We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
Triangulation consists in finding a 3D point reprojecting the best as possible onto corresponding image points. It is classical to minimize the reprojection error, which, in the p...
Human activity can be described as a sequence of 3D body postures. The traditional approach to recognition and 3D reconstruction of human activity has been to track motion in 3D, m...
High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured environments is essential for robotics and human motion analysis. However, building a system th...
Kernel-based objective functions optimized using the mean shift algorithm have been demonstrated as an effective means of tracking in video sequences. The resulting algorithms com...
Gregory D. Hager, Maneesh Dewan, Charles V. Stewar...