FMVIP 2022 Nov. 18-20, 2022 | Chengdu, China

Prof. Geoffrey Ye Li

(Keynote Speaker)

Imperial College London, UK

Speech Title: From Conventional to Semantic Communications based on Deep Learning

Abstract: To transmit text messages, speeches, or pictures, we usually convert them into a symbol sequence and transmit the symbols in a conventional communication system, which is designed based on the block structure with coding, decoding, modulation, demodulation, etc. It has been demonstrated recently that deep learning (DL) has great potentials to break the bottleneck of the block-based communication system. In this talk, we first provide our recent endeavors in developing end-to-end (E2E) communications, which combine all blocks at the transmitter by a neural network and those at the receiver by another neural network. Even if deep learning based E2E communication systems have a potential to outperform the conventional block-based communication systems in terms of performance and complexity, their spectrum efficiency is still limited by Shannon capacity since they essentially transmit bits or symbols. Semantic communication systems transmit and recover the desired meaning of the transmitted content (for example, a text message or a picture) directly and can significantly improve transmission efficiency. We will present our initial results on semantic communications.

Biography: Geoffrey Ye Li has been a Chair Professor at Imperial College London since 2020.  Before moving to Imperial, he was with Georgia Institute of Technology as a Professor for 20 years and with AT&T Labs - Research in New Jersey, USA, as a Principal Technical Staff Member for five years. His general research interests include statistical signal processing and machine learning for wireless communications. In these areas, he has published over 600 referred journal and conference papers in addition to over 40 granted patents. His publications have been cited over 54,000 times with H-index of over 110 and he has been listed as the World’s Most Influential Scientific Mind, also known as a Highly-Cited Researcher, by Thomson Reuters almost every year since 2001. He has been an IEEE Fellow since 2006 and an IET Fellow since 2021. He received several prestigious awards from IEEE ComSoc, IEEE VTS, and IEEE SPS, including 2019 IEEE ComSoc Edwin Howard Armstrong Achievement Award.<Personal Webpage>

Prof. Shahram Latifi

(Keynote Speaker)

University of Nevada, Las Vegas, USA

Speech Title: Facial Recognition- The most error-prone, yet enduring modern biometrics trait?
Abstract: In recent years, there has been much progress in the area of Facial Recognition (FR) that address the shortcomings in conventional FR systems. Spoofing using a high resolution image, high false negative rates due to partial occlusion of the face (ex. mask), and high positive rates due to similarity of subjects are among such shortcomings. Aided by advancements in AI and image acquisition technology (i.e. high resolution 2D/3D) cameras, researchers have been able to push the quality of the facial recognition systems to an impressive new level. Despite the progress, there are still challenging issues lingering around ranging from technology matters (ex. real-time standoff detection) to policy concerns (ex. privacy and ethics). In this talk, I will address the progress in facial recognition and present the state of the art technologies developed by the world software giants such as Google, Facebook, Microsoft and Baidu in FR. Amid the growing concerns about misuse of FR by governments and other public entities, companies have started to move away from broad identification toward more restrictive forms of personal identification. At the end, I will focus on the trade-offs of restrictive FR and the need for including control, privacy and transparency in future systems.

Biography: Shahram Latifi, an IEEE Fellow, received the Master of Science and the PhD degrees both in Electrical and Computer Engineering from Louisiana State University, Baton Rouge, in 1986 and 1989, respectively. He is currently a Professor of Electrical Engineering at the University of Nevada, Las Vegas. Dr. Latifi is the co-director of the Center for Information Technology and Algorithms (CITA) at UNLV. He has designed and taught undergraduate and graduate courses in the broad spectrum of Computer Science and Engineering in the past four decades. He has given keynotes and seminars on machine learning/AI and IT-related topics all over the world. He has authored over 250 technical articles in the areas of networking, cybersecurity, image processing, biosurveillance, biometrics, document analysis, fault tolerant computing, parallel processing, and data compression. His research has been funded by NSF, NASA, DOE, DoD, Boeing, Lockheed and Cray Inc. Dr. Latifi was an Associate Editor of the IEEE Transactions on Computers (1999-2006), an IEEE Distinguished Speaker (1997-2000), and Co-founder and General Chair of the IEEE Int'l Conf. on Information Technology (2004-2015). Dr. Latifi is the recipient of several research awards, the most recent being the Barrick Distinguished Research Award (2021). Dr. Latifi was recognized to be among the top 2% researchers around the world in December 2020, according to Stanford top 2% list (publication data in Scopus, Mendeley). He is a Registered Professional Engineer in the State of Nevada.

