With Prof. Tsuhan Chen (CMU)

Prof. Tsuhan Chen (from CMU, also graduated from NTU since 1987) gives the first Keynote Speech titled "Unsupervised Discovery of Objects and Object Hierarchy in Video: Content Extraction Made Easy" at MMM 2008. After that, we three members from NTU talk with him.

Finally, we reference the abstract from his talk here:

Based on the bag-of-words representation, statistical models have recently become a popular approach to object discovery, i.e., extracting the "object of interest" from a set of images in a completely unsupervised manner. In this talk, we will outline this approach and extend it from still images to motion videos. We will propose a novel spatial-temporal framework that applies statistical models to both appearance modeling and motion modeling. The spatial and temporal models are integrated so that motion ambiguities can be resolved by appearance, and appearance ambiguities can be resolved by motion. In addition, with statistical modeling we can extract hierarchical relationships among objects, completely driven by data without any manual labeling. This framework finds application in video retrieval (e.g., for YouTube or Google Video) and video surveillance.