Weighted finite-state transducers have been used successfully in a variety of natural language processing applications, including speech recognition, speech synthesis, and machine ...
This paper describes a method of supervised learning based on forward selection branching. This method improves fault tolerance by means of combining information related to general...
Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made ...
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
Object tracking is viewed as a two-class 'one-versusrest' classification problem, in which the sample distribution of the target is approximately Gaussian while the back...
Xiaoqin Zhang, Weiming Hu, Stephen J. Maybank, Xi ...