We present a new general framework for online istic plan recognition called the Abstract Hidden Markov Memory Model (AHMEM). The l is an extension of the existing Abstract Hidden ...
Sampling points with blue noise spectral characteristics are best suited for antialiasing. Compared to Poisson disk sampling, Lloyd's relaxation scheme yields samples that ap...
This paper discusses the interpretation of nominalizations in domain independent wide-coverage text. We present a statistical model which interprets nominalizations based on the c...
We present a novel OCR error correction method for languages without word delimiters that have a large character set, such as Japanese and Chinese. It consists of a statistical OC...
In global illumination computations the photon map is a powerful tool for approximating the irradiance, which is stored independent from scene geometry. By presenting a new algori...