We present a novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera. Related methods involving learning of pattern...
Most tracking algorithms implicitly apply a coarse segmentation of each target object using a simple mask such as a rectangle or an ellipse. Although convenient, such coarse segme...
In real world, an image is usually associated with multiple labels which are characterized by different regions in the image. Thus image classification is naturally posed as both ...
Zheng-Jun Zha, Xian-Sheng Hua, Tao Mei, Jingdong W...
Abstract—Diffusions are useful for image processing and computer vision because they provide a convenient way of smoothing noisy data, analyzing images at multiple scales, and en...
We propose an algorithm for extracting facial features robustly from images for face recognition under large pose variation. Rectangular facial features are retrieved via the by-p...