The paper poses video-to-video face recognition as a dynamical system identification and classification problem. Video-to-video means that both gallery and probe consists of video...
Amit K. Roy Chowdhury, Gaurav Aggarwal, Rama Chell...
Detection, tracking, segmentation and pose estimation of people in monocular images are widely studied. Two-dimensional models of the human body are extensively used, however, they...
In kernel density estimation methods, an approximation of the data probability density function is achieved by locating a kernel function at each data location. The smoothness of ...
Using models in different contexts poses major integration challenges, ranging from technical to conceptual levels. Independently of each other developed model components cannot b...
We present a new model-based bundle adjustment algorithm to recover the 3D model of a scene/object from a sequence of images with unknown motions. Instead of representing scene/ob...