Outputs (375)

Evaluating Gaussian Grasp Maps for Generative Grasping Models (2022)
Presentation / Conference Contribution

Generalising robotic grasping to previously unseen objects is a key task in general robotic manipulation. The current method for training many antipodal generative grasping models rely on a binary ground truth grasp map generated from the centre thir... Read More about Evaluating Gaussian Grasp Maps for Generative Grasping Models.

HGO-CNN: HYBRID GENERIC-ORGAN CONVOLUTIONAL NEURAL NETWORK FOR MULTI-ORGAN PLANT CLASSIFICATION (2017)
Presentation / Conference Contribution

Φ Clust: Pheromone-Based Aggregation for Robotic Swarms (2018)
Presentation / Conference Contribution

In this paper, we proposed a pheromone-based aggregation method based on the state-of-the-art BEECLUST algorithm. We investigated the impact of pheromone-based communication on the efficiency of robotic swarms to locate and aggregate at areas with a... Read More about Φ Clust: Pheromone-Based Aggregation for Robotic Swarms.

An Integrated Precision Farming Application Based on 5G, UAV and Deep Learning Technologies (2019)
Presentation / Conference Contribution

Smart Monitoring of Crops Using Generative Adversarial Networks (2019)
Presentation / Conference Contribution

Simulating People Dynamics (2021)
Presentation / Conference Contribution

INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations (2022)
Presentation / Conference Contribution

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decisionmaking, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a s... Read More about INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations.

Does lossy image compression affect racial bias within face recognition? (2022)
Presentation / Conference Contribution

This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject. We adopt a recently proposed racial phenotype-based bias analysis methodology to measur... Read More about Does lossy image compression affect racial bias within face recognition?.

Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery (2022)
Presentation / Conference Contribution

Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression c... Read More about Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery.

Long-term Reproducibility for Neural Architecture Search (2022)
Presentation / Conference Contribution

Heart synchronization for SPIM microscopy of living zebra fish (2011)
Presentation / Conference Contribution

We describe work on producing a selective plane illumination microscope for cardiac imaging in zebra fish embryos. The system has a novel synchronization system for imaging oscillating structures (e.g. the heart) and will have adaptive optics for ima... Read More about Heart synchronization for SPIM microscopy of living zebra fish.

Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task (2022)
Presentation / Conference Contribution

Numerical tables are widely employed to communicate or report the classification performance of machine learning (ML) models with respect to a set of evaluation metrics. For non-experts, domain knowledge is required to fully understand and interpret... Read More about Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task.

Cerebral Palsy Prediction with Frequency Attention Informed Graph Convolutional Networks (2022)
Presentation / Conference Contribution

Early diagnosis and intervention are clinically considered the paramount part of treating cerebral palsy (CP), so it is essential to design an efficient and interpretable automatic prediction system for CP. We highlight a significant difference betwe... Read More about Cerebral Palsy Prediction with Frequency Attention Informed Graph Convolutional Networks.

“Just Drive”: Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving (2021)
Presentation / Conference Contribution

Biases can filter into AI technology without our knowledge. Oftentimes, seminal deep learning networks champion increased accuracy above all else. In this paper, we attempt to alleviate biases encountered by semantic segmentation models in urban driv... Read More about “Just Drive”: Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving.

An optical platform for the production, trapping, manipulation and visualization of ultra-low interfacial tension emulsion droplets (2013)
Presentation / Conference Contribution

We discuss the design, implementation and performance of a novel platform for the production and optical control of ultra-low interfacial tension droplets in the 1-10 micron regime. A custom-designed, integrated microfluidic system allows the product... Read More about An optical platform for the production, trapping, manipulation and visualization of ultra-low interfacial tension emulsion droplets.

Pose-based Tremor Classification for Parkinson’s Disease Diagnosis from Video (2022)
Presentation / Conference Contribution

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that results in a variety of motor dysfunction symptoms, including tremors, bradykinesia, rigidity and postural instability. The diagnosis of PD mainly relies on clinical experience... Read More about Pose-based Tremor Classification for Parkinson’s Disease Diagnosis from Video.

On Depth Error from Spherical Camera Calibration within Omnidirectional Stereo Vision (2022)
Presentation / Conference Contribution

As a depth sensing approach, whilst stereo vision provides a good compromise between accuracy and cost, a key limitation is the limited field of view of the conventional cameras that are used within most stereo configurations. By contrast, the use of... Read More about On Depth Error from Spherical Camera Calibration within Omnidirectional Stereo Vision.

Biohybrid Entities for Environmental Monitoring (2021)
Presentation / Conference Contribution

In the wake of climate change and water quality crisis, it is crucial to find novel ways to extensively monitor the environment and to detect ecological changes early. Biomonitoring has been found to be an effective way of observing the aggregate eff... Read More about Biohybrid Entities for Environmental Monitoring.

360 Depth Estimation in the Wild - The Depth360 Dataset and the SegFuse Network (2022)
Presentation / Conference Contribution

Single-view depth estimation from omnidirectional images has gained popularity with its wide range of applications such as autonomous driving and scene reconstruction. Although data-driven learning-based methods demonstrate significant potential in t... Read More about 360 Depth Estimation in the Wild - The Depth360 Dataset and the SegFuse Network.

Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery (2022)
Presentation / Conference Contribution

Within commercial wind energy generation, the monitoring and predictive maintenance of wind turbine blades in-situ is a crucial task, for which remote monitoring via aerial survey from an Unmanned Aerial Vehicle (UAV) is commonplace. Turbine blades a... Read More about Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery.