Outputs (468)

Multi-Modal Learning for Real-Time Automotive Semantic Foggy Scene Understanding via Domain Adaptation (2021)
Presentation / Conference Contribution

Robust semantic scene segmentation for automotive applications is a challenging problem in two key aspects: (1) labelling every individual scene pixel and (2) performing this task under unstable weather and illumination changes (e.g., foggy weather),... Read More about Multi-Modal Learning for Real-Time Automotive Semantic Foggy Scene Understanding via Domain Adaptation.

PANDA: Perceptually Aware Neural Detection of Anomalies (2021)
Presentation / Conference Contribution

Semi-supervised methods of anomaly detection have seen substantial advancement in recent years. Of particular interest are applications of such methods to diverse, real-world anomaly detection problems where anomalous variations can vary from the vis... Read More about PANDA: Perceptually Aware Neural Detection of Anomalies.

Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions (2019)
Presentation / Conference Contribution

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.

Front Camera Eye Tracking For Mobile VR (2020)
Presentation / Conference Contribution

Autoencoders Without Reconstruction for Textural Anomaly Detection (2021)
Presentation / Conference Contribution

Automatic anomaly detection in natural textures is a key component within quality control for a range of high-speed, high-yield manufacturing industries that rely on camera-based visual inspection techniques. Targeting anomaly detection through the u... Read More about Autoencoders Without Reconstruction for Textural Anomaly Detection.

Image recoloring for home scene (2018)
Presentation / Conference Contribution

Indoor home scene coloring technology is a hot topic for home design, helping users make home coloring decisions. Image based home scene coloring is preferable for e-commerce customers since it only requires users to describe coloring expectations or... Read More about Image recoloring for home scene.

The Good, the Bad and the Ugly: Evaluating Convolutional Neural Networks for Prohibited Item Detection Using Real and Synthetically Composite X-ray Imagery (2019)
Presentation / Conference Contribution

Using Deep Neural Networks to Address the Evolving Challenges of Concealed Threat Detection within Complex Electronic Items (2019)
Presentation / Conference Contribution

X-ray baggage security screening is widely used to maintain aviation and transport safety and security. To address the future challenges of increasing volumes and complexities, the recent focus on the use of automated screening approaches are of part... Read More about Using Deep Neural Networks to Address the Evolving Challenges of Concealed Threat Detection within Complex Electronic Items.

Evaluating the Transferability and Adversarial Discrimination of Convolutional Neural Networks for Threat Object Detection and Classification within X-Ray Security Imagery (2019)
Presentation / Conference Contribution

X-ray imagery security screening is essential to maintaining transport security against a varying profile of threat or prohibited items. Particular interest lies in the automatic detection and classification of weapons such as firearms and knives wit... Read More about Evaluating the Transferability and Adversarial Discrimination of Convolutional Neural Networks for Threat Object Detection and Classification within X-Ray Security Imagery.

Experimental Exploration of Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection (2019)
Presentation / Conference Contribution

In this work we explore different Convolutional Neural Network (CNN) architectures and their variants for non-temporal binary fire detection and localization in video or still imagery. We consider the performance of experimentally defined, reduced co... Read More about Experimental Exploration of Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection.

Region Based Anomaly Detection With Real-Time Training and Analysis (2019)
Presentation / Conference Contribution

We present a method of anomaly detection that is capable of real-time operation on a live stream of images. The real-time performance applies to the training of the algorithm as well as subsequent analysis, and is achieved by substituting the region... Read More about Region Based Anomaly Detection With Real-Time Training and Analysis.

A Two-Stream Recurrent Network for Skeleton-based Human Interaction Recognition (2021)
Presentation / Conference Contribution

This paper addresses the problem of recognizing human-human interaction from skeletal sequences. Existing methods are mainly designed to classify single human action. Many of them simply stack the movement features of two characters to deal with huma... Read More about A Two-Stream Recurrent Network for Skeleton-based Human Interaction Recognition.

Colour Processing in Adversarial Attacks on Face Liveness Systems (2019)
Presentation / Conference Contribution

In the context of face recognition systems, liveness test is a binary classification task aiming at distinguishing between input images that come from real people’s faces and input images that come from photos or videos of those faces, and presented... Read More about Colour Processing in Adversarial Attacks on Face Liveness Systems.

Towards light-weight annotations: Fuzzy interpolative reasoning for zero-shot image classification (2018)
Presentation / Conference Contribution

Efficient and Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection (2021)
Presentation / Conference Contribution

Automatic visual fire detection is used to complement traditional fire detection sensor systems (smoke/heat). In this work, we investigate different Convolutional Neural Network (CNN) architectures and their variants for the non-temporal real-time bo... Read More about Efficient and Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection.

Towards affordable semantic searching: Zero-shot retrieval via dominant attributes (2018)
Presentation / Conference Contribution

Instance-level retrieval has become an essential paradigm to index and retrieves images from large-scale databases. Conventional instance search requires at least an example of the query image to retrieve images that contain the same object instance.... Read More about Towards affordable semantic searching: Zero-shot retrieval via dominant attributes.

Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery (2021)
Presentation / Conference Contribution

Automatic detection for threat object items is an increasing emerging area of future application in X-ray security imagery. Although modern X-ray security scanners can provide two or more views, the integration of such object detectors across the vie... Read More about Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery.

Attribute embedding with visual-semantic ambiguity removal for zero-shot learning (2016)
Presentation / Conference Contribution

Recognising Human-Object Interactions Using Attention-based LSTMs (2019)
Presentation / Conference Contribution

Recognising Human-object interactions (HOIs) in videos is a challenge task especially when a human can interact with multiple objects. This paper attempts to solve the problem of HOIs by proposing a hierarchical framework that analyzes human-object i... Read More about Recognising Human-Object Interactions Using Attention-based LSTMs.

Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling (2019)
Presentation / Conference Contribution

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.