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
Book ChapterDOI
A bayesian framework for learning shared and individual subspaces from multiple data sources
TL;DR: A novel Bayesian formulation to exploit shared structures across multiple data sources, constructing foundations for effective mining and retrieval across disparate domains is presented, providing a formal framework suitable for exploiting individual as well as mutual knowledge present across heterogeneous data sources of many kinds.
Posted Content
Column Networks for Collective Classification
TL;DR: The Column Network (CLN) as discussed by the authors is a deep learning model for collective classification in multi-relational domains, which encodes multi-relations between any two instances and allows complex functions to be approximated at the network level with a small set of free parameters.
Journal ArticleDOI
Web search activity data accurately predict population chronic disease risk in the USA
Thin Nguyen,Truyen Tran,Wei Luo,Sunil Gupta,Santu Rana,Dinh Phung,Melanie Nichols,Lynne Millar,Svetha Venkatesh,Steve Allender +9 more
TL;DR: The high predictive validity of web search activity for NCD risk has potential to provide real-time information on population risk during policy implementation and other population-level NCD prevention efforts.
Proceedings ArticleDOI
Application of computational media aesthetics methodology to extracting color semantics in film
TL;DR: Using film grammar as the underpinning, this work studies the extraction of structures in video based on color using a wide configuration of clustering methods combined with existing and new similarity measures and shows how it can bring out the interweaving of different themes and settings in a film.
Proceedings ArticleDOI
Learning Asynchronous and Sparse Human-Object Interaction in Videos
TL;DR: Asynchronous-Sparse Interaction Graph Networks (ASSIGN) as discussed by the authors is a recurrent graph network that is able to automatically detect the structure of interaction events associated with entities in a video scene.