We propose an online algorithm based on local sparse representation for robust object tracking. Local image patches of a target object are represented by their sparse codes with a...
We present a novel algorithm that takes as input an uncalibrated unordered set of spherical panoramic images and outputs their relative pose up to a global scale. The panoramas co...
Learning from streams of evolving and unbounded data is an important problem, for example in visual surveillance or internet scale data. For such large and evolving real-world data...
Chen Change Loy, Timothy M. Hospedales, Tao Xiang,...
We assess the generative power of the mPoTmodel of [10] with tiled-convolutional weight sharing as a model for visual textures by specifically training on this task, evaluating m...
Compositing is one of the most commonly performed operations in computer graphics. A realistic composite requires adjusting the appearance of the foreground and background so that...
Su Xue, Aseem Agarwala, Julie Dorsey, Holly E. Rus...