Prof. Henry Leung, IEEE Fellow, SPIE Fellow, University of Calgary, Canada
Bio: Henry Leung is a Schulich Industry Research Chair Professor of the Department of Electrical and Software Engineering at the University of Calgary, Canada. His current research interests include data analytic, information fusion, machine learning, signal and image processing, robotics, and internet of things. He has published over 350 journal papers and 250 refereed conference papers. Dr. Leung has been the associate editor of various journals such as the IEEE Circuits and Systems Magazine, International Journal on Information Fusion, IEEE Trans. Aerospace and Electronic Systems, IEEE Signal Processing Letters, IEEE Trans. Circuits and Systems, Scientific Reports He has also served as guest editors for the special issue “Intelligent Transportation Systems” for the International Journal on Information Fusion and “Cognitive Sensor Networks” for the IEEE Sensor Journal. He is the editor of the Springer book series on “Information Fusion and Data Science”. He is a Fellow of IEEE and SPIE.
Speech Title: 3D Computer Vision with Applications to Autonomous Vehicles
Abstract: In this talk we present our works on 3D computer vision based on RGBD sensing. A visual SLAM system on static and dynamic platforms is described that uses motion prior to obtain accurate motion estimation in metric scale to make dynamic features usable for SLAM on dynamic platforms. When depth info is not available, deep learning is used to perform depth prediction and the predicted depth can be used for RGBD SLAM. In this talk, we will also discuss 3D object detection and tracking that can be used for obstacles avoidance, including approaches to enhance object detection in different environments. The proposed RGBD image processing techniques for SLAM, depth prediction, object detection and object tracking are applied to autonomous driving and the performance are evaluated using publicly available benchmark datasets and experimental datasets we collected for practical driving scenarios in real environments including highways, residential, semi-urban and urban roads.
Prof. Weisi Lin, FIEEE, FIET, CEng, Hon. FSIET; Associate Chair(Research), School of Computer Science and Engineering, Nanyang Technological University, Singapore
Bio: Lin Weisi is
an active researcher in intelligent image processing, perception-based
signal modelling and assessment, video compression, and multimedia
communication. He had been the Lab Head, Visual Processing, in Institute for
Infocomm Research (I2R)，Singapore. He is a Professor in School of Computer
Science and Engineering, Nanyang Technological University, where he also
served as the Associate Chair (Research).
He is a Fellow of IEEE and IET, and has been awarded Highly Cited Researcher 2019, 2020, 2021 and 2022 by Clarivate Analytics. He has 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 in 50+ international conferences. He has been an Associate Editor for IEEE Trans. Neural Networks Learn. Syst., IEEE Trans. Image Process., IEEE Trans. Circuits Syst. Video Technol., IEEE Trans. Multim., IEEE Sig. Process. Lett., Quality and User Experience, and J. Visual Commun. Image Represent. He also chaired the IEEE MMTC QoE Interest Group (2012-2014); he has been a TP Chair for IEEE ICME 2013, QoMEX 2014, PV 2015, PCM 2012 and IEEE VCIP 2017, and is a General Co-Chair for IEEE ICME 2025. He believes that good theory is practical, and has delivered 10+ major systems and modules for industrial deployment with the related technology developed.
Speech Title: Modeling Visual Signal Sensitivity for Human Perception, Machine Understanding, and Both
Abstract: Visual signal sensitivity, termed as Just-Noticeable-Difference (JND), refers to the minimum change of an image to be distinguished by the user. This talk firstly discusses how to model various visual signals (images, videos, graphics, and so on) for human users. Since humans have developed unique characteristics in perception over the long evolution, effective JND modeling facilitates optimization of user-centric system performance and utility of available resources (bandwidth, memory, battery, computation, device cost/size, etc). Machines are becoming the ultimate users for a rapidly increasing amount of visual signals in this AI era, and therefore as the second part of the talk, we will investigate into the concept of JND to be extended with machine tasks, including scenarios where both humans and machines are ultimate users. Finally, possible further research directions will be highlighted, inclusive of exploration toward true multimedia that consists of hearing, smell, touch and even taste aspects as well.
Prof. De-Shuang Huang, IEEE Fellow / IAPR Fellow / AAIA Fellow, Director, Biomedical Data Mining and Computing Lab, Eastern Institute of Technology, Ningbo, China
Bio: De-Shuang Huang
is a Professor, Director of Biomedical Data Mining and Computing ab, Eastern
Institute of Technology, Ningbo, China. He is currently the Fellow of the
IEEE (IEEE Fellow), the Fellow of the International Association of Pattern
Recognition (IAPR Fellow), the Fellow of the Asia-Pacific Artificial
Intelligence Association (AAIA), and associated editors of IEEE/ACM
Transactions on Computational Biology & Bioinformatics and IEEE Transactions
on Cognitive and Developmental Systems, etc. He founded the International
Conference on Intelligent Computing (ICIC) in 2005. ICIC has since been
successfully held annually with him serving as General or Steering Committee
Chair. He also served as the 2015 International Joint Conference on Neural
Networks (IJCNN2015) General Chair, July12-17, 2015, Killarney, Ireland, the
2014 11th IEEE Computational Intelligence in Bioinformatics and
Computational Biology Conference (IEEE-CIBCBC) Program Committee Chair, May
21-24, 2014, Honolulu, USA. He has published over 480 papers in
international journals, international conferences proceedings, and book
chapters. Particularly, he has published over 260 SCI indexed papers. His
Google Scholar citation number is 23725 times and H index 80. His main
research interest includes neural networks, pattern recognition and
bioinformatics. His main research interest includes neural networks, pattern
recognition and bioinformatics.
Speech Title: Graph Data Learning and Healthy Aging Prediction
Abstract: Graph Neural
Networks (GNNs) have achieved advanced performance in many fields such
as traffic prediction, recommendation systems, and computer vision.
Recently there are majorities of methods on GNN focusing on graph
convolution, and less work about pooling. To address the problems of
information loss and low feature representation capability during graph
pooling operations. In this report, we explore higher efficient
graph-level representation learning methods and their application to
bioinformatics. Firstly, to address the problem of information loss in
the pooling operation, we propose a hierarchical graph-level
representation learning method with self-adaptive cluster aggregation.
Secondly, to address the fact that all existing graph pooling models
based on mutual information maximization need to construct negative
samples and usually only consider local neighborhood information, we
propose a mutual information graph pooling method based on simple
Siamese network. Finally, we present an application of our proposed
graph-level representation learning method to healthy aging prediction
by using scRNA-seq data.