Semantic Context Learning and Representation For Image Categorization and Annotation
Professor Horace H.S. Ip
Department of Computer Science
City University of Hong Kong
Semantic context of images play a key role in effective and robust categorization, annotation and searching of images. With the rapid growth of image archives and the existence of semantic gap, previous content-based approaches is no longer adequate, and techniques for bridging the semantic gap has been an area of intensive research over the past decade. This talk begins with an overview of content-based approaches to image characterization and their limitations, followed by a presentation of our recent work on automatic learning of semantic context from images as well as techniques for comparing semantic contexts among large scale image collections. The talk concludes with an incorporation of the learnt semantic context within the frameworks of Relevance Model and Semi-supervised
learning respectively to improve upon the state of the art performance in image categorization and annotation.
Professor. Horace H. S. Ip is a Chair Professor of Computer Science and the founding director of the AIMtech Centre (Centre for Innovative Applications of Internet and Multimedia Technologies) at City University of Hong Kong. He
received his B.Sc. degree in Applied Physics and Ph.D. degree in Image Processing from University College London, United Kingdom. His research interests include pattern recognition, multimedia content analysis and retrieval, virtual reality and technologies for education. Professor Ip’s research has won many awards including Prix Ars Electronica, and a Gold Medal of the Geneva Salon International Des Inventions. Prof. Ip had served on the editorial board of many international journals including the IEEE Transactions on Multimedia, and Pattern Recognition, and was an Area Editor of the Pattern Recognition Letter journal. He has published over 200 papers in international journals and conference proceedings. Prof. Ip is a Fellow of the Hong Kong Institution of Engineers (HKIE) and a Fellow of the UK Institution of Engineering and Technology (IET), a Fellow of the British Computer Society (FBCS) and a Fellow of the International Association for Pattern Recognition (IAPR).