Computer Science
Welcome to the research outputs of the University of Exeter College of Engineering, Mathematics and Physical Sciences, Department of Computer Science
Recent Submissions
-
Aggregated Sparse Attention for Steering Angle Prediction
(Institute of Electrical and Electronics Engineers Inc., 2018)In this paper, we apply the attention mechanism to autonomous driving for steering angle prediction. We propose the first model, applying the recently introduced sparse attention mechanism to visual domain, as well as the ... -
Continuous Control with a Combination of Supervised and Reinforcement Learning
(Institute of Electrical and Electronics Engineers, 2018)Reinforcement learning methods have recently achieved impressive results on a wide range of control problems. However, especially with complex inputs, they still require an extensive amount of training data in order to ... -
More complexity results about reasoning over (m)CP-nets
(International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2018-07)Aggregating preferences over combinatorial domains has several applications in artificial intelligence. Due to the exponential nature of combinatorial preferences, compact representations are needed, and (m)CP-nets are ... -
Engaging stakeholders in research to address water-energy-food (WEF) nexus challenges
(Springer Verlag, 2018-04-04)The water–energy–food (WEF) nexus has become a popular, and potentially powerful, frame through which to analyse interactions and interdependencies between these three systems. Though the case for transdisciplinary research ... -
Redesign of Industrial Apparatus using Multi-Objective Bayesian Optimisation
(International Conference on Computational Fluid Dynamics, 2018-07)Introduction. Design optimisation using Computational Fluid Dynamics (CFD) often requires extremising multiple (and often conflicting) objectives simultaneously. For instance, a heat exchanger design will require ... -
Unmanned Aerial Vehicles for Disaster Management
(Springer Verlag, 2017)This chapter highlights the communication and network technologies that contribute to UAV disaster management systems, surveys the latest development of UAV-assisted disaster management applications, including early ... -
Tuning the aggressive TCP behavior for highly concurrent HTTP connections in intra-datacenter
(Association for Computing Machinery, 2017-10-27)IEEE Modern data centers host diverse hyper text transfer protocol (HTTP)-based services, which employ persistent transmission control protocol (TCP) connections to send HTTP requests and responses. However, the ON/OFF ... -
A novel infrared video surveillance system using deep learning based techniques
(Springer Verlag (Germany), 2018-04-11)This paper presents a new, practical infrared video based surveillance system, consisting of a resolution-enhanced, automatic target detection/recognition (ATD/R) system that is widely applicable in civilian and military ... -
Dynamic social media affiliations amongst UK politicians
(Elsevier, 2018-02-05)Inter-personal affiliations and coalitions are an important part of politicians’ behaviour, but are often difficult to observe. Since an increasing amount of political communication now occurs online, data from online ... -
The 3D Menpo Facial Landmark Tracking Challenge
(Institute of Electrical and Electronics Engineers (IEEE), 2018-01-23)Recently, deformable face alignment is synonymous to the task of locating a set of 2D sparse landmarks in intensity images. Currently, discriminatively trained Deep Convolutional Neural Networks (DCNNs) are the state-of-the-art ... -
A 3D morphable model learnt from 10,000 faces
(Institute of Electrical and Electronics Engineers (IEEE), 2016-12-12)We present Large Scale Facial Model (LSFM) - a 3D Morphable Model (3DMM) automatically constructed from 9,663 distinct facial identities. To the best of our knowledge LSFM is the largest-scale Morphable Model ever constructed, ... -
A secure collaborative spectrum sensing strategy in cyber-physical systems
(Institute of Electrical and Electronics Engineers (IEEE), 2017-10-30)Cyber-physical systems (CPS) have the great potential to transform people's lives. Smart cities, smart homes, robot assisted living, and intelligent transportation systems are examples of popular CPS systems and applications. ... -
DTCS: An integrated strategy for enhancing data trustworthiness in mobile crowdsourcing
(Institute of Electrical and Electronics Engineers (IEEE), 2018-02-02)IEEE Mobile Crowdsourcing Systems (MCS) are important sources of information for the positioning services in IoT such as gathering location information through employing citizens to participate in data collection. Although ... -
DTRM: A new reputation mechanism to enhance data trustworthiness for high-performance cloud computing
(Elsevier, 2018-02-12)Cloud computing and the mobile Internet have been the two most influential information technology revolutions, which intersect in mobile cloud computing (MCC). The burgeoning MCC enables the large-scale collection and ... -
Structure tensor total variation
(Society for Industrial and Applied Mathematics, 2015-05-07)We introduce a novel generic energy functional that we employ to solve inverse imaging problems within a variational framework. The proposed regularization family, termed as structure tensor total variation (STV), penalizes ... -
Large Scale 3D Morphable Models
(Springer Verlag, 2017-04-08)We present large scale facial model (LSFM)—a 3D Morphable Model (3DMM) automatically constructed from 9663 distinct facial identities. To the best of our knowledge LSFM is the largest-scale Morphable Model ever constructed, ... -
Additional degrees of parallelism within the Adomian decomposition method
(Springer Verlag, 2018)The trend of future massively parallel computer architectures challenges the exploration of additional degrees of parallelism also in the time dimension when solving continuum mechanical partial differential equations. The ... -
On the complexity of mCP-nets
(AAAI Publications, 2016-02)mCP-nets are an expressive and intuitive formalism based on CP-nets to reason about preferences of groups of agents. The dominance semantics of mCP-nets is based on the concept of voting, and different voting schemes give ... -
Oil spill segmentation via adversarial f -divergence learning
(Institute of Electrical and Electronics Engineers, 2018-02-23)We develop an automatic oil spill segmentation method in terms of f-divergence minimization. We exploit fdivergence for measuring the disagreement between the distributions of ground-truth and generated oil spill ... -
The complexity of the nucleolus in compact games
(Association for Computing Machinery (ACM), 2014-12-01)The nucleolus is a well-known solution concept for coalitional games to fairly distribute the total available worth among the players. The nucleolus is known to be NP-hard to compute over compact coalitional games, that ...