2015.1.21 Professor Xiangjian He:Multiple Instance Learning for Visual Categorisation

报告题目:Multiple Instance Learning for Visual Categorisation

报告人: Professor Xiangjian He





Nowadays, huge amounts of visual data, e.g., videos and images, have become widely accessible. Therefore, intelligently categorizing the large and growing collections of data for access convenience has been a central goal for modern computer vision research. In this talk, several newly-developed approaches are presented for visual categorization upon multiple instance learning (MIL) cases. We focus on object categorisation. We propose a novel algorithm, multiple-instance learning with a supervised kernel density estimation (MIL-SKDE). Our algorithm extends the twin technologies, kernel density estimation (SKDE) and mean shift, to their supervised versions in which the labels of data points will affect the mode seeking. We apply MIL-SKDE for object categorization, and our algorithm performs superiorly compared with other state-of-the-art methods. Furthermore, to address the complexity issue of MIL-SKDE, we propose MIL-SS (MIL with speed-up SKDE) to speed up the training process.


Professor Xiangjian He, as a Chief Investigator has received various national Research Grants awarded by Australian Research Council (ARC). He is the Director of Computer Vision and Recognition Laboratory at the University of Technology, Sydney (UTS) and a co-leader of Network Security Research Team of UTS. He is a member of IEEE Signal Processing Society Student Committee, and an IEEE Senior Member. He has been awarded 'Internationally Registered Technology Specialist' by International Technology Institute (ITI). He has been carrying out research mainly in the areas of image processing, network security, pattern recognition and computer vision in the previous years. He is a leading researcher for image processing based on hexagonal structure. His most recent research results have appeared in various high quality journals including highly respected IEEE Transactions journals such as TC, TPDS and TCSVT and Elsevier's journals such as Neurocomputing, FGCS, Signal Processing and Computer Networks. His papers has also appeared in premier international conferences such as CVPR, ECCV and MM. He has played various chair roles in various international conferences including IEEE CIT, IEEE AVSS, ICARCV and ACM MM. Very recently, he has been a general chair of MIWAI2014, MMM2015 and PV2015. He is a guest editor for various international journals such as Signal Processing (Elsevier) and Journal of Computer Networks and Computer Applications (Elsevier), and in the editorial boards of various international journals. He is a Principal Supervisor of postdoctoral research fellows and PhD students. Since 1985, he has been an academic, a visiting professor, an adjunct professor, a postdoctoral researcher or a senior researcher in various well-known universities/institutions including Xiamen University, China, BIT University, China, University of Georgia, USA, Electronic and Telecommunication Research Institute (ETRI) of Korea, University of Aizu, Japan, Hong Kong Polytechnic University, and University of Macau.