Range Image Segmentation by an Effective Jump-Diffusion Method
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Salient Closed Boundary Extraction with Ratio Contour
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Parsing: Unifying Segmentation, Detection, and Recognition
International Journal of Computer Vision
Generalizing Swendsen-Wang to Sampling Arbitrary Posterior Probabilities
IEEE Transactions on Pattern Analysis and Machine Intelligence
Variational Maximum A Posteriori by Annealed Mean Field Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Parsing Images into Regions, Curves, and Curve Groups
International Journal of Computer Vision
A Generative Sketch Model for Human Hair Analysis and Synthesis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition Letters - Special issue: Evolutionary computer vision and image understanding
Random Walks for Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Revisiting probabilistic models for clustering with pair-wise constraints
Proceedings of the 24th international conference on Machine learning
Learning to Combine Bottom-Up and Top-Down Segmentation
International Journal of Computer Vision
Stereo matching using population-based MCMC
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Bayesian inference for layer representation with mixed Markov random field
EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Accurate semantic image labeling by fast geodesic propagation
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Multigrid and multi-level Swendsen-Wang cuts for hierarchic graph partition
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Segmentation subject to stitching constraints: finding many small structures in a large image
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Learning to combine bottom-up and top-down segmentation
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
A bayesian approach for building detection in densely build-up high resolution satellite image
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part II
On the relationship between image and motion segmentation
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
Grouping objects in multi-band images using an improved eigenvector-based algorithm
Mathematical and Computer Modelling: An International Journal
Improving performance of topic models by variable grouping
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Hi-index | 0.00 |
Vision tasks, such as segmentation, grouping, recognition, can beformulated as graph partition problems. The recent literaturewitnessed two popular graph cut algorithms: the Ncut using spectralgraph analysis and the minimum-cut using the maximum flowalgorithm. This paper presents a third major approach bygeneralizing the Swendsen-Wang method- a well celebrated algorithmin statistical mechanics. Our algorithm simulates ergodic,reversible Markov chain jumps in the space of graph partitions tosample a posterior probability. At each step, the algorithm splits,merges, or re-groups a sizable subgraph, and achieves fast mixingat low temperature enabling a fast annealing procedure. Experimentsshow it converges in 2-30seconds in a PC for image segmentation.This is 400 times faster than the single-site update Gibbs sampler,and 20-40 times faster than the DDMCMC algorithm. The algorithm canoptimize over the number of models and works for general forms ofposterior probabilities, so it is more general than the existinggraph cut approaches.