We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Ou...
We study the problem of projecting high-dimensional tensor data on an unspecified Riemannian manifold onto some lower dimensional subspace1 without much distorting the pairwise geo...
This paper describes how to improve the reusability of iconic program modules. In iconic programming systems, the most important features for reuse are the customization of a modu...
We propose reliable outdoor object detection on mobile phone imagery from off-the-shelf devices. With the goal to provide both robust object detection and reduction of computation...
This paper describes an approach to retrieve images containing specific objects, scenes or buildings. The image content is captured by a set of local features. More precisely, we ...