Outputs (236)

Monocular Segment-Wise Depth: Monocular Depth Estimation Based on a Semantic Segmentation Prior (2019)
Presentation / Conference Contribution
Atapour-Abarghouei, A., & Breckon, T. (2019, September). Monocular Segment-Wise Depth: Monocular Depth Estimation Based on a Semantic Segmentation Prior. Presented at IEEE International Conference on Image Processing, Taipei, Taiwen

Monocular depth estimation using novel learning-based approaches has recently emerged as a promising potential alternative to more conventional 3D scene capture technologies within real-world scenarios. Many such solutions often depend on large quant... Read More about Monocular Segment-Wise Depth: Monocular Depth Estimation Based on a Semantic Segmentation Prior.

Chinese Text Project: a dynamic digital library of premodern Chinese (2019)
Journal Article
Sturgeon, D. (2021). Chinese Text Project: a dynamic digital library of premodern Chinese. Digital Scholarship in the Humanities, 36(S1), i101-i112. https://doi.org/10.1093/llc/fqz046

This article presents technical approaches and innovations in digital library design developed during the design and implementation of the Chinese Text Project, a widely-used, large-scale full-text digital library of premodern Chinese writing. By lev... Read More about Chinese Text Project: a dynamic digital library of premodern Chinese.

Relating the bisection width of dual-port, server-centric datacenter networks and the solution of edge-isoperimetric problems in graphs (2019)
Journal Article
Erickson, A., Navaridas, J., & Stewart, I. (2020). Relating the bisection width of dual-port, server-centric datacenter networks and the solution of edge-isoperimetric problems in graphs. Journal of Computer and System Sciences, 108, 10-28. https://doi.org/10.1016/j.jcss.2019.08.005

Stellar datacenter networks are a recent generic construction designed to transform a base-graph into a dual-port, server-centric datacenter network. We prove that the S-bisection width of any stellar datacenter network can be obtained from the solut... Read More about Relating the bisection width of dual-port, server-centric datacenter networks and the solution of edge-isoperimetric problems in graphs.

Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling (2019)
Presentation / Conference Contribution
Wang, X., Wang, K., Yang, B., Li, F. W., & Liang, X. (2019, December). Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling. Presented at 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan

Blind image quality metrics have achieved significant improvement on traditional 2D image dataset, yet still being insufficient for evaluating synthesized images generated from depth-image-based rendering. The geometric distortions in synthesized ima... Read More about Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling.

Deleting edges to restrict the size of an epidemic in temporal networks (2019)
Presentation / Conference Contribution
Enright, J., Meeks, K., Mertzios, G., & Zamaraev, V. (2019, August). Deleting edges to restrict the size of an epidemic in temporal networks. Presented at 44th International Symposium on Mathematical Foundations of Computer Science (MFCS), Aachen, Germany

Spreading processes on graphs are a natural model for a wide variety of real-world phenomena, including information or behaviour spread over social networks, biological diseases spreading over contact or trade networks, and the potential flow of good... Read More about Deleting edges to restrict the size of an epidemic in temporal networks.

Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling (2019)
Journal Article
Wang, H., Ho, E. S., Shum, H. P., & Zhu, Z. (2021). Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling. IEEE Transactions on Visualization and Computer Graphics, 27(1), 216 - 227. https://doi.org/10.1109/tvcg.2019.2936810

Data-driven modeling of human motions is ubiquitous in computer graphics and vision applications. Such problems can be approached by deep learning on a large amount data. However, existing methods can be sub-optimal for two reasons. First, skeletal i... Read More about Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling.

Temporal vertex cover with a sliding time window (2019)
Journal Article
Akrida, E., Mertzios, G., Spirakis, P., & Zamaraev, V. (2020). Temporal vertex cover with a sliding time window. Journal of Computer and System Sciences, 107, 108-123. https://doi.org/10.1016/j.jcss.2019.08.002

Modern, inherently dynamic systems are usually characterized by a network structure which is subject to discrete changes over time. Given a static underlying graph, a temporal graph can be represented via an assignment of a set of integer time-labels... Read More about Temporal vertex cover with a sliding time window.

Colouring H-free graphs of bounded diameter (2019)
Presentation / Conference Contribution
Martin, B., Paulusma, D., & Smith, S. (2019, August). Colouring H-free graphs of bounded diameter. Presented at MFCS 2019, Aachen, Germany

The Colouring problem is to decide if the vertices of a graph can be coloured with at most k colours for an integer k, such that no two adjacent vertices are coloured alike. A graph G is H-free if G does not contain H as an induced subgraph. It is kn... Read More about Colouring H-free graphs of bounded diameter.

On the stability and instability of finite dynamical systems with prescribed interaction graphs (2019)
Journal Article
Gadouleau, M. (2019). On the stability and instability of finite dynamical systems with prescribed interaction graphs. Electronic Journal of Combinatorics, 26(3), Article P3.32

The dynamical properties of finite dynamical systems (FDSs) have been investigated in the context of coding theoretic problems, such as network coding, and in the context of hat games, such as the guessing game and Winkler's hat game. The instability... Read More about On the stability and instability of finite dynamical systems with prescribed interaction graphs.

Using Variable Natural Environment Brain-Computer Interface Stimuli for Real-time Humanoid Robot Navigation (2019)
Presentation / Conference Contribution
Aznan, N., Connolly, J., Al Moubayed, N., & Breckon, T. (2019, May). Using Variable Natural Environment Brain-Computer Interface Stimuli for Real-time Humanoid Robot Navigation. Presented at 2019 IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada

This paper addresses the challenge of humanoid robot teleoperation in a natural indoor environment via a Brain-Computer Interface (BCI). We leverage deep Convolutional Neural Network (CNN) based image and signal understanding to facilitate both real-... Read More about Using Variable Natural Environment Brain-Computer Interface Stimuli for Real-time Humanoid Robot Navigation.