scispace - formally typeset
J

James Bailey

Researcher at University of Melbourne

Publications -  394
Citations -  13628

James Bailey is an academic researcher from University of Melbourne. The author has contributed to research in topics: Cluster analysis & Computer science. The author has an hindex of 46, co-authored 377 publications receiving 10283 citations. Previous affiliations of James Bailey include University of London & Simon Fraser University.

Papers
More filters
Posted Content

Clean-Label Backdoor Attacks on Video Recognition Models

TL;DR: In this article, a universal adversarial trigger is used as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions, i.e., scenarios with more input dimensions (e.g., videos), scenarios with high resolution, scenarios with a large number of classes and few examples per class, and attacks with access to correct labels.

State-of-the-art on evolution and reactivity

TL;DR: This report starts by outlining aspects of querying and updating resources on the Web and on the Semantic Web, including the development of query and update languages to be carried out within the Rewerse project.
Journal ArticleDOI

Incremental View Maintenance By Base Relation Tagging in Distributed Databases

TL;DR: Two basic view maintenance algorithms are proposed using the use of tags to derive a tagged counting algorithm that further reduces the communication cost, and the performance analysis identifies the situations where a particular algorithm is superior to others.
Journal ArticleDOI

Limit cycle stability analysis and adaptive control of a multi-compartment model for a pressure-limited respirator and lung mechanics system

TL;DR: A general mathematical model for the dynamic behaviour of a multi-compartment respiratory system in response to an arbitrary applied inspiratory pressure is developed and it is shown that the periodic orbit generated by this system is globally asymptotically stable.
Proceedings ArticleDOI

Trajectory inference for mobile devices using connected cell towers

TL;DR: A novel cellular trajectory inference method which requires only the user's connected cell tower location, time and speed information and does not require any historical trajectory information or pre-training and incurs low storage and computation costs is proposed.