In this paper, we present a new deconvolution method, able to deal with noninvertible blurring functions. To avoid noise amplification, a prior model of the image to be reconstruc...
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
Visual modeling languages for discrete behavior modeling allow the modeler to describe how systems develop over time during system runs. Models of these languages are the basis fo...
Enrico Biermann, Claudia Ermel, Jonas Hurrelmann, ...
Automatic speech recognition (ASR) results contain not only ASR errors, but also disfluencies and colloquial expressions that must be corrected to create readable transcripts. We...
Graham Neubig, Yuya Akita, Shinsuke Mori, Tatsuya ...
— Many software development methodologies are based on modeling the real world. In some of these methodologies, real-world models are gradually transformed into software models, ...