Online Boosting is an effective incremental learning method which can update weak classifiers efficiently according to the object being trackedt. It is a promising technique for o...
Abstract. In this paper we introduce a new mesh refinement method for subdivision surfaces. It generates a semiregular 4-direction hierarchical structure from control meshes repres...
Sign language recognition (SLR) plays an important role in human-computer interaction (HCI), especially for the convenient communication between deaf and hearing society. How to e...
We propose a multiple source domain adaptation method, referred to as Domain Adaptation Machine (DAM), to learn a robust decision function (referred to as target classifier) for l...
Detection of objects of a given class is important for many applications. However it is difficult to learn a general detector with high detection rate as well as low false alarm r...