Abstract In case of insufficient data samples in highdimensional classification problems, sparse scatters of samples tend to have many ‘holes’—regions that have few or no nea...
Hakan Cevikalp, Diane Larlus, Marian Neamtu, Bill ...
High dimensional data that lies on or near a low dimensional manifold can be described by a collection of local linear models. Such a description, however, does not provide a glob...
Sam T. Roweis, Lawrence K. Saul, Geoffrey E. Hinto...
Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
Many perceptual models and theories hinge on treating objects as a collection of constituent parts. When applying these approaches to data, a fundamental problem arises: how can w...
Optical flow estimation is a fundamental and ill-posed problem in computer vision. To recover a dense flow field, appropriate spatial constraints have to be enforced. Recent ad...