S
Svetha Venkatesh
Researcher at Deakin University
Publications - 864
Citations - 20118
Svetha Venkatesh is an academic researcher from Deakin University. The author has contributed to research in topics: Bayesian optimization & Computer science. The author has an hindex of 60, co-authored 828 publications receiving 16441 citations. Previous affiliations of Svetha Venkatesh include Australian National University & National University of Singapore.
Papers
More filters
Proceedings ArticleDOI
Large-scale statistical modeling of motion patterns: a Bayesian nonparametric approach
TL;DR: This work proposes a modification of the decayed MCMC technique for incremental inference, providing the ability to discover theoretically unlimited patterns in unbounded video streams, and achieves near real-time execution and encouraging performance in abnormal activity detection.
Proceedings Article
Learning to Remember More with Less Memorization
TL;DR: In this article, Zhao et al. proposed Cached uniform writing to balance between maximizing memorization and forgetting via overwriting mechanisms, which is proved to be optimal under the assumption of equal timestep contributions.
Journal ArticleDOI
A predictive framework for modeling healthcare data with evolving clinical interventions
TL;DR: A prediction framework that explicitly models interventions by extracting a set of latent intervention groups through a Hierarchical Dirichlet Process (HDP) mixture is proposed and it is shown that by replacing HDP with a dynamic HDP prior, a more compact set of distributions can be learnt.
Proceedings ArticleDOI
Expected Hypervolume Improvement with Constraints
TL;DR: The Expected Hypervolume Improvement is extended by introducing expectation of constraints satisfaction and merging them into a new acquisition function called EHVIC, which is an effective algorithm that provides a promising performance by comparing to a well-known related method.
Journal ArticleDOI
Recognising online spatial activities using a bioinformatics inspired sequence alignment approach
TL;DR: An algorithm based on Smith-Waterman (SW) local alignment from the field of bioinformatics that can locate and accurately quantify embedded activities within a windowed sequence and produce results comparable to DTW and superior to the HMM is introduced.