On sparse images, contiguous runs of identical symbols often occur in the same coding context. This paper proposes a model for efficiently encoding such runs in a twodimensional s...
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
This paper describes a novel solution to the rigid point pattern matching problem in Euclidean spaces of any dimension. Although we assume rigid motion, jitter is allowed. We pres...
This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered...
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...