A new algorithm for the design of complex features, to be used in the discriminant saliency approach to object classification, is presented. The algorithm consists of sequential r...
We present a simple, principled approach to detecting foreground objects in video sequences in real-time. Our method is based on an on-line discriminative learning technique that ...
Li Cheng, Shaojun Wang, Dale Schuurmans, Terry Cae...
Recently, the optimal distance measure for a given object discrimination task under the nearest neighbor framework was derived [1]. For ease of implementation and efficiency consi...
In this paper, we follow the minimum error principle for acoustic modeling and formulate error objectives in insertion, deletion, and substitution separately for minimization duri...