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
Journal Article
Innovative sparse representation algorithms for robust face recognition
TL;DR: Two innovative and computationally efficient algorithms for robust face recognition, which extend the previous Sparse Representation- based Classication (SRC) algorithm, operate on matrix rep- resentation of images, as opposed to vector representation in SRC, to achieve efficiency whilst maintaining the recognition performance.
Proceedings ArticleDOI
Multi-task transfer learning for in-hospital-death prediction of ICU patients
TL;DR: The results indicates that the performance of in-hospital mortality can be improved using ICU type information and by balancing the `non-survivor' class.
Journal ArticleDOI
Fairness improvement for black-box classifiers with Gaussian process
TL;DR: A novel post-processing method based on Gaussian process that can improve fairness while maintaining high accuracy is proposed, and a theoretical analysis is provided to derive an upper bound on accuracy loss.
Proceedings ArticleDOI
Exploiting side information in distance dependent Chinese restaurant processes for data clustering
TL;DR: This work demonstrates how to incorporate different types of side information into a recently proposed Bayesian nonparametric model, the distance dependent Chinese restaurant process (DD-CRP), and embeds the affinity of this information into the decay function of the DD- CRP when side information is in the form of subsets of discrete labels.
Book ChapterDOI
Classifying and Learning Cricket Shots Using Camera Motion
TL;DR: By using the camera motion parameters, a complex and diflficult process of low level image segmenting of either the batsman or the cricket ball from video images is avoided and the method does not require high resolution images.