University of Technology Sydney（澳大利亚悉尼科技大学）
Yi Yang received the Ph.D. degree in computer science from Zhejiang University in 2010. He is currently an associate professor and deputy head of school (Research) with the School of Software, University of Technology Sydney, Australia. He was a Post-Doctoral Research with the School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA, from 2010 to 2013. His research interest include machine learning and its applications to multimedia content analysis and computer vision, such as multimedia indexing and retrieval, surveillance video analysis and video content understanding. He has published around 100 papers in many well known journals and conferences，including IJCV, ITIP, AAAI, IJCAI, CVPR, etc.
In this seminar,I will talk about our recent work on video and image analysis. I will start with a novel pooling method for robust imaginary sequences representation. Then I will talk about our recent progress in unconstrained video analysis, including Convolution Neural Network (CNN) based efficient video feature extraction, unsupervised visual parser adaptation from video to images, and hierarchy video representation based on the Recurrent Neural Networks. I will then talk about a few applications of surveillance video analysis, ranging from improving security to quality of life.