Skip to main content

Research Repository

Advanced Search

Dr Amir Atapour-Abarghouei's Outputs (49)

Rank over Class: The Untapped Potential of Ranking in Natural Language Processing (2021)
Presentation / Conference Contribution
Atapour-Abarghouei, A., Bonner, S., & McGough, A. S. (2021, December). Rank over Class: The Untapped Potential of Ranking in Natural Language Processing. Presented at 2021 IEEE International Conference on Big Data (IEEE BigData 2021), Orlando, FL, USA

Text classification has long been a staple within Natural Language Processing (NLP) with applications spanning across diverse areas such as sentiment analysis, recommender systems and spam detection. With such a powerful solution, it is often temptin... Read More about Rank over Class: The Untapped Potential of Ranking in Natural Language Processing.

Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking (2021)
Presentation / Conference Contribution
Carrell, S., & Atapour-Abarghouei, A. (2021, December). Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking. Presented at 2021 IEEE International Conference on Big Data (IEEE BigData 2021), Orlando, FL, USA

The use of mobiles phones when driving has been a major factor when it comes to road traffic incidents and the process of capturing such violations can be a laborious task. Advancements in both modern object detection frameworks and high-performance... Read More about Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking.

On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures (2021)
Presentation / Conference Contribution
Poyser, M., Atapour-Abarghouei, A., & Breckon, T. (2021, January). On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures. Presented at 25th International Conference on Pattern Recognition (ICPR2020), Milan, Italy

Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks. Whilst the reported performance of these a... Read More about On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures.

Volenti non fit injuria: Ransomware and its Victims (2019)
Presentation / Conference Contribution
Atapour-Abarghouei, A., Bonner, S., & McGough, A. S. (2019, December). Volenti non fit injuria: Ransomware and its Victims. Presented at 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA

With the recent growth in the number of malicious activities on the internet, cybersecurity research has seen a boost in the past few years. However, as certain variants of malware can provide highly lucrative opportunities for bad actors, significan... Read More about Volenti non fit injuria: Ransomware and its Victims.

Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions (2019)
Presentation / Conference Contribution
Bonner, S., Atapour-Abarghouei, A., Jackson, P., Brennan, J., Kureshi, I., Theodoropoulos, G., McGough, S., & Obara, B. (2019, December). Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions. Presented at IEEE International Conference on Big Data (Deep Graph Learning: Methodologies and Applications), Los Angeles, CA, USA

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently di... Read More about Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions.

Dealing with Missing Depth: Recent Advances in Depth Image Completion and Estimation (2019)
Book Chapter
Atapour-Abarghouei, A., & Breckon, T. (2019). Dealing with Missing Depth: Recent Advances in Depth Image Completion and Estimation. In P. L. Rosin, Y. Lai, L. Shao, & Y. Liu (Eds.), RGB-D image analysis and processing (15-50). Springer Verlag. https://doi.org/10.1007/978-3-030-28603-3_2

Even though obtaining 3D information has received significant attention in scene capture systems in recent years, there are currently numerous challenges within scene depth estimation which is one of the fundamental parts of any 3D vision system focu... Read More about Dealing with Missing Depth: Recent Advances in Depth Image Completion and Estimation.

Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection (2019)
Presentation / Conference Contribution
Akcay, A., Atapour-Abarghouei, A., & Breckon, T. P. (2019, July). Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection. Presented at Proc. Int. Joint Conference on Neural Networks, Budapest, Hungary

Despite inherent ill-definition, anomaly detection is a research endeavour of great interest within machine learning and visual scene understanding alike. Most commonly, anomaly detection is considered as the detection of outliers within a given data... Read More about Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection.

To complete or to estimate, that is the question: A Multi-Task Depth Completion and Monocular Depth Estimation (2019)
Presentation / Conference Contribution
Atapour-Abarghouei, A., & Breckon, T. P. (2019, September). To complete or to estimate, that is the question: A Multi-Task Depth Completion and Monocular Depth Estimation. Presented at International Conference on 3D Vision, Quebec

Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based model capabl... Read More about To complete or to estimate, that is the question: A Multi-Task Depth Completion and Monocular Depth Estimation.

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.

