Sciweavers

CVPR
2010
IEEE
14 years 21 days ago
A Content-Aware Image Prior
In image restoration tasks, a heavy-tailed gradient distribution of natural images has been extensively exploited as an image prior. Most image restoration algorithms impose a spa...
Taeg Sang Cho, Neel Joshi, Larry Zitnick, Sing Bin...
CVPR
2010
IEEE
14 years 21 days ago
Supervised Translation-Invariant Sparse Coding
In this paper, we propose a novel supervised hierarchical sparse coding model based on local image descriptors for classification tasks. The supervised dictionary training is perf...
Jianchao Yang, Kai Yu, Thomas Huang
CVPR
2010
IEEE
14 years 21 days ago
Self-calibrating Photometric Stereo
We present a self-calibrating photometric stereo method. From a set of images taken from a fixed viewpoint under different and unknown lighting conditions, our method automaticall...
Boxin Shi, Yasuyuki Matsushita, Yichen Wei, Chao X...
CVPR
2010
IEEE
14 years 21 days ago
Segmentation of Building Facades Using Procedural Shape Priors
In this paper we propose a novel approach to the perceptual interpretation of building facades that combines shape grammars, supervised classification and random walks. Procedural...
Olivier Teboul, Loic Simon, Panagiotis Koutsouraki...
CVPR
2010
IEEE
14 years 21 days ago
Reading Between The Lines: Object Localization Using Implicit Cues from Image Tags
Current uses of tagged images typically exploit only the most explicit information: the link between the nouns named and the objects present somewhere in the image. We propose to ...
Sung Ju Hwang, University of Texas, Kristen Grauma...
CVPR
2010
IEEE
1192views Computer Vision» more  CVPR 2010»
14 years 21 days ago
RASL: Robust Alignment by Sparse and Low-rank Decomposition for Linearly Correlated Images
This paper studies the problem of simultaneously aligning a batch of linearly correlated images despite gross corruption (such as occlusion). Our method seeks an optimal set of im...
Yigang Peng, Arvind Balasubramanian, John Wright, ...
CVPR
2010
IEEE
1106views Computer Vision» more  CVPR 2010»
14 years 21 days ago
Context-Aware Saliency Detection
We propose a new type of saliency – context-aware saliency – which aims at detecting the image regions that represent the scene. This definition differs from previous definit...
Stas Goferman, Ayellet Tal, Lihi Zelnik-Manor
CVPR
2010
IEEE
14 years 21 days ago
Cascade Object Detection with Deformable Part Models
We describe a general method for building cascade classifiers from part-based deformable models such as pictorial structures. We focus primarily on the case of star-structured mod...
Pedro Felzenszwalb, Ross Girshick, David McAlleste...
CVPR
2010
IEEE
14 years 21 days ago
The Role of Features, Algorithms and Data in Visual Recognition
There are many computer vision algorithms developed for visual (scene and object) recognition. Some systems focus on involved learning algorithms, some leverage millions of trainin...
Devi Parikh and C. Lawrence Zitnick
CVPR
2010
IEEE
1171views Computer Vision» more  CVPR 2010»
14 years 1 months ago
Geodesic Star Convexity for Interactive Image Segmentation
In this paper we introduce a new shape constraint for interactive image segmentation. It is an extension of Veksler's star-convexity prior, in two ways: from a single star to ...
Varun Gulshan, Carsten Rother, Antonio Criminisi, ...