Skip to main content

Research Repository

Advanced Search

All Outputs (53)

Beyond Syntax: How Do LLMs Understand Code? (2025)
Presentation / Conference Contribution
North, M., Atapour-Abarghouei, A., & Bencomo, N. (2025, April). Beyond Syntax: How Do LLMs Understand Code?. Presented at 2025 IEEE/ACM International Conference on Software Engineering ICSE, Ottawa , Canada

Within software engineering research, Large Language Models (LLMs) are often treated as 'black boxes', with only their inputs and outputs being considered. In this paper, we take a machine interpretability approach to examine how LLMs internally repr... Read More about Beyond Syntax: How Do LLMs Understand Code?.

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.

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.

Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving (2025)
Presentation / Conference Contribution
E, W., Yuan, C., Sun, Y., Gaus, Y., Atapour-Abarghouei, A., & Breckon, T. (2025, May). Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving. Presented at IEEE International Conference on Robotics and Automation (ICRA), Atlanta, USA

We present Dur360BEV, a novel spherical camera autonomous driving dataset equipped with a high-resolution 128-channel 3D LiDAR and a RTK-refined GNSS/INS system, along with a benchmark architecture designed to generate Bird-Eye-View (BEV) maps using... Read More about Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving.

Deep Learning-Enhanced Visual Monitoring in Hazardous Underwater Environments with a Swarm of Micro-Robots (2025)
Presentation / Conference Contribution
Chen, S., He, Y., Lennox, B., Arvin, F., & Atapour-Abarghouei, A. (2025, May). Deep Learning-Enhanced Visual Monitoring in Hazardous Underwater Environments with a Swarm of Micro-Robots. Presented at IEEE International Conference on Robotics & Automation, Atlanta, USA

Long-term monitoring and exploration of extreme environments, such as underwater storage facilities, is costly, labor-intensive, and hazardous. Automating this process with low-cost, collaborative robots can greatly improve efficiency. These robots c... Read More about Deep Learning-Enhanced Visual Monitoring in Hazardous Underwater Environments with a Swarm of Micro-Robots.

MxT: Mamba x Transformer for Image Inpainting (2024)
Presentation / Conference Contribution
Chen, S., Atapour-Abarghouei, A., Zhang, H., & Shum, H. P. H. (2024, November). MxT: Mamba x Transformer for Image Inpainting. Presented at BMVC 2024: The 35th British Machine Vision Conference, Glasgow, UK

Image inpainting, or image completion, is a crucial task in computer vision that aims to restore missing or damaged regions of images with semantically coherent content. This technique requires a precise balance of local texture replication and globa... Read More about MxT: Mamba x Transformer for Image Inpainting.

Insights from the Use of Previously Unseen Neural Architecture Search Datasets (2024)
Presentation / Conference Contribution
Geada, R., Towers, D., Forshaw, M., Atapour-Abarghouei, A., & Mcgough, A. S. (2024, June). Insights from the Use of Previously Unseen Neural Architecture Search Datasets. Presented at IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), Seattle, WA

The boundless possibility of neural networks which can be used to solve a problem-each with different performance leads to a situation where a Deep Learning expert is required to identify the best neural network. This goes against the hope of removin... Read More about Insights from the Use of Previously Unseen Neural Architecture Search Datasets.

Code Gradients: Towards Automated Traceability of LLM-Generated Code (2024)
Presentation / Conference Contribution
North, M., Atapour-Abarghouei, A., & Bencomo, N. (2024, June). Code Gradients: Towards Automated Traceability of LLM-Generated Code. Presented at 2024 IEEE 32nd International Requirements Engineering Conference (RE), Reykjavik, Iceland

Large language models (LLMs) have recently seen huge growth in capability and usage. Within software engineering, LLMs are increasingly being used by developers to generate code. Code generated by an LLM can be seen essentially a continuous mapping f... Read More about Code Gradients: Towards Automated Traceability of LLM-Generated Code.

Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics (2024)
Presentation / Conference Contribution
Yucer, S., Abarghouei, A. A., Al Moubayed, N., & Breckon, T. P. (2024, June). Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics. Presented at 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan

Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces. Despite these challenges... Read More about Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics.

Diagnosis of multiple sclerosis by detecting asymmetry within the retina using a similarity-based neural network (2024)
Journal Article
Bolton, R. C., Kafieh, R., Ashtari, F., & Atapour-Abarghouei, A. (2024). Diagnosis of multiple sclerosis by detecting asymmetry within the retina using a similarity-based neural network. IEEE Access, 12, 62975-62985. https://doi.org/10.1109/access.2024.3395995

Multiple sclerosis (MS) is a chronic neurological disorder that targets the central nervous system, causing demyelination and neural disruption, which can include retinal nerve damage leading to visual disturbances. The purpose of this study is to de... Read More about Diagnosis of multiple sclerosis by detecting asymmetry within the retina using a similarity-based neural network.

