Visit ShanghaiTech University | 中文
HOME > News and Events > Seminars
Sparse Online Learning of Image Similarity with Application to Image Retrieval
Date: 2017/2/14             Browse: 355
Seminar Topic: Sparse Online Learning of Image Similarity with Application to Image Retrieval

Speaker: Xingyu Gao
Time: Feb. 14, 11:00 a.m. - 12:00 a.m.
Venue:  Room 1A-200, SIST Building

Abstract:
Image similarity search plays a key role in many multimedia applications, where multimedia data (such as images and videos) are usually represented in high-dimensional feature space. In this paper, we propose a novel scheme for learning sparse distance functions from large-scale high-dimensional data and explore its application to image retrieval. In contrast to many existing learning algorithms that are often designed for low-dimensional data, the proposed algorithms are able to learn sparse distance metrics from high-dimensional data in an efficient and scalable manner. Our experimental results show that the proposed method achieves better or at least comparable accuracy performance than the state-of-the-art approaches, but enjoys a significant advantage in computational efficiency and sparsity, making it more practical for real-world applications.

Biography:

Xingyu Gao, Assistant Professor with Institute of Software, Chinese Academy of Sciences. He received Ph.D. from Institute of Computing Technology, Chinese Academy of Sciences, and he was Ph.D. student of School of Computer Engineering, Nanyang Technological University. His research interests include machine learning, multimedia information retrieval, and ubiquitous computing.

Seminar 17001