Skip to main content

Research Repository

Advanced Search

All Outputs (5770)

SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM (2025)
Presentation / Conference Contribution
Chen, S., Zhang, H., Atapour-Abarghouei, A., & Shum, H. P. H. (2025, February). SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM. Presented at 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, Arizona

Image inpainting aims to repair a partially damaged image based on the information from known regions of the images. Achieving semantically plausible inpainting results is particularly challenging because it requires the reconstructed regions to exhi... Read More about SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM.

Human Intracranial EEG Biometric Identification (2025)
Presentation / Conference Contribution
Belay, B., & Katsigiannis, S. (2025, July). Human Intracranial EEG Biometric Identification. Presented at International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE EMBC), Copenhagen, Denmark

Composing for AI Voice Model Choir (2025)
Presentation / Conference Contribution
Collins, N. (2025, June). Composing for AI Voice Model Choir. Presented at International Computer Music Conference, Boston

The rapid growth of generative AI capability has not left singing voice synthesis and voice transformation untouched. This paper details compositional experiments in the use of AI voice conversion models outside of their normal intended purpose. Deep... Read More about Composing for AI Voice Model Choir.

Compiler support for semi-manual AoS-to-SoA conversions with data views (2025)
Presentation / Conference Contribution
Radtke, P., & Weinzierl, T. (2024, September). Compiler support for semi-manual AoS-to-SoA conversions with data views. Presented at PPAM 2024 - 15th International Conference on Parallel Processing & Applied Mathematics, Ostrava, Czech Republic

The C programming language and its cousins such as C++ stipulate the static storage of sets of structured data: Developers have to commit to one, invariant data model -- typically a structure-of-arrays (SoA) or an array-of-structs (AoS) -- unles... Read More about Compiler support for semi-manual AoS-to-SoA conversions with data views.

Semi-supervised Object-Wise Anomaly Detection for Firearm and Firearm Component Detection in X-ray Security Imagery (2025)
Presentation / Conference Contribution
Gaus, Y. F. A., Isaac-Medina, B. K. S., Bhowmik, N., Lam, Y. T., & Breckon, T. P. (2025, June). Semi-supervised Object-Wise Anomaly Detection for Firearm and Firearm Component Detection in X-ray Security Imagery. Presented at 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, Tennessee, USA

FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment (2025)
Presentation / Conference Contribution
Han, R., Zhou, K., Atapour-Abarghouei, A., Liang, X., & Shum, H. P. H. (2025, June). FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment. Presented at Proceedings of the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025, Music City Center, Nashville TN

Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep learning approaches often operate as black boxes and are vulnerable to s... Read More about FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment.

Quant Hub seminar: Fifteen years of Pupil Premium policy in England. What have we learned from Pupil Parent Matched Data (PPMD)? (2025)
Presentation / Conference Contribution
Siddiqui, N. (2025, March). Quant Hub seminar: Fifteen years of Pupil Premium policy in England. What have we learned from Pupil Parent Matched Data (PPMD)?. Presented at Quant Hub seminar, Oxford ,15 Norham Gardens

The introduction and nationwide implementation of the Pupil Premium policy in 2011 was a major policy initiative by the then Coalition Government to address socio-economic segregation between schools in England, and reduce the persistent attainment g... Read More about Quant Hub seminar: Fifteen years of Pupil Premium policy in England. What have we learned from Pupil Parent Matched Data (PPMD)?.

An Integrated Stacked Sparse Autoencoder and CNN-BLSTM Model for Ultra-Short-Term Wind Power Forecasting with Advanced Feature Learning (2025)
Presentation / Conference Contribution
Liu, J., Kazemtabrizi, B., Du, H., Matthews, P., & Sun, H. (2024, November). An Integrated Stacked Sparse Autoencoder and CNN-BLSTM Model for Ultra-Short-Term Wind Power Forecasting with Advanced Feature Learning. Presented at 50th Annual Conference of the IEEE Industrial Electronics Society, Chicago, USA

With the increasing integration of renewable energy sources into the power grid, accurate and reliable ultra-short-term forecasting of wind power is critical for optimizing grid stability and energy efficiency, especially for a highly dynamic and var... Read More about An Integrated Stacked Sparse Autoencoder and CNN-BLSTM Model for Ultra-Short-Term Wind Power Forecasting with Advanced Feature Learning.

Multi-modal Dynamic Point Cloud Geometric Compression Based on Bidirectional Recurrent Scene Flow* (2025)
Presentation / Conference Contribution
Nan, F., Li, F., Wang, Z., Tam, G. K. L., Jiang, Z., DongZheng, D., & Yang, B. (2025, April). Multi-modal Dynamic Point Cloud Geometric Compression Based on Bidirectional Recurrent Scene Flow*. Presented at ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India

Deep learning methods have recently shown significant promise in compressing the geometric features of point clouds. However, challenges arise when consecutive point clouds contain holes, resulting in incomplete information that complicates motion es... Read More about Multi-modal Dynamic Point Cloud Geometric Compression Based on Bidirectional Recurrent Scene Flow*.

