Sciweavers

CVPR
2008
IEEE
16 years 2 months ago
Selective hidden random fields: Exploiting domain-specific saliency for event classification
Classifying an event captured in an image is useful for understanding the contents of the image. The captured event provides context to refine models for the presence and appearan...
Vidit Jain, Amit Singhal, Jiebo Luo
106
Voted
CVPR
2008
IEEE
16 years 2 months ago
Image partial blur detection and classification
In this paper, we propose a partially-blurred-image classification and analysis framework for automatically detecting images containing blurred regions and recognizing the blur ty...
Renting Liu, Zhaorong Li, Jiaya Jia
104
Voted
CVPR
2008
IEEE
16 years 2 months ago
Exploiting side information in locality preserving projection
Even if the class label information is unknown, side information represents some equivalence constraints between pairs of patterns, indicating whether pairs originate from the sam...
Senjian An, Wanquan Liu, Svetha Venkatesh
86
Voted
CVPR
2008
IEEE
16 years 2 months ago
Object categorization using co-occurrence, location and appearance
In this work we introduce a novel approach to object categorization that incorporates two types of context ? cooccurrence and relative location ? with local appearancebased featur...
Carolina Galleguillos, Andrew Rabinovich, Serge Be...
42
Voted
CVPR
2008
IEEE
16 years 2 months ago
Classifiability-based Optimal Discriminatory Projection Pursuit
Yu Su, Shiguang Shan, Xilin Chen, Wen Gao
CVPR
2008
IEEE
16 years 2 months ago
What are the high-level concepts with small semantic gaps?
Yijuan Lu, Lei Zhang, Qi Tian, Wei-Ying Ma
91
Voted
CVPR
2008
IEEE
16 years 2 months ago
Increasing the density of Active Appearance Models
Active Appearance Models (AAMs) typically only use 50-100 mesh vertices because they are usually constructed from a set of training images with the vertices hand-labeled on them. ...
Krishnan Ramnath, Simon Baker, Iain Matthews, Deva...
86
Voted
CVPR
2008
IEEE
16 years 2 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
166
Voted
CVPR
2008
IEEE
1094views Computer Vision» more  CVPR 2008»
16 years 2 months ago
Image super-resolution using gradient profile prior
In this paper, we propose an image super-resolution approach using a novel generic image prior ? gradient profile prior, which is a parametric prior describing the shape and the s...
Jian Sun, Zongben Xu, Heung-Yeung Shum
77
Voted
CVPR
2008
IEEE
16 years 2 months ago
Pan, zoom, scan - Time-coherent, trained automatic video cropping
We present a method to fully automatically fit videos in 16:9 format on 4:3 screens and vice versa. It can be applied to arbitrary aspect ratios and can be used to make videos sui...
Thomas Deselaers, Philippe Dreuw, Hermann Ney