We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probab...
This paper overviews our research on digital preservation of cultural assets and digital restoration of their original appearance. Geometric models are digitally achieved through ...
Copyright 2004 IEEE. Published in Conference on Computer Vision and Pattern Recognition (CVPR-2004), June 27 - July 2, 2004, Washington DC. Personal use of this material is permit...
We introduce a new approach, called Relative Start and Idle Time (RSIT), to solve probabilistic scheduling problems of construction repetitive projects. RSIT is a process of deter...
Chachrist Srisuwanrat, Photios G. Ioannou, Omer Ts...
In this paper, we introduce a first-order probabilistic model that combines multiple cues to classify human activities from video data accurately and robustly. Our system works in...