We address the problem of classifying scenes from feature films into semantic categories and propose a robust framework for this problem. We propose that the Finite State Machines ...
Blob trackers have become increasingly powerful in recent years largely due to the adoption of statistical appearance models which allow effective background subtraction and robus...
Face detection methods based on a cascade architecture have demonstrated fast and robust performance. Cascade learning is aided by the modularity of the architecture in which node...
In this paper, we propose a robust and efficient Lagrangian approach for modeling dynamic interfaces between different materials undergoing large deformations and topology change...
Face-to-face meetings usually encompass several modalities including speech, gesture, handwriting, and person identification. Recognition and integration of each of these modaliti...
Michael Bett, Ralph Gross, Hua Yu, Xiaojin Zhu, Yu...