In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
Visual object tracking can be considered as a figure-ground classification task. In this paper, different features are used to generate a set of likelihood maps for each pixel i...
We present a model of adaptive attacks which we combine with information-theoretic metrics to quantify the information revealed to an adaptive adversary. This enables us to expres...
In this paper, we propose a novel contextual descriptor which combines the contextual information and local appearance. Based on Gibbs distribution, a local descriptor is designed...
Yi Ouyang, Ming Tang, Jian Cheng, Jinqiao Wang, Ha...
The study of how metal deforms and flows as parts are machined yields important insights into the metal cutting process. Improvements in high-speed digital imaging and image proce...