academic Progress (JSPS). He published over 150 academic papers (40 first authored and 42 in correspondence), including 28 papers (26 first authored/correspondence) from the Chinese Academy of Sciences Tier-1, 14 CCF-A papers, 47 IEEE journal papers, 5 ESI hot/highly cited papers, and won the International Conference Best Paper Award 5 times. Undertake national and provincial key research and development projects. Served as the General/Program Co-Chair for international conferences/programs such as IEEE TrustCom 2021 and IEEE IUCC 2019/2020, and served as the editor of JSCS and IEEE TNSE. He received more than 10 awards, including the Digital Expo, Provincial Science and Technology Progress Award, and IEEE Outstanding Leadership Award. Participate in standardization work such as IEEE Future Network and IMT-2020 (5G).

Report Title: Intelligence-Enabled Vehicular Networking and Edge Computing

Abstract: Vehicular networking and edge computing (VMC) has been studied profoundly aiming to provide the efficient connectivity among vehicles and infrastructures to access to various of applications in which such networks can support all types of services in the internet of vehicles (IoV). Over the past two decades, VANET (vehicular ad-hoc network) has been studied to connect the vehicles in wide areas with its multi-hop connectivity. However, traditional VANET still faces challenges to enable intelligent networking and communication with its decentralized nature in which individual vehicle lacks the ability to collect and compute such large amount of data. Hence, learning algorithms and dedicated networking architecture should be applied to improve the networking quality. In this talk, the speaker will present the AI-enabled vehicular networking techniques and the related architectures. Further, this talk will also provide comprehensive introduction of vehicular networking, edge computing, in terms of softwarized networking, intelligent caching and offloading.