Sciweavers

Share
CVPR
2010
IEEE
9 years 24 days ago
An Online Approach: Learning-Semantic-Scene-by-Tracking and Tracking-by-Learning-Semantic-Scene
Learning the knowledge of scene structure and tracking a large number of targets are both active topics of computer vision in recent years, which plays a crucial role in surveilla...
Xuan Song, Xiaowei Shao, Huijing Zhao, Jinshi Cui,...
CVPR
2010
IEEE
9 years 24 days ago
"Lattice Cut" - Constructing superpixels using layer constraints
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 featur...
Alastair Moore, Simon Prince
CVPR
2010
IEEE
9 years 24 days ago
The Automatic Design of Feature Spaces for Local Image Descriptors using an Ensemble of Non-linear Feature Extractors
The design of feature spaces for local image descriptors is an important research subject in computer vision due to its applicability in several problems, such as visual classifi...
Gustavo Carneiro
CVPR
2010
IEEE
9 years 24 days ago
Object Separation In X-Ray Image Sets
In the segmentation of natural images, most algorithms rely on the concept of occlusion. In x-ray images, however, this assumption is violated, since x-ray photons penetrate most ...
Geremy Heitz, Gal Chechik
CVPR
2010
IEEE
9 years 1 months ago
Object Recognition as Ranking Holistic Figure-Ground Hypotheses
We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up,...
Fuxin Li, JoãCarreira, Cristian Sminchisescu
CVPR
2010
IEEE
9 years 1 months ago
Visual Recognition using Mappings that Replicate Margins
We consider the problem of learning to map between two vector spaces given pairs of matching vectors, one from each space. This problem naturally arises in numerous vision problem...
Lior Wolf, Nathan Manor
CVPR
2010
IEEE
9 years 1 months ago
Motion Fields to Predict Play Evolution in Dynamic Sport Scenes
Videos of multi-player team sports provide a challenging domain for dynamic scene analysis. Player actions and interactions are complex as they are driven by many factors, such as...
Kihwan Kim, Matthias Grundmann, Ariel Shamir, Iain...
books