258 search results - page 19 / 52 » Using Co-Occurrence and Segmentation to Learn Feature-Based ... |
NIPS
2004
13 years 9 months ago
2004
We consider the problem of geometrical surface reconstruction from one or several images using learned shape models. While humans can effortlessly retrieve 3D shape information, t...
CVPR
2010
IEEE
13 years 7 months ago
2010
IEEE
We present a novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera. Related methods involving learning of pattern...
CVPR
2011
IEEE
12 years 11 months ago
2011
IEEE
Simultaneously segmenting and labeling images is a fundamental problem in Computer Vision. In this paper, we introduce a hierarchical CRF model to deal with the problem of labelin...
ICIP
2006
IEEE
14 years 9 months ago
2006
IEEE
This paper proposes to combine spatial and color coherency with the pixel-wise GMM to determine the background model. We first represent each pixel with a hybrid feature vector, w...
CVPR
2011
IEEE
13 years 5 months ago
2011
IEEE
Unsupervised learning can be used to extract image representations that are useful for various and diverse vision tasks. After noticing that most biological vision systems for int...