Markov Random Fields for Vision and Image Processing
By Andrew Blake, Pushmeet Kohli, Carsten Rother. 2011
302 citations recorded by the source corpus.
Subfields: Atmospheric Science, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/22352ffef6a995aa0b265ba49a92832df09b0734
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Atmospheric Science
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jitendra Malik
- Ming-Hsuan Yang
- Xiaogang Wang
- Trevor Darrell
- Andrew Zisserman
- Dacheng Tao
- Andrea Vedaldi
Citations in the corpus
- Parameter Learning and Convergent Inference for Dense Random Fields (2013, methodology): “Random field models are often used to express image coherence priors in computer vision applications, such as segmentation and reconstruction (Blake et al., 2011).”
- Playing with Duality: An overview of recent primal?dual approaches for solving large-scale optimization problems (2014, unknown): “A good example is the field of com puter vision where one often needs to solve low level problems that require associating at least one (and ty pically more than one) variable to each pixel of an image (or even worse of an image sequence as in the case of video) [2] .”
- Joint 3D Object and Layout Inference from a Single RGB-D Image (2015, background): “Despite the great promise of high-order discrete CRFs for solving computer vision problems [2, 43], MAP inference in such models remains very challenging.”
- Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2011, background): “Classic Markov random fields [8] add generic spatial priors to achieve more homogeneous outputs by smoothing noisy local evidence.”
- Finding and Leveraging Structure in Learning Problems (2012, background): “, 2005], and computer vision [Blake et al., 2011] amongst several others.”
- Learning an interactive segmentation system (2009, background): “Two recent articles [13, 5] already employ our robot user to learn and compare various different segmentation algorithms, which demonstrates the usefulness of our approach.”