IEEE First Workshop on Emergent Issues in Large Amounts of Visual Data (WS-LAVD) October 4, 2009 in Kyoto, Japan. 14:00-14:50 Recent Advances in Image Representation for Image Segmentation, Object Class Detection and Image Classification Frederic Jurie (University of Caen) [Abstract] Recent advances in computer vision have made possible to obtain challenging results in difficult tasks such as object class detection [1], shape based object recognition [2], image segmentation [3] or image classification [4]. One of the key ingredients of such advances lies in the development of new frameworks for the representation of images, objects and objects classes. During this talk we will introduce several of these recent advances, advances which make possible the automatic processing of large amount of visual data. [References] [1] Combining efficient object localization and image classification H. Harzallah, F. Jurie and C. Schmid, International Conference on Computer Vision (ICCV), 2009. [2] From Images to Shape Models for Object Detection V. Ferrari, F. Jurie, and C. Schmid, International Journal of Computer Vision (IJCV), to appear. [3] Category Level Object Segmentation by Combining Bag-of-Words Models with Dirichlet Processes and Random Fields D. Larlus, J. Verbeek and F. Jurie, International Journal of Computer Vision (IJCV), to appear. [4] Randomized Clustering Forests for Image Classification F. Moosmann, E. Nowak, F. Jurie, IEEE Trans. on Pattern Analysis and Machine Intelligence, Volume: 30, Issue: 9, Sept. 2008 14:50-15:40 Internet Multimedia: Challenges and Opportunties Xian-Sheng Hua (Microsoft Research Asia) [Abstract] With the explosion of video and image data available on the Internet, it becomes more and more important and challenging to enable Internet-scale content-aware multimedia search, management, sharing and other related applications. Moreover, mining semantics and other useful information from large-scale multimedia data to facilitate online and local multimedia content analysis, search, and other applications has also gained more and more attention from both academia and industry. On the one hand, the rapid increase of Internet multimedia data brings us new challenges to multimedia content analysis and multimedia retrieval especially in terms of scalability and semantic gap. On the other hand, large-scale multimedia data also provides us new opportunities to attack these challenges as well as conventional problems in media analysis and computer vision. Recently, more and more researchers are realizing both the challenges and the opportunities for multimedia research brought by the rapid increase of Internet multimedia data, users, as well as the associated metadata, context and social information. This talk will discuss the challenges and opportunities in Internet multimedia research. [Biography] Xian-Sheng HUA received the B.S. and Ph.D. degrees from Peking University, Beijing, China, in 1996 and 2001, respectively, both in applied mathematics. When he was in Peking University, his major research interests were in the areas of image processing and multimedia watermarking. Since 2001, he has been with Microsoft Research Asia, Beijing, where he is currently a Lead Researcher with the media computing group. His current research interests are in the areas of video content analysis, multimedia search, management, authoring, sharing, mining, advertising and mobile multimedia computing. He has authored or co-authored more than 160 publications in these areas and has more than 40 filed patents or pending applications. Dr. HUA is a senior member of the Association for Computing Machinery and IEEE. He is now an adjunct professor of University of Science and Technology of China, and serves as an Associate Editor of IEEE Transactions on Multimedia, Editorial Board Member of Advances in Multimedia and Multimedia Tools and Applications, and editor of Scholarpedia (Multimedia Category). Dr. Hua won the Best Paper Award and Best Demonstration Award in ACM Multimedia 2007, Best Poster Paper Award in 2008 IEEE International Workshop on Multimedia Signal Processing. He also won 2008 MIT Technology Review TR35 Young Innovator Award, and named as one of the ``Business Elites of People under 40 to Watch'' by Global Entrepreneur. More information can be found at http://research.microsoft.com/~xshua |