Recreating the temporal illumination variations of natural scenes has great potential for realistic synthesis of video sequences. In this paper, we present a 3D (model-based) appr...
We have developed a new semi-automatic neural network based method to detect blotches with low false alarm rate on archive films. Blotches can be modeled as temporal intensity disc...
In this paper, we present a modified snake model for the problem of general video object tracking. We introduce a new external force into the snake equation based on the predictiv...
Discrepancy between CT and PET data due to motion in PET/CT studies is a significant problem. PET is acquired over a period of time whereas CT is static. Thus attenuation correcti...
Camera motion detection is essential for automated video analysis. We propose a new probabilistic model for detecting zoom-in/zoom-out operations. The model uses EM to estimate th...