L
Len Hamey
Researcher at Macquarie University
Publications - 30
Citations - 717
Len Hamey is an academic researcher from Macquarie University. The author has contributed to research in topics: Deep learning & Closed captioning. The author has an hindex of 8, co-authored 30 publications receiving 446 citations. Previous affiliations of Len Hamey include Commonwealth Scientific and Industrial Research Organisation & Australian National University.
Papers
More filters
Proceedings ArticleDOI
Autoencoder-based feature learning for cyber security applications
TL;DR: It is shown how well the AE is capable of automatically learning a reasonable notion of semantic similarity among input features, and how the scheme can reduce the dimensionality of the features thereby signicantly minimising the memory requirements.
Journal ArticleDOI
Text summarization using unsupervised deep learning
Mahmood Yousefi-Azar,Len Hamey +1 more
TL;DR: Experiments show that the AE using local vocabularies clearly provide a more discriminative feature space and improves the recall on average 11.2%, and the ENAE can make further improvements, particularly in selecting informative sentences.
Posted Content
Automatic Recognition of Student Engagement using Deep Learning and Facial Expression.
TL;DR: A deep learning model to improve engagement recognition from images that overcomes the data sparsity challenge by pre-training on readily available basic facial expression data, before training on specialised engagement data is presented.
Proceedings ArticleDOI
Designing a user-defined gesture vocabulary for an in-vehicle climate control system
TL;DR: Comparisons are drawn between the proposed approach to define a vocabulary using 9 new gestures (GestDrive) and previously suggested methods and the outcomes demonstrate that GestDrive is successful in describing the employed gestures in detail.
Proceedings ArticleDOI
Adversarial Attacks on Mobile Malware Detection
TL;DR: This work proposes a machine learning based model to attack malware classifiers leveraging the expressive capability of generative adversarial networks (GANs) and shows that the generated samples can bypass detection in 99% of attempts using a real Android application dataset.