Synergistic Reinforcement Learning Models for Pedestrian-Friendly Traffic Signal Control (2025)
Presentation / Conference Contribution
Chen, D., Hu, J., Zhang, H., & Chen, B. (2025, June). Synergistic Reinforcement Learning Models for Pedestrian-Friendly Traffic Signal Control. Presented at 2025 European Control Conference (ECC), Thessaloniki, Greece

Traffic signal control is essential for managing urban traffic, reducing congestion, and minimizing environmental impact by optimizing both vehicular and pedestrian flow. This paper investigates the application of Reinforcement Learning (RL) in traff... Read More about Synergistic Reinforcement Learning Models for Pedestrian-Friendly Traffic Signal Control.

Integrated Satellite-Terrestrial Network for Smart Grid Communications in 6G Era (2025)
Presentation / Conference Contribution
Bisu, A. A., Sun, H., & Gallant, A. (2025, January). Integrated Satellite-Terrestrial Network for Smart Grid Communications in 6G Era. Presented at 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC), University of Nevada, Las Vegas, USA

In this work, we developed and proposed a real testbed with Integrated Satellite-Terrestrial Network (ISTN) scenario. This topology was used to measure the actual parameters that were used as the Smart Grid (SG) Quality of Service (QoS) metrics. Perf... Read More about Integrated Satellite-Terrestrial Network for Smart Grid Communications in 6G Era.

Lo stato solido e la nuova mappa della fisica (2025)
Presentation / Conference Contribution
Martin, J. D. (2024, September). Lo stato solido e la nuova mappa della fisica. Presented at XLIV Congresso Nazionale Sisfa, Firenze

Neither solid state nor condensed matter physics existed at the end of World War II. Physical problems related to the properties of materials, of course, have a much longer history, but the physics community was not yet subdivided in a way that recog... Read More about Lo stato solido e la nuova mappa della fisica.

Coordination Mechanisms in AI Development: Practitioner Experiences on Integrating UX Activities (2025)
Presentation / Conference Contribution
Bruun, A., Van Berkel, N., Raptis, D., & Law, E. L.-C. (2025, April). Coordination Mechanisms in AI Development: Practitioner Experiences on Integrating UX Activities. Presented at CHI 2025 (Conference on Human Factors in Computing Systems), Yokohama, Japan

Software development relies on collaboration and alignment between a variety of roles, including software developers and user experience designers. The increasing focus on artificial intelligence in today's development projects has given rise to new... Read More about Coordination Mechanisms in AI Development: Practitioner Experiences on Integrating UX Activities.

Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient (2025)
Presentation / Conference Contribution
Dinh, V., Ho, L., & Nguyen, C. (2024, December). Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient. Presented at The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada

Weather Impact on DER Long-term Performance: A Formal Verification Approach (2025)
Presentation / Conference Contribution
Santana, M. A., Stefanakos, I., Fang, X., Garg, A., Sun, H., & Osman, A. (2024, November). Weather Impact on DER Long-term Performance: A Formal Verification Approach. Presented at 2024 IEEE PES Innovative Smart Grid Technologies - Asia (ISGT Asia), Bangalore, India

Distributed energy resources (DERs), such as solar photovoltaic (PV) panels, are essential to modern energy systems, providing resilience and producing clean, local energy. However, their long-term performance is vulnerable to environmental factors,... Read More about Weather Impact on DER Long-term Performance: A Formal Verification Approach.

Energy Self-Sufficiency Assessment of a Novel Low-Light Enhanced Photovoltaic Model in the Residential Sector (2025)
Presentation / Conference Contribution
Celis, A. A., Sun, H., Groves, C., & Harsh, P. (2024, October). Energy Self-Sufficiency Assessment of a Novel Low-Light Enhanced Photovoltaic Model in the Residential Sector. Presented at 2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024, Phoenix, AZ, USA

Increased photovoltaic (PV) penetration in the low-voltage residential sector highlights the intrinsic problems with Silicon PV (Si-PV) in seasonal power output fluctuations. Exploring the potential performance of emerging PV materials, such as Perov... Read More about Energy Self-Sufficiency Assessment of a Novel Low-Light Enhanced Photovoltaic Model in the Residential Sector.

A robust Bayesian model to quantify and adjust for study quality and conflict of interest in meta-analyses (2025)
Presentation / Conference Contribution
Troffaes, M. C. M., Casini, L., Landes, J., & Sahlin, U. (2025, July). A robust Bayesian model to quantify and adjust for study quality and conflict of interest in meta-analyses. Presented at 14th International Symposium on Imprecise Probabilities: Theories and Applications, Bielefeld, Germany

Meta-analyses are vital for synthesizing evidence in medical research, but conflicts of interest can introduce research bias, undermining the reliability of the synthesized findings. This paper proposes a new robust Bayesian meta-analysis model. The... Read More about A robust Bayesian model to quantify and adjust for study quality and conflict of interest in meta-analyses.