#### Filter Results:

- Full text PDF available (12)

#### Publication Year

2007

2017

- This year (1)
- Last 5 years (4)
- Last 10 years (14)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

- Lubor Ladicky, Christopher Russell, Pushmeet Kohli, Philip H. S. Torr
- 2009 IEEE 12th International Conference on…
- 2009

Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It is well known that each quantisation has its fair share of pros and cons; and the existence of a common optimal quantisation level suitable for all object categories is highly… (More)

Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the CRF. We show how they can be readily optimised using standard graph cut algorithms at little extra… (More)

- Lubor Ladicky, Paul Sturgess, +4 authors Philip H. S. Torr
- International Journal of Computer Vision
- 2011

The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly… (More)

- Lubor Ladicky, Paul Sturgess, +4 authors Philip H. S. Torr
- BMVC
- 2010

The problems of object class segmentation [2], which assigns an object label such as road or building to every pixel in the image and dense stereo reconstruction, in which every pixel within an image is labelled with a disparity [1], are well suited for being solved jointly. Both approaches formulate the problem of providing a correct labelling of an image… (More)

- Lubor Ladicky, Christopher Russell, Pushmeet Kohli, Philip H. S. Torr
- IEEE Transactions on Pattern Analysis and Machine…
- 2014

This paper makes two contributions: the first is the proposal of a new model-The associative hierarchical random field (AHRF), and a novel algorithm for its optimization; the second is the application of this model to the problem of semantic segmentation. Most methods for semantic segmentation are formulated as a labeling problem for variables that might… (More)

- Lubor Ladicky, Christopher Russell, Pushmeet Kohli, Philip H. S. Torr
- International Journal of Computer Vision
- 2012

The Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is generally thought to be the only case that is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the CRF. We show how they can be readily optimised using… (More)

- Karteek Alahari, Christopher Russell, Philip H. S. Torr
- 2010 IEEE Computer Society Conference on Computer…
- 2010

Conditional Random Field models have proved effective for several low-level computer vision problems. Inference in these models involves solving a combinatorial optimization problem, with methods such as graph cuts, belief propagation. Although several methods have been proposed to learn the model parameters from training data, they suffer from various… (More)

- Stewart Taggart, Geoffrey James, ZhaoYang Dong, Christopher Russell
- Proceedings of the IEEE
- 2012

| In this paper, we argue that Asia’s unique geography, abundant low-emission energy resources, rapid economic growth, and rising energy demands merit consideration of a Pan-Asian Energy Infrastructure. In our study, we focus on development of wind and solar resources in Australia, China, Mongolia, and Vietnam as the potential foundation for an electricity… (More)

Markov Networks are widely used through out computer vision and machine learning. An important subclass are the Associative Markov Networks which are used in a wide variety of applications. For these networks a good approximate minimum cost solution can be found efficiently using graph cut based move making algorithms such as alpha-expansion. Recently a… (More)