In this paper, we propose a novel learning method, called Jensen-Shannon Boosting (JSBoost) and demonstrate its application to object recognition. JSBoost incorporates Jensen-Shan...
We consider the problem of grasping novel objects in cluttered environments. If a full 3-d model of the scene were available, one could use the model to estimate the stability and...
Self-explaining has been repeatedly shown to result in positive learning outcomes for students in a wide variety of disciplines. However, there are two potential accounts for why s...
In this paper, we present a novel feature extraction framework, called learning by propagability. The whole learning process is driven by the philosophy that the data labels and o...
Bingbing Ni, Shuicheng Yan, Ashraf A. Kassim, Loon...
Studying human activities has significant implication in human beneficial applications such as personal healthcare. This research has been facilitated by the development of sensor ...