Sciweavers

CVPR
2006
IEEE
15 years 4 days ago
Solving Markov Random Fields using Second Order Cone Programming Relaxations
This paper presents a generic method for solving Markov random fields (MRF) by formulating the problem of MAP estimation as 0-1 quadratic programming (QP). Though in general solvi...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
CVPR
2006
IEEE
15 years 4 days ago
Principled Hybrids of Generative and Discriminative Models
When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications suc...
Julia A. Lasserre, Christopher M. Bishop, Thomas P...
CVPR
2006
IEEE
15 years 4 days ago
Clustering Appearance for Scene Analysis
We propose a new approach called "appearance clustering" for scene analysis. The key idea in this approach is that the scene points can be clustered according to their s...
Sanjeev J. Koppal, Srinivasa G. Narasimhan
CVPR
2006
IEEE
15 years 4 days ago
Image Matching Using Photometric Information
Image matching is an essential task in many computer vision applications. It is obvious that thorough utilization of all available information is critical for the success of match...
Michael Kolomenkin, Ilan Shimshoni
CVPR
2006
IEEE
15 years 4 days ago
The Design of High-Level Features for Photo Quality Assessment
1 We propose a principled method for designing high level features for photo quality assessment. Our resulting system can classify between high quality professional photos and low...
Yan Ke, Xiaoou Tang, Feng Jing
CVPR
2006
IEEE
15 years 4 days ago
Correlated Label Propagation with Application to Multi-label Learning
Many computer vision applications, such as scene analysis and medical image interpretation, are ill-suited for traditional classification where each image can only be associated w...
Feng Kang, Rong Jin, Rahul Sukthankar
CVPR
2006
IEEE
15 years 4 days ago
Statistical Analysis of Local 3D Structure in 2D Images
For the analysis of images, a deeper understanding of their intrinsic structure is required. This has been obtained for 2D images by means of statistical analysis [15, 18]. Here, ...
Florentin Wörgötter, Norbert Krüger...