Sciweavers

206 search results - page 26 / 42
» Learning Parameterized Models of Image Motion
Sort
View
81
Voted
ICCV
2009
IEEE
16 years 4 months ago
Recovering the Spatial Layout of Cluttered Rooms
In this paper, we consider the problem of recovering the spatial layout of indoor scenes from monocular images. The presence of clutter is a major problem for existing singleview...
Varsha Hedau, Derek Hoiem, David Forsyth
CVPR
2006
IEEE
16 years 1 months ago
Unsupervised Bayesian Detection of Independent Motion in Crowds
While crowds of various subjects may offer applicationspecific cues to detect individuals, we demonstrate that for the general case, motion itself contains more information than p...
Gabriel J. Brostow, Roberto Cipolla
CVPR
2003
IEEE
16 years 1 months ago
Learning Appearance and Transparency Manifolds of Occluded Objects in Layers
By mapping a set of input images to points in a lowdimensional manifold or subspace, it is possible to efficiently account for a small number of degrees of freedom. For example, i...
Brendan J. Frey, Nebojsa Jojic, Anitha Kannan
NIPS
1998
15 years 1 months ago
Learning to Estimate Scenes from Images
We seek the scene interpretation that best explains image data. For example, we may want to infer the projected velocities (scene) which best explain two consecutive image frames ...
William T. Freeman, Egon C. Pasztor
CLOR
2006
15 years 3 months ago
Sequential Learning of Layered Models from Video
Abstract. A popular framework for the interpretation of image sequences is the layers or sprite model, see e.g. [1], [2]. Jojic and Frey [3] provide a generative probabilistic mode...
Michalis K. Titsias, Christopher K. I. Williams