#### Filter Results:

- Full text PDF available (14)

#### Publication Year

2011

2017

- This year (3)
- Last 5 years (13)
- Last 10 years (15)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Mark Everingham, S. M. Ali Eslami, Luc Van Gool, Christopher K. I. Williams, John M. Winn, Andrew Zisserman
- International Journal of Computer Vision
- 2014

The Pascal Visual Object Classes (VOC) challenge consists of two components: (i) a publicly available dataset of images together with ground truth annotation and standardised evaluation software; and (ii) an annual competition and workshop. There are five challenges: classification, detection, segmentation, action classification, and person layout. In this… (More)

- S. M. Ali Eslami, Nicolas Heess, Christopher K. I. Williams, John M. Winn
- International Journal of Computer Vision
- 2012

A good model of object shape is essential in applications such as segmentation, detection, inpainting and graphics. For example, when performing segmentation, local constraints on the shapes can help where object boundaries are noisy or unclear, and global constraints can resolve ambiguities where background clutter looks similar to parts of the objects. In… (More)

- S. M. Ali Eslami, Nicolas Heess, +4 authors Geoffrey E. Hinton
- NIPS
- 2016

We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use… (More)

A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods on several datasets, including… (More)

The Shape Boltzmann Machine (SBM) [1] has recently been introduced as a stateof-the-art model of foreground/background object shape. We extend the SBM to account for the foreground object’s parts. Our new model, the Multinomial SBM (MSBM), can capture both local and global statistics of part shapes accurately. We combine the MSBM with an appearance model to… (More)

- S. M. Ali Eslami, Daniel Tarlow, Pushmeet Kohli, John M. Winn
- NIPS
- 2014

Representation. Let mout be the outgoing message and min the set of incoming messages. • Represent the outgoing message mout by a vector of real valued numbers rout. • Each set of incoming messages min is represented in two ways: – Regression parameterization denoted by rin (e.g. concatenation of message parameters), – Tree parameterization denoted by tin… (More)

- Nicolas Heess, Dhruva TB, +9 authors David Silver
- ArXiv
- 2017

The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular solution, or to derive it from demonstration data. In this paper explore how a rich environment can help to promote the… (More)

- Wittawat Jitkrittum, Arthur Gretton, +4 authors Zoltán Szabó
- UAI
- 2015

We propose an efficient nonparametric strategy for learning a message operator in expectation propagation (EP), which takes as input the set of incoming messages to a factor node, and produces an outgoing message as output. This learned operator replaces the multivariate integral required in classical EP, which may not have an analytic expression. We use… (More)

- Varun Jampani, S. M. Ali Eslami, Daniel Tarlow, Pushmeet Kohli, John M. Winn
- AISTATS
- 2015

Generative models provide a powerful framework for probabilistic reasoning. However, in many domains their use has been hampered by the practical difficulties of inference. This is particularly the case in computer vision, where models of the imaging process tend to be large, loopy and layered. For this reason bottom-up conditional models have traditionally… (More)

- Wittawat Jitkrittum, Arthur Gretton, +4 authors Zoltán Szabó
- 2015

We propose an efficient nonparametric strategy for learning a message operator in expectation propagation (EP), which takes as input the set of incoming messages to a factor node, and produces an outgoing message as output. This learned operator replaces the multivariate integral required in classical EP, which may not have an analytic expression. We use… (More)