Lei Wang, University of Wollongong, Australia
Learning SPD-matrix-based Representation for Visual Recognition
During the past several years, covariance matrices have been used as feature representation in multiple visual recognition tasks. This talk will report our recent work on learning and designing covariance and generic symmetric positive definite matrices to achieve better recognition. The first part of this talk presents a method called discriminative Stein kernel. It integrates class label information into the Stein kernel to adjust input covariance matrices to enhance its discriminative capability. The second part explores the sparsity structure among features to compute sparse inverse covariance matrix as representation, achieving better recognition performance in the case of high-dimensional features but small sample. The third part moves beyond covariance matrix to employ kernel matrix as feature representation and jointly learn it in deep learning framework via an end-to-end manner. This not only resolves the high dimensionality and small sample problems, but can also take advantage of the capability of kernel matrix in modelling nonlinear relationship among features. Comprehensive experimental study is conducted on visual classification tasks to demonstrate the efficacy and advantage of the proposed methods over the comparable ones in the literature.
Lei Wang received his PhD degree from Nanyang Technological University, Singapore in 2004. He is now Associate Professor at School of Computing and Information Technology of University of Wollongong, Australia. His research interests include machine learning, pattern recognition, and computer vision. Lei Wang has published 150+ peer-reviewed papers, including those in highly regarded journals and conferences such as IEEE TPAMI, IJCV, CVPR, ICCV and ECCV, etc.. He was awarded the Early Career Researcher Award by Australian Academy of Science and Australian Research Council. He served as the General Co-Chair of DICTA 2014 and on the Technical Program Committees of 20+ international conferences and workshops. Lei Wang is senior member of IEEE.
Thomas Bräunl, The University of Western Australia
Cars: From Zero Emission to Zero Accidents?
This talk covers the three major revolutions currently happening in the Automotive industry: Connected Vehicles, Electric Vehicles, and Autonomous Driving Connected vehicles are already there and electric vehicles are coming to the market in larger numbers. Autonomous vehicles are still part of ongoing research by automotive companies and IT companies alike. This talk will present future trends in the automotive industry together with work that is currently being conducted at UWA's Renewable Energy Vehicle Project (REV).
Thomas Bräunl directs the Renewable Energy Vehicle Project (REV) as well as the Robotics & Automation Lab at The University of Western Australia. He performed several Electric Vehicle conversions, including a Lotus Elise, Hyundai Getz, a Sea-Doo Jet-Ski, and operates one of Western Australia’s largest EV charging networks with 24 AC and DC stations.
He developed two autonomous vehicles based on a BMW X5 and a Formula-SAE-Electric car, linking Lidar and vision sensors. His research concentrates on deep learning methods for autonomous driving and hardware-in-the-loop simulations of autonomous vehicles. Thomas Bräunl has held academic positions at Univ. Stuttgart, TU Munich and Santa Clara Univ., as well as industry positions with Daimler/Mercedes-Benz, BMW Germany, BMW Technology of North America, and served as Technical Director of the West Australian Electric Vehicle Trial.
Speaker (partially Sponsored by IAPR)
Yalin Zheng, University of Liverpool, United Kingdom
Advance Biomedical Imaging Technologies for Blindness
The human eye is the most important organ of sense. It is often said the eye is the window to the soul. Nearly 300 million people are estimated to be visually impaired worldwide of which 40 million are blind. The eye is the only inner organ that can be directly visualised or imaged, imaging technologies are the key for the diagnosis and management of eye diseases. There is also an ever-increasing demand on automated image analysis for precision medicine in eye diseases. I will first give a brief overview of the eye anatomy, imaging technologies and major forms of eye diseases, then present our recent progress in device development, biomedical image analysis and computer-aided diagnosis of eye diseases, and conclude with new challenges and future directions.
Dr Yalin Zheng is a Reader at the University of Liverpool, UK. He has nearly 20 year research experience in image processing, computer vision and medical image analysis in both industry and academia. His research group is focusing on developing new imaging technologies for eye diseases and other healthcare problems. His research is funded by various UK research councils, Department of Health, Welcome Trust and industry. He has over 110 papers published in high impact international journals (e.g. IEEE TMI, Ophthalmology, eLife) and top international conferences (e.g. MICCAI and CVPR). He serves as an Associate Editor of BMJ Open Ophthalmology and Scientific Report and has been a regular keynote speaker at international conferences.