Submodular extensions of an energy function can be used to efficiently compute approximate marginals via variational inference. The accuracy of the m…

Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. Unsup…

The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare…

Space-based transit search missions such as Kepler are collecting large numbers of stellar light curves of unprecedented photometric precision and ti…

We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person's appearance to improve pose estimati…

In this paper we propose a family of tractable kernels that is dense in the family of bounded positive semi-definite functions (i.e. can approximate …

We introduce a new approach to solving path-finding problems under uncertainty by representing them as probabilistic models and applying domain-indep…

Face recognition performance evaluation has traditionally focused on one-to-one verification, popularized by the Labeled Faces in the Wild dataset fo…

We develop a technique for generalising from data in which models are samplers represented as program text. We establish encouraging empirical result…

State-of-the-art methods for unsupervised representation learning can train well the first few layers of standard convolutional neural networks, but …

Bayesian optimization has demonstrated impressive success in finding the optimum location $x^{*}$ and value $f^{*}=f(x^{*})=\max_{x\in\mathcal{X}}f(x…

An object can be seen as a geometrically organized set of interrelated parts. A system that makes explicit use of these geometric relationships to re…

Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for eg…

We propose Radial Bayesian Neural Networks: a variational distribution for mean field variational inference (MFVI) in Bayesian neural networks that i…

The task of decision-making under uncertainty is daunting, especially for problems which have significant complexity. Healthcare policy makers across…

We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module t…

We consider the task of learning to estimate human pose in still images. In order to avoid the high cost of full supervision, we propose to use a div…

Although DiffSharp started as a vehicle for conducting research at the intersection of AD and machine learning, it has grown into an industrial-strength AD solution for F# in particular and the cross-platform .NET platform in general. Its functional…

DiffSharp is an algorithmic differentiation or automatic differentiation (AD) library for the .NET ecosystem, which is targeted by the C# and F# lang…

Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cum…

The success of Deep Learning and its potential use in many important safety- critical applications has motivated research on formal verification of N…

By signing up you accept our content policy

Already have an account? Sign in

No a member yet? Create an account