Multi-View Fusion and Representation for Image Analysis

Abstract

Real-world data can be described from multiple views. For instance, an image can be described by color histogram, SIFT, HOG and other features. The content of a Web page can be described by texts, images and videos. Describing an object from multiple perspectives constitutes multi-view data. Multi-view learning is to use the complementary nature of different views to improve the learning performance than using a single view. In this talk, I will first briefly introduce some basic concepts and issues in multi-view learning. Then I will introduce some of our recent multi-view learning works for image analysis including multi-view dimensionality reduction, multi-view clustering and incomplete multi-view classification. This report aims to help the audience understand the basic tasks and latest developments of multi-view learning.

Biography

Dr. Zhe Xue received his Ph,D. degree in Computer Science from school of computer and control engineering, University of Chinese Academy of Sciences (UCAS) in 2017. After that, he became an assistant professor at school of computer science, Beijing University of Posts and Telecommunications. His research interest is generally in machine learning and data mining, and particularly in multi-view learning and image analysis. Dr. Xue has published over 20 papers in international conferences and journals such as AAAI, IJCAI, IEEE TCSVT, CVIU, Information Sciences. He has undertook and participated in many projects, including National Key R&D Program of China, 973 Program, National Natural Science Foundation of China and so on. He is the reviewer of ACM MM, DASFAA, IEEE TIFS, Multimedia Tools and Applications and other international journals and conferences. He is also a member of the Intelligent Service Committee of the Chinese Association for Artificial Intelligence.