Keqiu Li, PhD
Professor

School of Computer Science and Technology
Dalian University of Technology China
No 2, Linggong Road, Dalian 116023, China
Email: keqiu@dlut.edu.cn

Title: Large Scale Multimedia Information Retrieval

Abstract: Due to the limitation of the traditional multimedia information retrieval methods based on keywords and textual metadata, content-based multimedia information retrieval (CBMIR) has drawn a lot of attentions. However, exisitng methods of CBMIR are not efficient to deal with for large scale dataset because of their high computational complexities. In this talk, we focus on how to find the efficient methods of CBMIR for for solving the problem of multimedia information retrieval for large scale dataset. First, we will give a comprehensive review of recent research on CBMIR. Then, we share our work about content-basesd image retrieval which is an important branch of CBMIR. Finally, we include this talk by challenges raised in combining CBMIR and cloud computing.

Professor Keqiu Li's Biography

Keqiu Li is currently a Professor at the School of Computer Science and Technology, Dalian University of Technology, China. He got his bachelor and master degree both from Dalian University of Technology, China in 1994 and 1997, and his doctor degree from Japan Advanced Institute of Science and Technology in 2005. Keqiu Li was a research fellow at the University of Tokyo, Japan from Oct. 2005 to Sep. 2007. Keqiu Li’s research interests maily focus on data center networks, cloud computing, multimedia application, wireless network. Keqiu Li has published more than 100 technical papers in international journals and conferences, such as IEEE TPDS, IEEE TKDE, ACM TOIT, and ACM TOMCCAP. He is on the committee board for several international/national journals including IEEE TPDS and serves as organization chair/program chair/publication chair/program committee member for a couple of international conferences.

Bo Yang, PhD
Professor

Dept of Computer Science & Technology, Jilin University

Title: on the Spectral Characterization and Scalable Mining of Network Communities

Abstract: A wide variety of applications can be formulated for the detection of communities from networks, ranging from social and biological network analysis to web mining and searching. This talk will explore the notion of network communities and their properties based on the dynamics of a stochastic model naturally introduced, and the relationship between the hierarchical community structure of a network and the local mixing properties of the stochastic model, which has been established with the large-deviation theory. Topological information regarding the community structures hidden in networks can be inferred from their spectral signatures. Based on the above-mentioned relationship, a general framework is introduced to characterise, analyse, and mine network communities. Utilizing the two basic properties of metastability, i.e. being locally uniform and temporarily fixed, an efficient implementation of the framework, called the LM algorithm, is introduced. This algorithm can scalably mine communities hidden in large-scale networks.

Short Bio:

Bo Yang is currently a Professor in the College of Computer Science and Technology, Jilin University, China. He received his B.Sc., M.S. and Ph.D. degrees in Computer Science from Jilin University in 1997, 2000, and 2003, respectively. Prof. Yang was a visiting research fellow of Computer Science Department at Hong Kong Baptist University from 2005 to 2006 and at Warwick University from 2006 to 2007, respectively. Prof. Yang has published over 40 international journal articles and conference papers. His current research interests are in the areas of data mining, complex/social network analysis, self-organized and self-adaptive multi-agent systems, knowledge engineering, with applications to Web Intelligence (WI) and Social Computing.