We describe a simple variant of the interpolated Markov model with nonemitting state transitions and prove that it is strictly more powerful than any Markov model. More importantl...
We address the problem of selecting nondomain-specific language model training data to build auxiliary language models for use in tasks such as machine translation. Our approach i...
Developing effective content recognition methods for diverse imagery continues to challenge computer vision researchers. We present a new approach for document image content catego...
Guangyu Zhu, Xiaodong Yu, Yi Li, David S. Doermann
It is a well documented fact that, for human readers, familiar text is more legible than unfamiliar text. Current-generation computer vision systems also are able to exploit some ...