Tharindu Fernando

TL;DR: This work proposes a novel method to predict the future motion of a pedestrian given a short history of their, and their neighbours, past behaviour using a combined attention model which utilises both "soft attention" as well as "hard-wired" attention in order to map the trajectory information from the local neighbourhood to the future positions of the pedestrian of interest.

TL;DR: In this paper, a combined attention model was proposed to map the trajectory information from the local neighbourhood to the future positions of the pedestrian of interest, where a simple approximation of attention weights (i.e hard-wired) can be merged together with soft attention weights in order to make their model applicable for challenging real world scenarios with hundreds of neighbours.

TL;DR: A coherent and systematic review of state-of-the-art techniques, comparing and contrasting their architectural differences as well as training algorithms and a comprehensive overview of deep model interpretation strategies that can be used to interpret model decisions are provided.

TL;DR: In this paper, the authors proposed two patient-independent deep learning architectures with different learning strategies that can learn a global function utilizing data from multiple subjects and achieved state-of-the-art performance for seizure prediction on the CHB-MIT-EEG dataset, demonstrating 88.81% and 91.54% accuracy respectively.

TL;DR: This work introduces a light weight sequential Generative Adversarial Network architecture for person localisation, which overcomes issues related to occlusions and noisy detections, typically found in a multi person environment and proposes a novel data association scheme based on predicted trajectories.