Multi-Task Regression-based Learning for Autonomous Unmanned Aerial Vehicle Flight Control within Unstructured Outdoor Environments (2019)
Journal Article
Maciel-Pearson, B., Akcay, S., Atapour-Abarghouei, A., Holder, C., & Breckon, T. (2019). Multi-Task Regression-based Learning for Autonomous Unmanned Aerial Vehicle Flight Control within Unstructured Outdoor Environments. IEEE Robotics and Automation Letters, 4(4), 4116-4123. https://doi.org/10.1109/lra.2019.2930496

Increased growth in the global Unmanned Aerial Vehicles (UAV) (drone) industry has expanded possibilities for fully autonomous UAV applications. A particular application which has in part motivated this research is the use of UAV in wide area search... Read More about Multi-Task Regression-based Learning for Autonomous Unmanned Aerial Vehicle Flight Control within Unstructured Outdoor Environments.

Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification (2019)
Presentation / Conference Contribution
Aznan, N., Atapour-Abarghouei, A., Bonner, S., Connolly, J., Al Moubayed, N., & Breckon, T. (2019, December). Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification. Presented at International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary

Despite significant recent progress in the area of Brain-Computer Interface (BCI), there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals in real-world environments. These include, but are not limited to, subj... Read More about Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification.

Generative Adversarial Framework for Depth Filling via Wasserstein Metric, Cosine Transform and Domain Transfer (2019)
Journal Article
Atapour-Abarghouei, A., Akcay, S., de La Garanderie, G. P., & Breckon, T. P. (2019). Generative Adversarial Framework for Depth Filling via Wasserstein Metric, Cosine Transform and Domain Transfer. Pattern Recognition, 91, 232-244. https://doi.org/10.1016/j.patcog.2019.02.010

In this work, the issue of depth filling is addressed using a self-supervised feature learning model that predicts missing depth pixel values based on the context and structure of the scene. A fully-convolutional generative model is conditioned on th... Read More about Generative Adversarial Framework for Depth Filling via Wasserstein Metric, Cosine Transform and Domain Transfer.

Style Augmentation: Data Augmentation via Style Randomization (2019)
Presentation / Conference Contribution
Jackson, P., Atapour-Abarghouei, A., Bonner, S., Breckon, T., & Obara, B. (2019, June). Style Augmentation: Data Augmentation via Style Randomization. Presented at IEEE/CVF Conference on Computer Vision and Pattern Recognition, Deep Vision, Long Beach, CA, USA

We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of Convolutional Neural Networks (CNN) over both classification and regression based tasks. During training, style augmentat... Read More about Style Augmentation: Data Augmentation via Style Randomization.

Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer (2018)
Presentation / Conference Contribution
Atapour-Abarghouei, A., & Breckon, T. (2018, June). Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer. Presented at 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)., Salt Lake City, Utah, USA

Monocular depth estimation using learning-based approaches has become promising in recent years. However, most monocular depth estimators either need to rely on large quantities of ground truth depth data, which is extremely expensive and difficult t... Read More about Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer.

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training (2018)
Presentation / Conference Contribution
Akcay, S., Atapour-Abarghouei, A., & Breckon, T. P. (2018, December). GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training. Presented at 14th Asian Conference on Computer Vision (ACCV)., Perth, Australia

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal). While... Read More about GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training.

Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery (2018)
Book Chapter
Payen de La Garanderie, G., Atapour Abarghouei, A., & Breckon, T. P. (2018). Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery. In V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Eds.), Computer Vision – ECCV 2018 : 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XII (812-830). Springer Verlag. https://doi.org/10.1007/978-3-030-01261-8_48

Recent automotive vision work has focused almost exclusively on processing forward-facing cameras. However, future autonomous vehicles will not be viable without a more comprehensive surround sensing, akin to a human driver, as can be provided by 360... Read More about Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery.

Extended Patch Prioritization for Depth Filling Within Constrained Exemplar-Based RGB-D Image Completion (2018)
Presentation / Conference Contribution
Atapour-Abarghouei, A., & Breckon, T. P. (2018, December). Extended Patch Prioritization for Depth Filling Within Constrained Exemplar-Based RGB-D Image Completion. Presented at International Conference Image Analysis and Recognition, Póvoa de Varzim, Portugal

We address the problem of hole filling in depth images, obtained from either active or stereo sensing, for the purposes of depth image completion in an exemplar-based framework. Most existing exemplar-based inpainting techniques, designed for color i... Read More about Extended Patch Prioritization for Depth Filling Within Constrained Exemplar-Based RGB-D Image Completion.