CIS Colloquium, Mar 14, 2012, 11:00AM - 12:00PM, Wachman 447
Multiple Instance Learning for Human Centered Visual Computing
Gang Hua, Stevens Institute of Technology
The proliferation of internet and visual sensors have created tremendous amount of online visual media. A significant amount of online user activities are indeed driven by these massive visual media. There is an emerging need for human centered visual computing, where the users are actively engaged in, or are the target of, the analytics of these visual contents. In this talk, we will explore how multiple instance learning could benefit human centered visual computing. We will firstly introduce the theory of multiple instance learning. We then present the details of a multiple instance boosting algorithm, which is an iterative algorithm to induce an additive discriminative classifier. We will present two applications of multiple instance boosting: one on human assisted video object summarization, and the other on part based human detection. Our focus will be on the first application where it clearly reflected how visual features, machine learning, visual context, and user interaction can work synergistically to our analytics goal. In the end of my talk, I will briefly demo some of my other works and hence present some more comprehensive views of my research.
Bio: Gang Hua is an Associate Professor of Computer Science in Stevens Institute of Technology. He also holds an Academic Visiting Researcher position at IBM T. J. Watson Research Center. Before that, he was a Research Staff Member at IBM Research T. J. Watson Center from 2010 to 2011, a Senior Researcher at Nokia Research Center, Hollywood from 2009 to 2010, and a Scientist at Microsoft Live Labs Research from 2006 to 2009. He received the Ph.D. degree in Electrical and Computer Engineering from Northwestern University in 2006. He is an Associate Editor of IEEE Trans. on Image Processing, an Associate Editor of IAPR Journal of Machine Vision and Applications, a Guest Editor of IEEE Trans. on Pattern Analysis and Machine Intelligence, and a Guest Editor of International Journal on Computer Vision. He has also served as Chairs, TPC Members, or Reviewers for a large number of prestigious international conferences. In particular, he is an Area Chair of ICCV’2011, an Area Chair of both ACM Multimedia 2011 and 2012, an Area Chair of ICIP2012, an Area Chair of ICASSP2012, and a Workshops and Proceedings Chair of IEEE Conf. on Face and Gesture Recognition, 2011. He is the author of more than 60 peer reviewed publications in prestigious international journals and conferences. To date, he holds 6 US patent and has 14 more US patents pending. He is a Senior Member of the IEEE and a member of the ACM.