In this work, we systematically study the problem of visual event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which vide...
In this paper, we present an approach to incorporating partial geometric information into a local feature-based The distance-supported shape index is proposed for the representatio...
Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets for use in obje...
This paper deals with the representation of document models used in the field of document recognition. A novel formalism called generalized n-gram is presented, which is shown to b...
: We present a symbol recognition method without segmentation of the document. Our approach uses Zernike moments for the coding and a multilayered Perceptron for the classifier. Re...