Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Studies support the need for high resolution imagery to identify persons in surveillance videos[13]. However, the use of telephoto lenses sacrifices a wider field of view and ther...
Boosting has been widely applied in computer vision, especially after Viola and Jones's seminal work [23]. The marriage of rectangular features and integral-imageenabled fast...
Reliable 3D tracking is still a difficult task. Most parametrized 3D deformable models rely on the accurate extraction of image features for updating their parameters, and are pro...
Christian Vogler, Zhiguo Li, Atul Kanaujia, Siome ...
Abstract. Multi-sampled imaging is a general framework for using pixels on an image detector to simultaneously sample multiple dimensions of imaging (space, time, spectrum, brightn...