Detection of objects through scanning windows is widely used and accepted method. The detectors traditionally do not make use of information that is shared between neighboring imag...
Abstract. In this paper, we address the problem of efficient human action detection with only one template. We choose the standard slidingwindow approach to scan the template video...
Compressed sensing, an emerging multidisciplinary field involving mathematics, probability, optimization, and signal processing, focuses on reconstructing an unknown signal from a...
Shiqian Ma, Wotao Yin, Yin Zhang, Amit Chakraborty
This paper generalizes the methods in a previous paper [10] in two ways. First, a more comprehensive analysis of the initialization problem of the Chan-Vese models is given. Secon...
J. Douglas Birdwell, Seddik M. Djouadi, Yongsheng ...
We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features....