CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously Ncat = 104 -...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
Symmetry is one of the important cues for human and machine perception of the world. For over three decades, automatic symmetry detection from images/patterns has been a standing ...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
Given the video of a still background occluded by a fluid dynamic texture (FDT), this paper addresses the problem of separating the video sequence into its two constituent layers....
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
A generic imaging model refers to a non-parametric camera model where every camera is treated as a set of unconstrained projection rays. Calibration would simply be a method to ma...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
This paper proposes a general framework called Markov stationary features (MSF) to extend histogram based features. The MSF characterizes the spatial co-occurrence of histogram pa...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
This paper presents a novel local image descriptor that is robust to general image deformations. A limitation with traditional image descriptors is that they use a single support ...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
A new hierarchical Bayesian model is proposed for image segmentation based on Gaussian mixture models (GMM) with a prior enforcing spatial smoothness. According to this prior, the...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
Image categorization is undoubtedly one of the most challenging open problems faced in Computer Vision, far from being solved by employing pure visual cues. Recently, additional t...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
We consider two scenarios of naming people in databases of news photos with captions: (i) finding faces of a single person, and (ii) assigning names to all faces. We combine an in...