87 citations · 375 across the 43 of their papers we have counts for
28 papers · 1 filter
Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers
Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando +6
Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical system…
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
Sutharsan Mahendran, Darshana Priyasad, Kaushik Roy +4
Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point…
Physics-Guided Attention in a Lightweight TCN for Efficient WiFi CSI-Based Human Activity Recognition
Chinthaka Ranasingha, Tharindu Fernando, Sridha Sridharan +2
Human Action Recognition (HAR) using WiFi Channel State Information (CSI) has gained increasing attention due to its non-contact, low-cost, and privacy-preserving nature. However,…
DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learning
Tharindu Fernando, Clinton Fookes, Sridha Sridharan
Rapid advances in generative AI have led to increasingly realistic deepfakes, posing growing challenges for law enforcement and public trust. Existing passive deepfake detectors st…
Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection
Tharindu Fernando, Clinton Fookes, Sridha Sridharan +1
Remarkable advancements in generative AI technology have given rise to a spectrum of novel deepfake categories with unprecedented leaps in their realism, and deepfakes are increasi…
Dual-Domain Masked Image Modeling: A Self-Supervised Pretraining Strategy Using Spatial and Frequency Domain Masking for Hyperspectral Data
Shaheer Mohamed, Tharindu Fernando, Sridha Sridharan +2
Hyperspectral images (HSIs) capture rich spectral signatures that reveal vital material properties, offering broad applicability across various domains. However, the scarcity of la…
Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking
Shaheer Mohamed, Tharindu Fernando, Sridha Sridharan +2
Hyperspectral object tracking using snapshot mosaic cameras is emerging as it provides enhanced spectral information alongside spatial data, contributing to a more comprehensive un…
Face Deepfakes -- A Comprehensive Review
Tharindu Fernando, Darshana Priyasad, Sridha Sridharan +2
In recent years, remarkable advancements in deep-fake generation technology have led to unprecedented leaps in its realism and capabilities. Despite these advances, we observe a no…
Damage Assessment after Natural Disasters with UAVs: Semantic Feature Extraction using Deep Learning
Nethmi S. Hewawiththi, M. Mahesha Viduranga, Vanodhya G. Warnasooriya +4
Unmanned aerial vehicle-assisted disaster recovery missions have been promoted recently due to their reliability and flexibility. Machine learning algorithms running onboard signif…
Point-PNG: Conditional Pseudo-Negatives Generation for Point Cloud Pre-Training
Sutharsan Mahendren, Saimunur Rahman, Piotr Koniusz +4
We propose Point-PNG, a novel self-supervised learning framework that generates conditional pseudo-negatives in the latent space to learn point cloud representations that are both…
AI, Entrepreneurs, and Privacy: Deep Learning Outperforms Humans in Detecting Entrepreneurs from Image Data
Martin Obschonka, Christian Fisch, Tharindu Fernando +1
Occupational outcomes like entrepreneurship are generally considered personal information that individuals should have the autonomy to disclose. With the advancing capability of ar…
FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining
Shaheer Mohamed, Maryam Haghighat, Tharindu Fernando +3
Hyperspectral images (HSIs) contain rich spectral and spatial information. Motivated by the success of transformers in the field of natural language processing and computer vision…
Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction
Tharindu Fernando, Harshala Gammulle, Sridha Sridharan +2
Humans exhibit complex motions that vary depending on the task that they are performing, the interactions they engage in, as well as subject-specific preferences. Therefore, foreca…
Physical Adversarial Attacks for Surveillance: A Survey
Kien Nguyen, Tharindu Fernando, Clinton Fookes +1
Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversa…
Using Auxiliary Information for Person Re-Identification -- A Tutorial Overview
Tharindu Fernando, Clinton Fookes, Sridha Sridharan +1
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 ch…
Towards On-Board Panoptic Segmentation of Multispectral Satellite Images
Tharindu Fernando, Clinton Fookes, Harshala Gammulle +2
With tremendous advancements in low-power embedded computing devices and remote sensing instruments, the traditional satellite image processing pipeline which includes an expensive…
Patient-independent Epileptic Seizure Prediction using Deep Learning Models
Theekshana Dissanayake, Tharindu Fernando, Simon Denman +2
Objective: Epilepsy is one of the most prevalent neurological diseases among humans and can lead to severe brain injuries, strokes, and brain tumors. Early detection of seizures ca…
Domain Generalization in Biosignal Classification
Theekshana Dissanayake, Tharindu Fernando, Simon Denman +3
Objective: When training machine learning models, we often assume that the training data and evaluation data are sampled from the same distribution. However, this assumption is vio…
Fast & Slow Learning: Incorporating Synthetic Gradients in Neural Memory Controllers
Tharindu Fernando, Simon Denman, Sridha Sridharan +1
Neural Memory Networks (NMNs) have received increased attention in recent years compared to deep architectures that use a constrained memory. Despite their new appeal, the success…
Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks
Tharindu Fernando, Clinton Fookes, Simon Denman +1
Advances in computer vision have brought us to the point where we have the ability to synthesise realistic fake content. Such approaches are seen as a source of disinformation and…
Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation
Harshala Gammulle, Tharindu Fernando, Simon Denman +2
We propose a novel conditional GAN (cGAN) model for continuous fine-grained human action segmentation, that utilises multi-modal data and learned scene context information. The pro…
GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowds
Tharindu Fernando, Simon Denman, Sridha Sridharan +1
This paper presents a novel deep learning framework for human trajectory prediction and detecting social group membership in crowds. We introduce a generative adversarial pipeline…
Pedestrian Trajectory Prediction with Structured Memory Hierarchies
Tharindu Fernando, Simon Denman, Sridha Sridharan +1
This paper presents a novel framework for human trajectory prediction based on multimodal data (video and radar). Motivated by recent neuroscience discoveries, we propose incorpora…
Deep Decision Trees for Discriminative Dictionary Learning with Adversarial Multi-Agent Trajectories
Tharindu Fernando, Sridha Sridharan, Clinton Fookes +1
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…