时间：3月22日 下午3：30—5：30

地点：研究所106会议室

Title: Towards Web-Scale Content-Aware Image Search

Abstract: In recent years, remarkable progress has been made towards large-scale content-aware image search. However, there is still a long way to go to bridge the two “gaps”: semantic gap and intent gap. Large-scale data brings us both challenges and opportunities to tackle these difficulties. In this talk, we will review existing image search schemes and then focus on large-scale content-aware image search. We will discuss the connections and differences among different large-scale CBIR techniques such as partition tree, clustering, hashing, graph and inverted index, and then introduce a few exemplary scalable approaches including graph based search, color map based search, and concept map based search. For each exemplary approach, we will discuss how to make it work for billions of images. The limitations will then be analyzed for these techniques, followed by introducing indexing and searching schemes based on web-scale image content understanding. Connections between search and content understanding will be also discussed. And last we will talk about challenges and opportunities along this direction.

Bio: Dr Xian-Sheng Hua became a researcher in Microsoft Research Redmond in 2013, working on Web-scale image and video understanding and search, as well as related applications. Before that, he was a Principal Research and Development Lead in Multimedia Search for the Microsoft search engine, Bing, since 2011. He led a team that designed and delivered leading-edge media understanding, indexing and searching features. He joined Microsoft Research Asia in 2001 as a researcher. Since then, his research interests have been in the areas of multimedia search, advertising, understanding, and mining, as well as pattern recognition and machine learning. He has authored or co-authored more than 200 research papers in these areas and has filed more than 90 patents. Dr Hua received his BS in 1996 and PhD in applied mathematics in 2001 from Peking University, Beijing. He served or is now serving as an associate editor of IEEE Transactions on Multimedia, an associate editor of ACM Transactions on Intelligent Systems and Technology, an editorial board member of Advances in Multimedia and Multimedia Tools and Applications, and an editor of Scholarpedia (multimedia category). He was vice program chair; workshop organizer; senior TPC member and area chair; and demonstration, tutorial, and special session chairs and PC member of many more international conferences. He served or is serving as a program co-chair for IEEE ICME 2013, ACM Multimedia 2012, and IEEE ICME 2012, as well as on the Technical Directions Board of IEEE Signal Processing Society. He was honored as one of the recipients of the prestigious 2008 MIT Technology Review TR35 Young Innovator Award for his outstanding contributions to video search. He won the Best Paper and Best Demonstration Awards at ACM Multimedia 2007, the Best Poster Award at IEEE International Workshop on Multimedia Signal Processing 2008, the Best Student Paper Award at ACM Conference on Information and Knowledge Management 2009, and the Best Paper Award at International Conference on MultiMedia Modeling 2010. He was named one of Global Entrepreneur’s “Business Elites of People under 40 to Watch'' in 2009.