Search Results for author: Tharindu Fernando

Found 29 papers, 1 papers with code

FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining

1 code implementation18 Sep 2023 Shaheer Mohamed, Maryam Haghighat, Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Peyman Moghadam

However, current state-of-the-art hyperspectral transformers only tokenize the input HSI sample along the spectral dimension, resulting in the under-utilization of spatial information.

Physical Adversarial Attacks for Surveillance: A Survey

no code implementations1 May 2023 Kien Nguyen, Tharindu Fernando, Clinton Fookes, Sridha Sridharan

In particular, we propose a framework to analyze physical adversarial attacks and provide a comprehensive survey of physical adversarial attacks on four key surveillance tasks: detection, identification, tracking, and action recognition under this framework.

Action Recognition

Using Auxiliary Information for Person Re-Identification -- A Tutorial Overview

no code implementations15 Nov 2022 Tharindu Fernando, Clinton Fookes, Sridha Sridharan, Dana Michalski

Person re-identification (re-id) is a pivotal task within an intelligent surveillance pipeline and there exist numerous re-id frameworks that achieve satisfactory performance in challenging benchmarks.

Person Re-Identification

Towards On-Board Panoptic Segmentation of Multispectral Satellite Images

no code implementations5 Apr 2022 Tharindu Fernando, Clinton Fookes, Harshala Gammulle, Simon Denman, Sridha Sridharan

To address this challenge, we propose a multimodal teacher network based on a cross-modality attention-based fusion strategy to improve the segmentation accuracy by exploiting data from multiple modes.

Knowledge Distillation Panoptic Segmentation +1

Deep Learning for Medical Anomaly Detection -- A Survey

no code implementations4 Dec 2020 Tharindu Fernando, Harshala Gammulle, Simon Denman, Sridha Sridharan, Clinton Fookes

Machine learning-based medical anomaly detection is an important problem that has been extensively studied.

Anomaly Detection

Patient-independent Epileptic Seizure Prediction using Deep Learning Models

no code implementations18 Nov 2020 Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes

Patient-independent seizure prediction models are designed to offer accurate performance across multiple subjects within a dataset, and have been identified as a real-world solution to the seizure prediction problem.

EEG Electroencephalogram (EEG) +1

Domain Generalization in Biosignal Classification

no code implementations12 Nov 2020 Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Houman Ghaemmaghami, Sridha Sridharan, Clinton Fookes

Conclusion: Recognizing the complexity induced by the inherent temporal nature of biosignal data, the two-stage method proposed in this study is able to effectively simplify the whole process of domain generalization while demonstrating good results on unseen domains and the adopted basis domains.

Classification Domain Generalization +1

Fast & Slow Learning: Incorporating Synthetic Gradients in Neural Memory Controllers

no code implementations10 Nov 2020 Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes

In addition, we demonstrate the practical implications of the proposed learning strategy, where the feedback path can be shared among multiple neural memory networks as a mechanism for knowledge sharing.

Meta-Learning Retrieval

Attention Driven Fusion for Multi-Modal Emotion Recognition

no code implementations23 Sep 2020 Darshana Priyasad, Tharindu Fernando, Simon Denman, Clinton Fookes, Sridha Sridharan

In this paper, we present a deep learning-based approach to exploit and fuse text and acoustic data for emotion classification.

Emotion Classification Emotion Recognition

Memory based fusion for multi-modal deep learning

no code implementations16 Jul 2020 Darshana Priyasad, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes

The use of multi-modal data for deep machine learning has shown promise when compared to uni-modal approaches with fusion of multi-modal features resulting in improved performance in several applications.

A Robust Interpretable Deep Learning Classifier for Heart Anomaly Detection Without Segmentation

no code implementations21 May 2020 Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Sridha Sridharan, Houman Ghaemmaghami, Clinton Fookes

In this study, we explicitly examine the importance of heart sound segmentation as a prior step for heart sound classification, and then seek to apply the obtained insights to propose a robust classifier for abnormal heart sound detection.

Anomaly Detection Classification +4

Heart Sound Segmentation using Bidirectional LSTMs with Attention

no code implementations2 Apr 2020 Tharindu Fernando, Houman Ghaemmaghami, Simon Denman, Sridha Sridharan, Nayyar Hussain, Clinton Fookes

This paper proposes a novel framework for the segmentation of phonocardiogram (PCG) signals into heart states, exploiting the temporal evolution of the PCG as well as considering the salient information that it provides for the detection of the heart state.

Segmentation

Neural Memory Networks for Seizure Type Classification

no code implementations10 Dec 2019 David Ahmedt-Aristizabal, Tharindu Fernando, Simon Denman, Lars Petersson, Matthew J. Aburn, Clinton Fookes

Inspired by recent advances in neural memory networks (NMNs), we introduce a novel approach for the classification of seizure type using electrophysiological data.

Classification EEG +4

Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks

no code implementations17 Nov 2019 Tharindu Fernando, Clinton Fookes, Simon Denman, Sridha Sridharan

Advances in computer vision have brought us to the point where we have the ability to synthesise realistic fake content.

Face Detection

Neural Memory Plasticity for Anomaly Detection

no code implementations12 Oct 2019 Tharindu Fernando, Simon Denman, David Ahmedt-Aristizabal, Sridha Sridharan, Kristin Laurens, Patrick Johnston, Clinton Fookes

In the domain of machine learning, Neural Memory Networks (NMNs) have recently achieved impressive results in a variety of application areas including visual question answering, trajectory prediction, object tracking, and language modelling.

Anomaly Detection EEG +7

Deep Decision Trees for Discriminative Dictionary Learning with Adversarial Multi-Agent Trajectories

no code implementations14 May 2018 Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Simon Denman

With the explosion in the availability of spatio-temporal tracking data in modern sports, there is an enormous opportunity to better analyse, learn and predict important events in adversarial group environments.

Clustering Dictionary Learning

Task Specific Visual Saliency Prediction with Memory Augmented Conditional Generative Adversarial Networks

no code implementations9 Mar 2018 Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes

Visual saliency patterns are the result of a variety of factors aside from the image being parsed, however existing approaches have ignored these.

Saliency Prediction

Tree Memory Networks for Modelling Long-term Temporal Dependencies

no code implementations12 Mar 2017 Tharindu Fernando, Simon Denman, Aaron McFadyen, Sridha Sridharan, Clinton Fookes

In this paper, we propose a Tree Memory Network (TMN) for modelling long term and short term relationships in sequence-to-sequence mapping problems.

Machine Translation Part-Of-Speech Tagging +3

Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection

no code implementations18 Feb 2017 Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes

We illustrate how a simple approximation of attention weights (i. e hard-wired) can be merged together with soft attention weights in order to make our model applicable for challenging real world scenarios with hundreds of neighbours.

Event Detection Machine Translation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.