We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
Abstract: We address the recovery of segmented, 3-0 descriptions of an object from intensity images. We use three views of an objectfrom slightly different viewpointsas our input. ...
Abstract. A novel method is proposed for performing multi-label, semi-automated image segmentation. Given a small number of pixels with user-defined labels, one can analytically (...
Given a collection of images of offices, what would we say we see in the images? The objects of interest are likely to be monitors, keyboards, phones, etc. Such identification of t...
SVM based image retrieval suffers from the scarcity of labelled samples. In this paper, this problem is solved by incorporating prior knowledge into SVM. Firstly, some prior knowl...