We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of di...
Vladimir Pavlovic, Brendan J. Frey, Thomas S. Huan...
Abstract. This paper presents a novel approach to analyze the appearance of human motions with a simple model i.e. mapping the motions using a virtual marionette model. The approac...
A method is presented to recover 3D scene structure and camera motion from multiple images without the need for correspondence information. The problem is framed as finding the ma...
Frank Dellaert, Steven M. Seitz, Charles E. Thorpe...
In this paper, a Bayesian self-calibration approach using sequential importance sampling (SIS) is proposed. Given a set of feature correspondences tracked through an image sequenc...
Inferring both 3D structure and motion of nonrigid objects from monocular images is an important problem in computational vision. The challenges stem not only from the absence of ...