澳大利亚卧龙岗大学王雷教授学术报告
　　地点：信息学院赛博南楼412(党员之家)
　　时间：2017年7月6日14：00
　　欢迎广大师生参加！
　　Title: Learning and Designing SPD-matrix-based Representation for Visual Recognition
　　Abstract
　　During the past several years, SPD (symmetric positive definite) matrices have been used as feature representation in multiple visual recognition tasks. This talk will report our recent work on learning and designing SPD 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 develop sparse inverse covariance matrix for SPD-matrix-based representation, achieving better recognition performance in the case of high-dimensional features and small sample. The third part moves beyond covariance matrix and employs SPD kernel matrix as feature representation. 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.
　　Short bio
　　Lei Wang received his PhD degree from Nanyang Technological University, Singapore. 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 120+ 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.He leads the group VILA (Visual Information Learning and Analysis).

信息学院
2017年7月5日