We present an integrated model for visual object localization and continuous state estimation in a discriminative structured prediction framework. While existing discriminative `p...
Graphical models are powerful tools for processing images. However, the large dimensionality of even local image data poses a difficulty: representing the range of possible graphi...
Marshall F. Tappen, Bryan C. Russell, William T. F...
A bugbear of uncalibrated stereo reconstruction is that cameras which deviate from the pinhole model have to be pre-calibrated in order to correct for nonlinear lens distortion. I...
This paper deals with the 3D shape estimation from silhouette cues of multiple moving objects in general indoor or outdoor 3D scenes with potential static obstacles, using multipl...
A Bayesian marked point process (MPP) model is developed
to detect and count people in crowded scenes. The
model couples a spatial stochastic process governing number
and placem...