The work proposes a hierarchical architecture for learning amic scenes at various levels of knowledge abstraction. The raw visual information is processed at different stages to g...
Many realistic visual recognition tasks are “open” in the sense that the number and nature of the categories to be learned are not initially known, and there is no closed set ...
We developed a distributed support model in an interface for distant learning. The support is integrated into the ExploraGraph navigator which makes it possible to navigate through...
We present a binocular robot that learns compensatory camera movements for image stabilization purposes. Most essential in achieving satisfactory image stabilization performance i...
It is common in classification methods to first place data in a vector space and then learn decision boundaries. We propose reversing that process: for fixed decision boundaries, ...