Efficient Belief Propagation with Learned Higher-Order Markov Random Fields
By Xiangyang Lan, Stefan Roth, Dan Huttenlocher, Michael J. Black. 2006
225 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Philip H. S. Torr
- Raquel Urtasun
- Chunhua Shen
- Alexander Gerhard Schwing
- Bernt Schiele
- Pushmeet Kohli
- Sanja Fidler
- Alan L. Yuille
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Chunhua Shen
- Jitendra Malik
- Andrew Zisserman
- Dacheng Tao
- Andrea Vedaldi
- Ming-Hsuan Yang
- Xiaogang Wang
In Media Technology
- Chunhua Shen
- C. V. Jawahar
- Anand Mishra
- Alahari Karteek
- Raquel Urtasun
- Hiroshi Ishikawa
- Philip H. S. Torr
- Stefan Roth
Citations in the corpus
- Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising (2019, background): “Traditional image denoising methods generally focus on modeling natural image priors and use the priors to restore the clean image, including sparse models [5, 26], Markov random field models [13], etc.”
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (2016, neutral): “random field (MRF) models [10], [11], [12].”
- Scene Text Recognition using Higher Order Language Priors (2009, methodology): “They have been successfully used to improve the results of problems such as image denoising, restoration [20, 22], texture segmentation [15], object category segmentation [16].”
- Fields of Experts (2009, methodology): “As already discussed in Section 2.3 in the context of general MRF models, inference with FoEs will almost necessarily have to be approximate, not only because of the loopy graph structure, but also because of the high dimensionality of images, and the large state space (large number of gray levels, ”
- Robust Higher Order Potentials for Enforcing Label Consistency (2008, methodology): “They have been frequently used to model image textures [18, 20, 24].”
- A Fully-Connected Layered Model of Foreground and Background Flow (2013, unknown): “One way to go beyond local MRFs is to use higher-order potentials [24], but these models are difficult to optimize using GC [14] or BP [19].”
- Higher-order clique reduction in binary graph cut (2009, methodology): “Both in [17] and [23], 2 × 2 patches were used to show that 2 × 2 FoE improves over pairwise models significantly.”
- Distributed message passing for large scale graphical models (2011, background): “Here we focus on message passing algorithms which have proven very effective to solve vision tasks such as super-resolution [3], stereo reconstruction [26], segmentation [15], denoising [13], and inpainting [16].”