The goal of semi-supervised image segmentation is to obtain the segmentation from a partially labeled image. By utilizing the image manifold structure in labeled and unlabeled pix...
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...
This paper sets out a tracking framework, which is applied to the recovery of threedimensional hand motion from an image sequence. The method handles the issues of initialization,...
Kernel-based non-parametric models have been applied widely over recent years. However, the associated computational complexity imposes limitations on the applicability of those me...
Jian Qing Shi, Roderick Murray-Smith, D. M. Titter...
In this paper, we deal with the estimation of body and head poses (i.e orientations) in surveillance videos, and we make three main contributions. First, we address this issue as ...