13476 search results - page 614 / 2696 » Learning from Streams |
228
click to vote
ICCV
2009
IEEE
16 years 10 months ago
2009
IEEE
Methods for super-resolution (SR) can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misa...
194
click to vote
CVPR
2004
IEEE
16 years 9 months ago
2004
IEEE
In this paper we perform 3D face tracking on corrupted video sequences. We use a deformable model, combined with a predictive filter, to recover both the rigid transformations and...
211
Voted
CVPR
2006
IEEE
16 years 9 months ago
2006
IEEE
In order to work well, many computer vision algorithms require that their parameters be adjusted according to the image noise level, making it an important quantity to estimate. W...
224
click to vote
ICCV
2001
IEEE
16 years 9 months ago
2001
IEEE
By representing images and image prototypes by linear subspaces spanned by "tangent vectors" (derivatives of an image with respect to translation, rotation, etc.), impre...
240
click to vote
ECCV
2008
Springer
16 years 9 months ago
2008
Springer
Abstract. The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often "engineered" to...