FEGR: Feature Enhanced Graph Representation Method for Graph Classification (2024)
Presentation / Conference Contribution
Abushofa, M., Atapour-Abarghouei, A., Forshaw, M., & McGough, A. S. (2023, November). FEGR: Feature Enhanced Graph Representation Method for Graph Classification. Presented at 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Kusadasi, Turkey

Graph representation plays a key role in graph analytics to perform a variety of downstream machine-learning tasks. This paper presents a novel method for extracting expressive graph representation based on a combination of statistics captured from a... Read More about FEGR: Feature Enhanced Graph Representation Method for Graph Classification.

HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention (2024)
Journal Article
Chen, S., Atapour-Abarghouei, A., & Shum, H. P. H. (2024). HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention. IEEE Transactions on Multimedia, 26, 7649-7660. https://doi.org/10.1109/TMM.2024.3369897

Existing image inpainting methods leverage convolution-based downsampling approaches to reduce spatial dimensions. This may result in information loss from corrupted images where the available information is inherently sparse, especially for the scen... Read More about HINT: High-quality INpainting Transformer with Mask-Aware Encoding and Enhanced Attention.

Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery (2023)
Presentation / Conference Contribution
Gaus, Y., Bhowmik, N., Issac-Medina, B., Atapour-Abarghouei, A., Shum, H., & Breckon, T. (2023, June). Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery. Presented at IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, Vancouver, BC

Anomaly detection is a classical problem within automated visual surveillance, namely the determination of the normal from the abnormal when operational data availability is highly biased towards one class (normal) due to both insufficient sample siz... Read More about Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery.

INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network (2023)
Journal Article
Chen, S., Atapour-Abarghouei, A., Ho, E. S., & Shum, H. P. (2023). INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network. Software impacts, 17, Article 100517. https://doi.org/10.1016/j.simpa.2023.100517

We present a software that predicts non-cleft facial images for patients with cleft lip, thereby facilitating the understanding, awareness and discussion of cleft lip surgeries. To protect patients’ privacy, we design a software framework using image... Read More about INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network.

Predicting the Performance of a Computing System with Deep Networks (2023)
Presentation / Conference Contribution
Cengiz, M., Forshaw, M., Atapour-Abarghouei, A., & McGough, A. S. (2023, April). Predicting the Performance of a Computing System with Deep Networks. Presented at 2023 ACM/SPEC International Conference on Performance Engineering (ICPE ’23), Coimbra, Portugal

Predicting the performance and energy consumption of computing hardware is critical for many modern applications. This will inform procurement decisions, deployment decisions, and autonomic scaling. Existing approaches to understanding the performanc... Read More about Predicting the Performance of a Computing System with Deep Networks.

Differentiating Glaucomatous Optic Neuropathy from Non-Glaucomatous Optic Neuropathies Using Deep Learning Algorithms (2023)
Journal Article
Vali, M., Mohammadi, M., Zarei, N., Samadi, M., Atapour-Abarghouei, A., Supakontanasan, W., Suwan, Y., Subramanian, P. S., Miller, N. R., Kafieh, R., & Fard, M. A. (2023). Differentiating Glaucomatous Optic Neuropathy from Non-Glaucomatous Optic Neuropathies Using Deep Learning Algorithms. American Journal of Ophthalmology, 252, 1-8. https://doi.org/10.1016/j.ajo.2023.02.016

Purpose : A deep learning framework to differentiate glaucomatous optic disc changes (GON) from non-glaucomatous optic neuropathy-related disc changes (NGON). Design : Cross-sectional study. Method : A deep-learning system was trained, validated, and... Read More about Differentiating Glaucomatous Optic Neuropathy from Non-Glaucomatous Optic Neuropathies Using Deep Learning Algorithms.

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification (2022)
Presentation / Conference Contribution
Bevan, P., & Atapour-Abarghouei, A. (2022, July). Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification. Presented at The 39th International Conference on Machine Learning (ICML 2022), Baltimore, MD

Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma and other skin lesions, but prediction irregularities due to biases seen within the training data are an issue that should be addressed... Read More about Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification.

A Feasibility Study on Image Inpainting for Non-cleft Lip Generation from Patients with Cleft Lip (2022)
Presentation / Conference Contribution
Chen, S., Atapour-Abarghouei, A., Kerby, J., Ho, E. S., Sainsbury, D. C., Butterworth, S., & Shum, H. P. (2022, September). A Feasibility Study on Image Inpainting for Non-cleft Lip Generation from Patients with Cleft Lip. Presented at 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), Ioannina, Greece

A Cleft lip is a congenital abnormality requiring surgical repair by a specialist. The surgeon must have extensive experience and theoretical knowledge to perform surgery, and Artificial Intelligence (AI) method has been proposed to guide surgeons in... Read More about A Feasibility Study on Image Inpainting for Non-cleft Lip Generation from Patients with Cleft Lip.