Night surveillance is a challenging task because of low brightness, low contrast, low Signal to Noise Ratio (SNR) and low appearance information. Most existing models for night su...
In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation ...
Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. ...
Abstract. We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We tre...
Jian Li, Timothy M. Hospedales, Shaogang Gong, Tao...
The detection of correlations between different features in a set of feature vectors is a very important data mining task because correlation indicates a dependency between the fe...