Large high-resolution displays combine the images of multiple smaller display devices to form one large display area. A total resolution that can easily comprise several hundred m...
Abstract—The idea of an online visual vocabulary is proposed. In contrast to the accepted strategy of generating vocabularies offline, using the k-means clustering over all the ...
Despite significant recent progress, the best available visual saliency models still lag behind human performance in predicting eye fixations in free-viewing of natural scenes. ...
The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or nonGaussian functions, leading to analytically intractable inference. ...
We propose a generative model that codes the geometry and appearance of generic visual object categories as a loose hierarchy of parts, with probabilistic spatial relations linkin...