Harvesting Heterogenous and Redundant Multimedia Data¶
Heng Tao Shen
Professor
University of Queensland
Abstract: In the era of big data, the amount of multimedia data has reached an unprecedented level and keeps growing exponentially. It has been shown that heterogenous multimedia data gathered from different sources in different media types can be often correlated and linked to the same knowledge. In this talk, we will discuss the phenomena of heterogeneity and redundancy of big multimedia data, followed by the emerging opportunities in related research communities. In particular, I will introduce some recent progress in several promising directions, including automatic media tagging, near-duplicate utilization, and scalable indexing methods to manage Web-scale multimedia data.
Bio: Heng Tao Shen is a Professor of Computer Science in the School of Information Technology & Electrical Engineering at the University of Queensland. He obtained his BSc with 1st class Honours and PhD from Department of Computer Science at National University of Singapore in 2000 and 2004 respectively. He then joined the University of Queensland as a Lecturer and became a Professor in 2011. His research interests mainly include multimedia content analysis/understanding/search, and big data management on spatial/temporal/multimedia databases. Heng Tao has extensively published and served on program committees in most prestigious international forums of multimedia and database areas. He received the Chris Wallace Award for outstanding Research Contribution in 2010 and was awarded the Future Fellowship by Australia Research Council in 2012. He is also recognised by the National "Thousand Talent Program" with the University of Electronic Science and Technology of China. He is currently an Associate Editor of IEEE Transactions of Knowledge and Data Engineering and a PC Co-Chair for ACM Multimedia 2015.