题目：Unsupervised Image Saliency Detection with Gestalt-laws Guided Optimization and Visual Attention Based Refinement
报告人：Prof. Jinchang Ren, University of Strathclyde, Glasgow, U.K.
摘要：Visual attention is a kind of fundamental cognitive capability that allows human beings to focus on the region of interests (ROIs) under complex natural environments. Within our framework, the model of a bottom-up mechanism is guided by the gestalt-laws of perception. The model of top-down mechanism aims to use a formal computational model to describe the background connectivity of the attention and produce the priority map. Integrating both mechanisms and applying to salient object detection, our results have demonstrated that the proposed method consistently outperforms a number of existing unsupervised approaches on five challenging and complicated datasets in terms of higher precision and recall rates, AP (average precision) and AUC (area under curve) values.
Short Biography: Jinchang Ren is currently a Reader with the Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, UK. He received B. Eng. in Computer Software, M.Eng. in Image Processing and Pattern Recognition and EngD in Computer Vision from Northwestern Polytechnical University (NWPU), China, in 1992, 1997 and 2000, respectively. He was also awarded the PhD degree in Electronic Imaging and Media Communication from the University of Bradford, United Kingdom in 2009. Before he joined Strathclyde in Dec. 2010, he had worked in several universities in U.K. including University of Bradford, University of Surrey, Kingston University and University of Abertay, Dundee.
Dr. Ren has published over 260 peer-reviewed research papers in prestigious international journals and conferences, including over 150 in journals (100+ SCI cited, 20+ with IEEE). He is a Senior Member of IEEE, and Fellow of the Higher Education Academy, U.K. His research interests include: image processing and analysis, intelligent multimedia information processing; visual computing; computer vision; content-based image/video retrieval and understanding; machine learning, big data analytics, visual surveillance; motion estimation; hyperspectral imaging. He sits in the editorial board of six int. journals, including J. The Franklin Institute, IEEE JSTARS, IET Image Processing, Multidimensional Signal Processing and Systems, Int. J. Pattern Recognition and Artificial Intelligence, and Big Data Analytics.