• Keynote Speakers 主讲嘉宾 (ICIGP 2021)


    Prof. Wan-Chi Siu
    IEEE Life Fellow & IET Fellow

    Hong Kong Polytechnic University, Hong Kong, China

    Wan-Chi Siu (S’77-M’77-SM’90-F’12-Life-F’16) received the MPhil and PhD degrees from The Chinese University of Hong Kong in 1977 and Imperial College London in 1984. He is Life-Fellow of IEEE and Fellow of IET, and Immediate-Past President (2019-2020) of APSIPA (Asia-Pacific Signal and Information Processing Association). Prof. Siu is now Emeritus Professor, and was Chair Professor, Founding Director of Signal Processing Research Centre, Head of Electronic and Information Engineering Department and Dean of Engineering Faculty of The Hong Kong Polytechnic University. He is an expert in DSP, transforms, fast algorithms, machine learning, and conventional and deep learning approaches for super-resolution imaging, 2D and 3D video coding, object recognition and tracking. He has published 500 research papers (over 200 appeared in international journal papers), and edited three books. He has also 9 recent patents granted. Prof. Siu was an independent non-executive director (2000-2015) of a publicly-listed video surveillance company and convenor of the First Engineering/IT Panel of the RAE(1992/93) in Hong Kong. He is an outstanding scholar, with many awards, including the Best Teacher Award, the Best Faculty Researcher Award (twice) and IEEE Third Millennium Medal (2000). Prof. Siu has been Guest Editor/Subject Editor/AE for IEEE Transactions on Circuits and System II, Image Processing, Circuit & System for Video Technology, and Electronics Letters, and organized very successfully over 20 international conferences including IEEE society-sponsored flagship conferences, such as TPC Chair of ISCAS1997 and General Chair of ICASSP2003 and General Chair of ICIP2010. He was Vice-President, Chair of Conference Board and Core Member of Board of Governors (2012-2014) of the IEEE Signal Processing Society, and has been a member of the IEEE Educational Activities Board, IEEE Fourier Award for Signal Processing Committee (2017-2020) and some other IEEE Technical Committees.

    Speech Title: Deep Learning Baseline Model Design for Image Enlightening and Super-Resolution
    Abstract: There are always large demands for more suitable and efficient machine learning techniques for hi-tech applications. In this talk we will start with a brief review of the architecture of a standard deep learning network for classification and image manipulation applications. Many possible approaches can possibly be used to achieve improvement of the architecture of the deep learning structure, which include making novel improvement on the design of the baseline model, information aggregation, resolving the conflict between optimization and generalization and normalization approach of deep learning algorithms. For the present presentation, we will just concentrate on the study of baseline models for deep learning, and will give a brief discussion on the evolution of building blocks for deep learning architectures. We will then proceed with the discussion of our proposed baseline models making use of joint back projection and residual network. Network design for applications in super-resolution imaging and image enlightening will be discussed. The techniques can be used as a reference for those who want to design their own deep learning networks for specific applications. Demonstrations and experimental results will be provided to show the effect of the new design. At the end of the talk we will also discuss briefly other possible ways for architectural improvement, and research trend along this direction.

    Prof. Weisi Lin
    IEEE Fellow & IET Fellow

    Nanyang Technological University, Singapore

    Dr. Weisi Lin is an active researcher in image processing, perception-based signal modelling and assessment, video compression, and multimedia communication systems. In the said areas, he has published 180+ international journal papers and 230+ international conference papers, 7 patents, 9 book chapters, 2 authored books and 3 edited books, as well as excellent track record in leading and delivering more than 10 major funded projects (with over S$7m research funding). He earned his BSc and MSc from Sun Yat-Sen University, China, and Ph.D from King’s College, University of London. He had been the Lab Head, Visual Processing, Institute for Infocomm Research (I2R). He is a Professor in School of Computer Science and Engineering, Nanyang Technological University, where he also serves as the Associate Chair (Research).
    He is a Fellow of IEEE and IET, and an Honorary Fellow of Singapore Institute of Engineering Technologists. He has been awarded Highly Cited Researcher 2019 by Web of Science, and elected as a Distinguished Lecturer in both IEEE Circuits and Systems Society (2016-17) and Asia-Pacific Signal and Information Processing Association (2012-13), and given keynote/invited/tutorial/panel talks to 20+ international conferences during the past 10 years. He has been an Associate Editor for IEEE Trans. on Image Processing, IEEE Trans. on Circuits and Systems for Video Technology, IEEE Trans. on Multimedia, IEEE Signal Processing Letters, Quality and User Experience, and Journal of Visual Communication and Image Representation. He was also the Guest Editor for 7 special issues in international journals, and chaired the IEEE MMTC QoE Interest Group (2012-2014); he has been a Technical Program Chair for IEEE Int’l Conf. Multimedia and Expo (ICME 2013), International Workshop on Quality of Multimedia Experience (QoMEX 2014), International Packet Video Workshop (PV 2015), Pacific-Rim Conf. on Multimedia (PCM 2012) and IEEE Visual Communications and Image Processing (VCIP 2017). He believes that good theory is practical, and has delivered 10+ major systems and modules for industrial deployment with the technology developed.

