Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
ct We describe work on the visualization of bibliographic data and, to aid in this task, the application of numerical techniques for multidimensional scaling. Many areas of scienti...
`Invariant regions' are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then desc...
In semi-supervised learning, a number of labeled examples are usually required for training an initial weakly useful predictor which is in turn used for exploiting the unlabeled e...
Local features are widely utilized in a large number of applications, e.g., object categorization, image retrieval, robust matching, and robot localization. In this review, we foc...