Prof. Xinguo Yu

(Keynote Speaker)

IEEE and ACM Senior Member

Central China Normal University, China

Speech Title: Principles and Benchmarks of Object Detection/Recognition and Tracking
Abstract: Object detection/recognition and tracking is an intensively research topic and will be hot for many more years. It is a valuable to identify the principles and benchmarks of object detection/recognition and tracking for different scenarios. The analysis will also discloses the underlying logics of these principles and benchmarks.

Biography: Dr. Yu Xinguo is the dean of CCNU Wollongong Joint Institute and a professor of National Engineering Research Center for E-Learning at Central China Normal University, Wuhan, China. He is a senior member of both IEEE and ACM, and an adjunct professor of University of Wollongong, Australia. He is a vice director of Smart Educational Technology Branch Society under Automation Society in China, and the chair of Hubei Society of Artificial Intelligence in Research and Education. He received B.Sc. degree in Mathematics from Wuhan University of Technology, M. Eng degree from Huazhong University of Science and Technology, another M. Eng. degree from Nanyang Technological University, Singapore and Ph.D. degree in Computer Science from National University of Singapore. His current research mainly focuses on intelligent educational technology, educational robotics, multimedia analysis, computer vision, and machine learning. He has published over 150 research papers and his research papers have been widely cited by experts at home and abroad. He is Associate Editor and Guest Editors for several international journals. He was general chairs or program chairs for more than 20 international conferences.  <personal webpage>

Prof. Peter Han Joo Chong

(Keynote Speaker)

Auckland University of Technology, New Zealand

Speech Title: A Novel AI-enabled Video Background Marketing Technology for Influencers/KOLs
Abstract: The massive amount of social media consumption makes KOL (Key opinion leader)/Influencer/Wanghong marketing becomes very effective. Because they have power to influence and motivate the viewers to purchase a brand’s product, improve brand visibility, and ultimately boost sales. In this talk, we will introduce our computer vision-based product placement technology to make the KOL video background marketing more viable and flexible. The idea is to embed the advertisement (AD) seamlessly and smoothly pasting into the KOLs’ videos. One major obstacle for AD embedding on the KOL’s videos is human occlusion. Our technology first embeds an AD to a video automatically and then we use a deep learning model to solve the occlusion problem. The image matting-based deep learning model is develop for human segmentation. After that, we put an AD photo to replace a picture on the KOL’s video. Since the AD photo occludes the KOL’s body on the video, we then use the segmentation result from the deep learning model to paste the KOL body’s pixels back to the video. As a result, the AD photo is occluded by the KOL’s body naturally.

Biography: Professor Peter Han Joo Chong is currently an Associate Head of School (Research), School of Engineering, Computer and Mathematical Sciences, at Auckland University of Technology, New Zealand. He received the Ph.D. degree from the University of British Columbia, Canada, in 2000. He is an Adjunct Professor at the Department of Information Engineering, Chinese University of Hong Kong, Hong Kong. He was previously an Associate Professor (tenured) in the School of Electrical and Electronic Engineering at Nanyang Technological University, Singapore. Between 2013 and 2016, he was a Director of Infinitus, Centre for Infocomm Technology, at NTU. From February 2001 to May 2002, he was a Research Engineer at Nokia Research Center, Finland. Between July 2000 and January 2001, he worked in the Advanced Networks Division at Agilent Technologies Canada Inc., Canada. His research interests are in the areas of mobile communications systems including MANETs/VANETs, V2X, Internet of Things/Vehicles, artificial intelligence for wireless networks, and 5G networks. He has published over 300 research articles. He is a co-founder of a AI technology company, Zyetric, the world-first AI KOL Video Advertising Hub, based in Hong Kong and New Zealand. He is a Fellow of The Institution of Engineering and Technology (FIET). <Personal Webpage>

Prof. Songtao Guo

(Keynote Speaker)

Senior member of IEEE/ACM

Chongqing Univerity, China

Speech Title: Intelligent Mobile Edge Computing for On-Demand Deep Learning
Abstract: As the backbone technology of machine learning, deep neural networks (DNNs) have quickly ascended to the spotlight. Running DNNs on resource-constrained mobile devices is, however, by no means trivial, since it incurs high performance and energy overhead. While offloading DNNs to the cloud for execution suffers unpredictable performance, due to the uncontrolled long wide-area network latency. To address these challenges, in this paper, we propose a collaborative and on-demand DNN framework with device-edge synergy. The framework pursues two design knobs: (1) DNN partitioning that adaptively partitions DNN computation between device and edge, in order to leverage hybrid computation resources in proximity for real-time DNN inference. (2) DNN rightsizing that accelerates DNN inference through early-exit at a proper intermediate DNN layer to further reduce the computation latency.

