Sciweavers

508 search results - page 48 / 102
» Near-Optimal Regularization Parameters for Applications in C...
Sort
View
CVPR
2011
IEEE
13 years 3 months ago
Sharing Features Between Objects and Their Attributes
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
Sung Ju Hwang, Fei Sha, Kristen Grauman
CVPR
2008
IEEE
14 years 9 months ago
A two-frame theory of motion, lighting and shape
This paper explores how shape, motion, and lighting interact in the case of a two-frame motion sequence. We consider a rigid object with Lambertian reflectance properties undergoi...
Ronen Basri, Darya Frolova
ACCV
2006
Springer
14 years 1 months ago
A Bottom up Algebraic Approach to Motion Segmentation
We present a bottom up algebraic approach for segmenting multiple 2D motion models directly from the partial derivatives of an image sequence. Our method fits a polynomial called ...
Dheeraj Singaraju, René Vidal
ICIP
2003
IEEE
14 years 29 days ago
A SR-based radon transform to extract weak lines from noise images
The Radon transform is able to transform two dimensional images with lines into a space of line parameters, where each line in the image will give a peak positioned at the corresp...
Qinghua Ye, Haining Huang, Xinyi He, Chimhua Zhang
ICVGIP
2004
13 years 9 months ago
Use of Linear Diffusion in Depth Estimation Based on Defocus Cue
Diffusion has been used extensively in computer vision. Most common applications of diffusion have been in low level vision problems like segmentation and edge detection. In this ...
Vinay P. Namboodiri, Subhasis Chaudhuri