106
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications suc...
121
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
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...
118
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
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...
99
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
102
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
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...
95
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
105
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
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...
89
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
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, ...
83
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
Conventional video summarization methods focus predominantly on summarizing videos along the time axis, such as building a movie trailer. The resulting video trailer tends to reta...