V
Vuong Le
Researcher at Deakin University
Publications - 59
Citations - 3147
Vuong Le is an academic researcher from Deakin University. The author has contributed to research in topics: Question answering & Object (computer science). The author has an hindex of 15, co-authored 59 publications receiving 1828 citations. Previous affiliations of Vuong Le include Amazon.com & University of Illinois at Urbana–Champaign.
Papers
More filters
Book ChapterDOI
Interactive facial feature localization
TL;DR: An improvement to the Active Shape Model is proposed that allows for greater independence among the facial components and improves on the appearance fitting step by introducing a Viterbi optimization process that operates along the facial contours.
Proceedings ArticleDOI
Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection
Dong Gong,Lingqiao Liu,Vuong Le,Budhaditya Saha,Moussa Reda Mansour,Svetha Venkatesh,Anton van den Hengel +6 more
TL;DR: The proposed memory-augmented autoencoder called MemAE is free of assumptions on the data type and thus general to be applied to different tasks and proves the excellent generalization and high effectiveness of the proposed MemAE.
Proceedings ArticleDOI
Hierarchical Conditional Relation Networks for Video Question Answering
TL;DR: In this paper, the authors introduce a general-purpose reusable neural unit called CRN, which serves as a building block to construct more sophisticated structures for representation and reasoning over video.
Proceedings ArticleDOI
Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
TL;DR: Wang et al. as mentioned in this paper proposed a new method to model the normal patterns of human movements in surveillance video for anomaly detection using dynamic skeleton features, which decomposes the skeletal movements into two sub-components: global body movement and local body posture.
Posted Content
Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
Dong Gong,Lingqiao Liu,Vuong Le,Budhaditya Saha,Moussa Reda Mansour,Svetha Venkatesh,Anton van den Hengel +6 more
TL;DR: In this article, a memory-augmented autoencoder (MemAE) is proposed to improve the performance of anomaly detection by augmenting the autoencoders with a memory module.