Active vision
Class-Specific, Top-Down Segmentation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Graph Partition by Swendsen-Wang Cuts
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Image Parsing: Unifying Segmentation, Detection, and Recognition
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Kernel conditional random fields: representation and clique selection
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Combining Top-Down and Bottom-Up Segmentation
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 4 - Volume 04
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
LOCUS: Learning Object Classes with Unsupervised Segmentation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
One-Shot Learning of Object Categories
IEEE Transactions on Pattern Analysis and Machine Intelligence
Minimax Entropy Principle and Its Application to Texture Modeling
Neural Computation
Multiscale conditional random fields for image labeling
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Learning and incorporating top-down cues in image segmentation
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Constructing free-energy approximations and generalized belief propagation algorithms
IEEE Transactions on Information Theory
A bottom-up and top-down model for cell segmentation using multispectral data
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Image segmentation with topic random field
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part II
A Numerical Study of the Bottom-Up and Top-Down Inference Processes in And-Or Graphs
International Journal of Computer Vision
Multi-scale stacked sequential learning
Pattern Recognition
International Journal of Computer Vision
SLAR (simultaneous localization and recognition) framework for smart CBIR
PerMIn'12 Proceedings of the First Indo-Japan conference on Perception and Machine Intelligence
Segmentation of objects in a detection window by Nonparametric Inhomogeneous CRFs
Computer Vision and Image Understanding
Object Recognition by Sequential Figure-Ground Ranking
International Journal of Computer Vision
Beyond bounding-boxes: learning object shape by model-driven grouping
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
Bottom-up segmentation based only on low-level cues is a notoriously difficult problem. This difficulty has lead to recent top-down segmentation algorithms that are based on class-specific image information. Despite the success of top-down algorithms, they often give coarse segmentations that can be significantly refined using low-level cues. This raises the question of how to combine both top-down and bottom-up cues in a principled manner.In this paper we approach this problem using supervised learning. Given a training set of ground truth segmentations we train a fragment-based segmentation algorithm which takes into account both bottom-up and top-down cues simultaneously, in contrast to most existing algorithms which train top-down and bottom-up modules separately. We formulate the problem in the framework of Conditional Random Fields (CRF) and derive a feature induction algorithm for CRF, which allows us to efficiently search over thousands of candidate fragments. Whereas pure top-down algorithms often require hundreds of fragments, our simultaneous learning procedure yields algorithms with a handful of fragments that are combined with low-level cues to efficiently compute high quality segmentations.