1 code implementation • 7 Jul 2023 • Zhongliang Jiang, Yuan Bi, Mingchuan Zhou, Ying Hu, Michael Burke, Nassir Navab
The results demonstrated that the proposed advanced framework can robustly work on a variety of seen and unseen phantoms as well as in-vivo human carotid data.
no code implementations • 17 Sep 2021 • Emma Perkins, Chiranjibi Sitaula, Michael Burke, Faezeh Marzbanrad
In particular, physiological monitoring methods such as Electroencephalography (EEG) are intrusive to drivers; while behavioural monitoring is least robust, affected by external factors such as lighting, as well as being subject to privacy concerns.
no code implementations • 13 Sep 2021 • Miguel Jaques, Martin Asenov, Michael Burke, Timothy Hospedales
This paper introduces V-SysId, a novel method that enables simultaneous keypoint discovery, 3D system identification, and extrinsic camera calibration from an unlabeled video taken from a static camera, using only the family of equations of motion of the object of interest as weak supervision.
no code implementations • 2 May 2021 • Michael Burke, Subramanian Ramamoorthy
Data association is a fundamental component of effective multi-object tracking.
no code implementations • 30 Nov 2020 • Tatiana Lopez-Guevara, Michael Burke, Nicholas K. Taylor, Kartic Subr
This distribution can then be used as a policy certificate in downstream applications.
no code implementations • 18 Aug 2020 • Todor Davchev, Kevin Sebastian Luck, Michael Burke, Franziska Meier, Stefan Schaal, Subramanian Ramamoorthy
Dynamic Movement Primitives (DMP) are a popular way of extracting such policies through behaviour cloning (BC) but can struggle in the context of insertion.
1 code implementation • 3 Aug 2020 • Michael Burke, Kartic Subr, Subramanian Ramamoorthy
Humans can easily reason about the sequence of high level actions needed to complete tasks, but it is particularly difficult to instil this ability in robots trained from relatively few examples.
no code implementations • CVPR 2021 • Miguel Jaques, Michael Burke, Timothy Hospedales
Learning low-dimensional latent state space dynamics models has been a powerful paradigm for enabling vision-based planning and learning for control.
no code implementations • 4 Feb 2020 • Michael Burke, Katie Lu, Daniel Angelov, Artūras Straižys, Craig Innes, Kartic Subr, Subramanian Ramamoorthy
This work considers the inverse problem, where the goal of the task is unknown, and a reward function needs to be inferred from exploratory example demonstrations provided by a demonstrator, for use in a downstream informative path-planning policy.
no code implementations • 30 Jan 2020 • Mamuku Mokuwe, Michael Burke, Anna Sergeevna Bosman
This is achieved by a sampling-based approach to model perturbations that seeks to localise salient regions of an image to the black-box model.
no code implementations • 10 Dec 2019 • Mkhuseli Ngxande, Jules-Raymond Tapamo, Michael Burke
Our framework improves Convolutional Neural Network (CNN) trained for prediction by using Generative Adversarial networks (GAN) for targeted data augmentation based on a population bias visualisation strategy that groups faces with similar facial attributes and highlights where the model is failing.
1 code implementation • 29 Nov 2019 • Todor Davchev, Michael Burke, Subramanian Ramamoorthy
Context plays a significant role in the generation of motion for dynamic agents in interactive environments.
no code implementations • 31 Jul 2019 • Yordan Hristov, Daniel Angelov, Michael Burke, Alex Lascarides, Subramanian Ramamoorthy
Learning from demonstration is an effective method for human users to instruct desired robot behaviour.
no code implementations • 18 Jul 2019 • Daniel Angelov, Yordan Hristov, Michael Burke, Subramanian Ramamoorthy
Robot control policies for temporally extended and sequenced tasks are often characterized by discontinuous switches between different local dynamics.
1 code implementation • 9 Jul 2019 • Michael Burke, Yordan Hristov, Subramanian Ramamoorthy
This paper introduces switching density networks, which rely on a categorical reparametrisation for hybrid system identification.
1 code implementation • ICLR 2020 • Miguel Jaques, Michael Burke, Timothy Hospedales
Our approach significantly outperforms related unsupervised methods in long-term future frame prediction of systems with interacting objects (such as ball-spring or 3-body gravitational systems), due to its ability to build dynamics into the model as an inductive bias.
no code implementations • 23 Apr 2019 • Mkhuseli Ngxande, Jule-Raymond Tapamo, Michael Burke
Convolutional Neural Networks (CNNs) have been used successfully across a broad range of areas including data mining, object detection, and in business.
no code implementations • 6 Mar 2019 • Mkhuseli Ngxande, Jules-Raymond Tapamo, Michael Burke
In this paper, we investigate the use of depthwise separable convolutions to reduce training time while maintaining data generation performance.
no code implementations • 27 Feb 2019 • Michael Burke, Svetlin Penkov, Subramanian Ramamoorthy
This work introduces an approach to learning hybrid systems from demonstrations, with an emphasis on extracting models that are explicitly verifiable and easily interpreted by robot operators.
no code implementations • 19 Jun 2017 • Michael Burke, Siyabonga Mbonambi, Purity Molala, Raesetje Sefala
A great deal of work aims to discover large general purpose models of image interest or memorability for visual search and information retrieval.
1 code implementation • 20 May 2014 • Michael Burke, Joan Lasenby
This model is combined with measurements of the human head and hand positions, using recursive Bayesian estimation to incorporate temporal information.