Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
Recent research in object recognition has demonstrated the advantages of representing objects and scenes through localized patterns such as small image templates. In this paper we...
This paper describes an online learning method of color transformation for interactive object recognition. In order to recognize objects under various lighting conditions, the sys...
Model learning and tracking are two important topics in computer vision. While there are many applications where one of them is used to support the other, there are currently only...
We present an approach for online learning of discriminative appearance models for robust multi-target tracking in a crowded scene from a single camera. Although much progress has...