Abstract. We propose a novel tracking algorithm based on the WangLandau Monte Carlo sampling method which efficiently deals with the abrupt motions. Abrupt motions could cause conv...
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...
The joint tasks of object recognition and object segmentation from a single image are complex in their requirement of not only correct classification, but also deciding exactly whi...
We show that the complexity of the recently introduced medoid-shift algorithm in clustering N points is O(N2 ), with a small constant, if the underlying distance is Euclidean. This...
Abstract. We propose a fully automatic framework to detect and extract arbitrary human motion volumes from real-world videos collected from YouTube. Our system is composed of two s...
Juan Carlos Niebles, Bohyung Han, Andras Ferencz, ...