Probabilistic models have been adopted for many computer vision applications, however inference in highdimensional spaces remains problematic. As the statespace of a model grows, ...
Modeling representations of image patches that are quasi-invariant to spatial deformations is an important problem in computer vision. In this paper, we propose a novel concept, t...
Jan Ernst, Maneesh Kumar Singh, Visvanathan Ramesh
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...
We describe a software development approach for vision that enhances robustness by making novel use of context. Conventional approaches to most image understanding problems suffe...
This paper presents an unsupervised method for assembling semantic knowledge from a part-ofspeech tagged corpus using graph algorithms. The graph model is built by linking pairs o...