Biography: Songtao Guo received his B.S., M.S. and Ph.D. degrees in Computer Software and Theory from Chongqing University, Chongqing, China, in 1999, 2003 and 2008, respectively. He was a professor from 2011 to 2012 at Chongqing University and a professor from 2013 to 2018 at Southwest University. At present, he is a full professor at Chongqing University, China. He was a senior research associate at the City University of Hong Kong from 2010 to 2011, and a visiting scholar at Stony Brook University, New York, USA, from May 2011 to May 2012. His research interests include mobile edge computing, wireless sensor networks, wireless ad hoc networks and parallel and distributed computing. He has published more than 100 scientific papers in leading refereed journals such as IEEE Transactions on Computers、IEEE Transactions on Mobile Computing、IEEE Transactions on Communications, etc, and top conferences such as IEEE INFOCOM、IEEE MASS、IEEE SECON、 IEEE WCNC、IEEE GLOBECOM, IEEE ICC, etc. He has received 20 research grants as a Principal Investigator from the National Science Foundation of China and Chongqing and the Postdoctoral Science Foundation of China. He is an ACM senior member and IEEE Senior Member. He is also a New Century Excellent Tenant of Education Ministry of China.<Personal Webpage>

Prof. Jimmy Liu

(Keynote Speaker)

IEEE Member

Southern University of Science and
Technology, China

Speech Title: Intelligent Ocular Image Process – Research Update of iMED Team
Abstract:  Jimmy will talk about the modalities, methods, algorithms of the ocular imaging research. He will also highlight the iMED team （www.imed-lab.com）latest research progress in the past one year in ocular image enhancement, retinal blood vessel reconstruction, AS-OCT glaucoma screening,  search-based ocular disease diagnosis, corneal endothelial cell detection, etc.

Biography: Jimmy Liu graduated from the Department of Computer Science of the University of Science and Technology of China in 1988. He further obtained his master and doctoral degrees in Computer Science from the National University of Singapore. In 2004, he started and grew the Intelligent Medical Imaging Research Team (iMED Singapore), focusing on ocular Artificial Intelligence research. Jimmy was the chairman of the IEEE Singapore Biomedical Engineering Society in Singapore before moving to China. In March 2016, Jimmy moved to China and became the founding institute director of the Cixi Institute of Biomedical Engineering (CIBE) under the Chinese Academy of Sciences (CAS). He further founded the iMED China Ningbo team in CIBE focusing on ocular image AI research. In February 2019, he joined the Department of Computer Science and Engineering of the Southern University of Science and Technology and established iMED China Shenzhen continue to focus on ocular AI image AI research. Right now, iMED China team are devoting themselves to eye-brain imaging, ocular imaging, ocular precision medicine, and ocular surgical robotics 4 research areas.

Dr. Zhao Yue

(Keynote Speaker)

IEEE Member

Southwest Communication
Research Institute, China

Speech Title: An Information Security Management and Control Scheme for Smart Industrial Parks
Abstract: Focusing on the basic concept of smart industrial parks and the information security risks of existing schemes, we introduce a sensitive information security sharing (SISS) platform by adopting cryptography and information security technology to enable the smart industrial parks, provide technical aspects such as unified authority control scheme, sensitive data security sharing, and intelligent gateway based on edge computing for smart industrial parks, establish a new security management and control system of smart industrial parks. Finally, we introduce the research achievements of the information security management and control technology used in smart industrial parks, as well as the application value of SISS security platform in other industry fields.

Biography: Zhao Yue is a senior engineer and Ph.D. of Southwest Communication Research Institute. He has presided over more than ten projects such as National Natural Science Foundation Projects, Key Technology R&D Programs of Sichuan Province, and participated in National Key Technology R&D Program as the person in charge of special topics. As the first author or corresponding author, he has more than 20 academic papers published on IEEE Transactions on Mobile Computing, IEEE/ACM Transactions on Knowledge and Data Engineering, and other top network and communication academic journals and conferences, 34 patents authorized and 4 software copyrights registered. In addition, he published 4 academic monographs. He is now a master supervisor of Shanghai Jiaotong University, Sichuan University, University of Electronic Science and Technology of China, and an associate editor or guest associate editor of Wireless Communications and Mobile Computing、KSII Transactions on Internet and Information Systems、Journal of Smart City Application.