    Speech Title: From Video Coding to Visual Feature Coding: toward Collaborative Intelligence & Beyond
    Abstract: Great success has been achieved in image and video coding during the past 3 decades thanks to joint effort of academia and industries, resulting in countless products and services. The ubiquity of images and videos enabled by the coding technology no doubt has significantly contributed to the huge impact leading to the award of 2009 Nobel Prize in Physics to the CCD camera inventors.

    It is expected the further exploration in this area to be along 2 major directions: with humans and machines as the ultimate users, respectively. Firstly in this talk, several new paradigms are to be explored to compress whole visual signals, along the 1st direction since the human being continues to use more and more images and videos. After 30+ years’ intensive development and optimization, the room for further improvement is diminishing with the existing hybrid coding framework; we will discuss some out-of-the-box approaches, including synthetic frame formation, alternative transforms, just-noticeable-difference guided coding, fine-grained quality evaluation, and so on.

    The second part of this talk is devoted to the aforementioned 2nd direction, since machines increasingly become the ultimate users for visual signals in the AI era. We explore for intermediate deep-learnt visual features (rather than whole image/video) to be coded in response to the challenges of collaborative intelligence (CI) between edge and cloud/clients, and facilitate integration of signal compression and machine vision (being separate tasks traditionally), accurate feature extraction, privacy preservation, flexible load distribution and power/battery reduction. It is hoped that the presentation can trigger more R&D in the related fields, inclusive of collaborative human and artificial intelligence.

    Prof. Ce Zhu
    IEEE Fellow

    University of Electronic Science and Technology of China, China

    Ce Zhu is currently a Professor with the School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China. His research interests include image/video coding and communications, 3D video, visual analysis and understanding, visual perception and applications. He has served on the editorial boards of a few journals, including as an Associate Editor of IEEE Transactions on Image Processing, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Broadcasting, IEEE Signal Processing Letters, and IEEE Communications Surveys and Tutorials. He has also served as a Guest Editor of a few special issues in international journals, including as a Guest Editor in the IEEE Journal of Selected Topics in Signal Processing. He is a Fellow of the IEEE, and an IEEE CASS Distinguished Lecturer (2019-2020).

    Speech Title: Substitute Training for Adversarial Attacks - Is Real Training Data Really Necessary?
    Abstract: Recent study shows machine learning models are extremely vulnerable to adversarial attacks. Substitute attacks, typically black-box ones, employ pre-trained models to generate adversarial examples. It is generally accepted that substitute attacks need to acquire a large amount of real training data combined with model-stealing methods to obtain a substitute model. However, the real training data may be difficult (if not impossible) to be obtained for some practical tasks, e.g., in medical or financial sectors. As the first trial study, the talk will present our recently developed data-free model-stealing method for substitute training that does not require any real training data. The experimental results demonstrate that the substitute models produced by the proposed method without any real training data can achieve competitive performance against the baseline models trained by the same training set as in attacked models.

    Prof. Ioannis Pitas
    IEEE Fellow

    Aristotle University of Thessaloniki, Greece

    Prof. Ioannis Pitas (IEEE fellow, IEEE Distinguished Lecturer, EURASIP fellow) received the Diploma and PhD degree in Electrical Engineering, both from the Aristotle University of Thessaloniki (AUTH), Greece. Since 1994, he has been a Professor at the Department of Informatics of AUTH and Director of the Artificial Intelligence and Information Analysis (AIIA) lab. He served as a Visiting Professor at several Universities.

    His current interests are in the areas of computer vision, machine learning, autonomous systems, intelligent digital media, image/video processing, human-centred interfaces, affective computing, 3D imaging and biomedical imaging. He has published over 906 papers, contributed in 47 books in his areas of interest and edited or (co-)authored another 11 books. He has also been member of the program committee of many scientific conferences and workshops. In the past he served as Associate Editor or co-Editor of 9 international journals and General or Technical Chair of 4 international conferences. He participated in 70 R&D projects, primarily funded by the European Union and is/was principal investigator/researcher in 42 such projects. He has 31200+ citations to his work and h-index 84+ (Google Scholar).

    Prof. Pitas lead the big European H2020 R&D project MULTIDRONE: https://multidrone.eu/. He is AUTH principal investigator in H2020 R&D projects Aerial Core and AI4Media. He is chair of the Autonomous Systems Initiative https://ieeeasi.signalprocessingsociety.org/. He is head of the EC funded AI doctoral school of Horizon2020 EU funded R&D project AI4Media (1 of the 4 in Europe).

    Speech Title: Generative Adversarial Networks in Multimedia Content Creation
    Abstract: Deep Convolutional Generative Adversarial Networks (DCGAN) have been used to generate highly compelling pictures or videos, such as manipulated facial animations, interior and outdoor images, videos. This lecture provides an extensive overview of several Generative Adversarial Networks applications for media production, notably for image content generation (e.g., human facial and body images), automatic image restyling/translation/captioning, text to image synthesis, video frame prediction, video content generation (e.g., human animations), automatic audio-visual content captioning. If this trend does indeed succeed, it will revolutionize arts and media production.