Prof. Huiyu Zhou
Title: Emerging challenges and solutions in data and privacy protection
Dr. Huiyu Zhou received a Bachelor of Engineering degree in Radio Technology from Huazhong University of Science and Technology of China, and a Master of Science degree in Biomedical Engineering from University of Dundee of United Kingdom, respectively. He was awarded a Doctor of Philosophy degree in Computer Vision from Heriot-Watt University, Edinburgh, United Kingdom. Dr. Zhou currently is a full Professor at School of Computing and Mathematical Sciences, University of Leicester, United Kingdom. He has published over 450 peer-reviewed papers in the field. He was the recipient of “CVIU 2012 Most Cited Paper Award“, “MIUA 2020 Best Paper Award”, “ICPRAM 2016 Best Paper Award” and was nominated for “ICPRAM 2017 Best Student Paper Award” and “MBEC 2006 Nightingale Prize“. His research work has been or is being supported by UK EPSRC, ESRC, AHRC, MRC, EU, Royal Society, Leverhulme Trust, Invest NI, Puffin Trust, Alzheimer’s Research UK, Invest NI and industry. Homepage: https://le.ac.uk/people/huiyu-zhou
There are many questions to answer in data and privacy protection. Challenges in data and privacy protection needs strong and powerful modelling tools to describe the problems in practice. Different learning and inference methodologies play a very important role in the design of a robust tool for data and privacy protection. Using some examples from his own work in these areas, Prof. Zhou will explore how mathematical modelling can stimulate new concepts or development of dealing with complicated problems and lead us to novel adventures through these applications.
Keywords: Blockchain, authentication, key, aggregation, trust, signature.
Prof. Jungong Han
Title: Open World Deep Learning for Visual Understanding
Professor Jungong Han is Chair of Computer Vision at the Department of Computer Science, the University of Sheffield, UK. He also holds an Honorary Professorship at the University of Warwick, UK. Previously, he was Chair Professor and Director of Research of the Computer Science department at Aberystwyth University, UK. Prof. Han has authored over 90 papers in IEEE/ACM Transactions and 29 papers in CVPR/ICCV/ECCV/NeurIPS/ICML/ICLR, cited over 14k times with an h-index of 62. Prof. Han has been an Associate Editor-in-Chief of Elsevier Neurocomputing, an Associate Editor of the IEEE Trans. on Neural Networks and Learning Systems, IEEE Trans. on Circuits and Systems for Video Technology, Elsevier Pattern Recognition, and several others. Prof. Han received JVCI Best Editor award in 2022. Prof. Han is a Fellow of IAPR and a Fellow of AAIA.
In the last decade, research for visual understanding has become more prevalent due to the great success of deep learning, especially deep convolutional neural networks (DCNN). By feeding high-quality annotated training data into a fully supervised learning (FSL) engine, DCNN models could even surpass human-level performance in many visual understanding tasks, such as object classification and face recognition. However, conducting FSL in real-world scenarios is challenging due to 1) deep learning technique generates high-dimensional visual features, which make applications like real-time feature matching and large-scale retrieval intractable; 2) there are potentially unlimited object categories in real life such that it is almost impossible to collect enough well-annotated samples for each category; 3) existing DCNN solutions often require a large number of computational resources to run, which are not available on real-life embedded devices. In this talk, I will share with you three projects that I supervised in the past 3 years, where we showcase how we tackled these problems.