Sciweavers

297 search results - page 28 / 60
» Topologically-constrained latent variable models
Sort
View
ICCV
2011
IEEE
12 years 10 months ago
Are Spatial and Global Constraints Really Necessary for Segmentation?
Many state-of-the-art segmentation algorithms rely on Markov or Conditional Random Field models designed to enforce spatial and global consistency constraints. This is often accom...
Aurelien Lucchi, Yunpeng Li, Xavier Boix, Kevin Sm...
ECCV
2010
Springer
14 years 2 months ago
Inferring 3D Shapes and Deformations from Single Views
Abstract. In this paper we propose a probabilistic framework that models shape variations and infers dense and detailed 3D shapes from a single silhouette. We model two types of sh...
CVIU
2011
13 years 1 months ago
Single and sparse view 3D reconstruction by learning shape priors
In this paper, we aim to reconstruct free-form 3D models from only one or few silhouettes by learning the prior knowledge of a specific class of objects. Instead of heuristically...
Yu Chen, Roberto Cipolla
CVPR
2012
IEEE
12 years 9 days ago
Top-down visual saliency via joint CRF and dictionary learning
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
Jimei Yang, Ming-Hsuan Yang
ECCV
2010
Springer
14 years 3 months ago
A Discriminative Latent Model of Object Classes and Attributes
Abstract. We present a discriminatively trained model for joint modelling of object class labels (e.g. “person”, “dog”, “chair”, etc.) and their visual attributes (e.g....