Sciweavers

ICCV
2009
IEEE
16 years 8 months ago
Is a detector only good for detection?
A common design of an object recognition system has two steps, a detection step followed by a foreground withinclass classification step. For example, consider face detection by...
Quan Yuan and Stan Sclaroff
116
Voted
ICCV
2009
IEEE
16 years 8 months ago
Deformable Model Fitting with a Mixture of Local Experts
Local experts have been used to great effect for fitting deformable models to images. Typically, the best location in an image for the deformable model’s landmarks are found t...
Jason M. Saragih, Simon Lucey, Jeffrey F. Cohn
ICCV
2009
IEEE
16 years 8 months ago
Scene Shape Priors for Superpixel Segmentation
Unsupervised over-segmentation of an image into superpixels is a common preprocessing step for image parsing algorithms. Superpixels are used as both regions of support for feat...
Alastair P. Moore, Simon J. D. Prince, Jonathan Wa...
110
Voted
ICCV
2009
IEEE
16 years 8 months ago
Detecting Interpretable and Accurate Scale-Invariant keypoints
This paper presents a novel method for detecting scale invariant keypoints. It fills a gap in the set of available methods, as it proposes a scale-selection mechanism for juncti...
Wolfgang F¨orstner, Timo Dickscheid, Falko Schind...
180
Voted
ICCV
2009
IEEE
1048views Computer Vision» more  ICCV 2009»
16 years 8 months ago
Face Recognition With Contiguous Occlusion Using Markov Random Fields
Partially occluded faces are common in many applications of face recognition. While algorithms based on sparse representation have demonstrated promising results, they achieve t...
Zihan Zhou, Andrew Wagner, Hossein Mobahi, John Wr...