In this work, we present a new semantic language modeling approach to model news stories in the Topic Detection and Tracking (TDT) task. In the new approach, we build a unigram la...
In this paper, we propose a novel method to localize (or track) a foreground object and segment the foreground object from the surrounding background with occlusions for a moving ...
We describe a technique for using the joint occurrence of local features at multiple resolutions to measure the similarity between texture images. Though superficially similar to ...
This paper presents a new approach to largevocabulary online handwritten Chinese character recognition based on semi-tied covariance (STC) modeling. Detailed procedures are descri...
—Perception, prediction and generation of sequences is a fundamental aspect of human behavior and depends on the ability to detect serial order. This paper presents a plausible m...