Sciweavers

CVPR
2007
IEEE
14 years 11 months ago
Hybrid learning of large jigsaws
A jigsaw is a recently proposed generative model that describes an image as a composition of non-overlapping patches of varying shape, extracted from a latent image. By learning t...
Julia A. Lasserre, Anitha Kannan, John M. Winn
CVPR
2007
IEEE
14 years 11 months ago
Opti-Acoustic Stereo Imaging, System Calibration and 3-D Reconstruction
Utilization of an acoustic camera for range measurements is a key advantage for 3-D shape recovery of underwater targets by opti-acoustic stereo imaging, where the associated epip...
Shahriar Negahdaripour, Hicham Sekkati, Hamed Pirs...
CVPR
2007
IEEE
14 years 11 months ago
Stereo Matching on Objects with Fractional Boundary
Conventional stereo matching algorithms assume color constancy on the corresponding opaque pixels in the stereo images. However, when the foreground objects with fractional bounda...
Wei Xiong, Jiaya Jia
CVPR
2007
IEEE
14 years 11 months ago
Filtered Component Analysis to Increase Robustness to Local Minima in Appearance Models
Appearance Models (AM) are commonly used to model appearance and shape variation of objects in images. In particular, they have proven useful to detection, tracking, and synthesis...
Fernando De la Torre, Alvaro Collet, Manuel Quero,...
CVPR
2007
IEEE
14 years 11 months ago
3D Occlusion Inference from Silhouette Cues
We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views....
Jean-Sébastien Franco, Li Guan, Marc Pollef...
CVPR
2007
IEEE
14 years 11 months ago
Visual Curvature
Hairong Liu, Longin Jan Latecki, Wenyu Liu, Xiang ...
CVPR
2007
IEEE
14 years 11 months ago
On the Spacetime Geometry of Galilean Cameras
In this paper, a projection model is presented for cameras moving at constant velocity (which we refer to as Galilean cameras). To that end, we introduce the concept of spacetime ...
Yaser Sheikh, Alexei Gritai, Mubarak Shah
CVPR
2007
IEEE
14 years 11 months ago
Learning Object Material Categories via Pairwise Discriminant Analysis
In this paper, we investigate linear discriminant analysis (LDA) methods for multiclass classification problems in hyperspectral imaging. We note that LDA does not consider pairwi...
Zhouyu Fu, Antonio Robles-Kelly
CVPR
2007
IEEE
14 years 11 months ago
Variable Bandwidth Image Denoising Using Image-based Noise Models
This paper introduces a variational formulation for image denoising based on a quadratic function over kernels of variable bandwidth. These kernels are scale adaptive and reflect ...
Noura Azzabou, Nikos Paragios, Frederic Guichard, ...
CVPR
2007
IEEE
14 years 11 months ago
Two thresholds are better than one
The concept of the Bayesian optimal single threshold is a well established and widely used classification technique. In this paper, we prove that when spatial cohesion is assumed ...
Tao Zhang, Terrance E. Boult, R. C. Johnson