ORCID Profile
0000-0001-8095-4637
Current Organisations
A*STAR
,
University of Technology Sydney: Broadway, NSW, Australia
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Research Topics
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Top 5 Research Topics
ANZSRC Field of Research (FoR)
Pattern Recognition and Data Mining | Artificial Intelligence and Image Processing | Artificial Intelligence and Image Processing not elsewhere classified |
ANZSRC Socio-Economic Objective (SEO)
Information Processing Services (incl. Data Entry and Capture) | Social Structure and Health | Expanding Knowledge in the Information and Computing Sciences | Mental Health | Application Software Packages (excl. Computer Games) | Application Tools and System Utilities
Related Links
Publications
Learning word dependencies in text by means of a deep recurrent belief network
Publisher: Elsevier BV
Date: 09-2016
A Flexible and Effective Linearization Method for Subspace Learning
Publisher: Springer New York
Date: 21-09-2012
On the Confluence of Freedom of the Press, Control of Corruption and Societal Welfare
Publisher: Springer Science and Business Media LLC
Date: 04-08-2015
Making Trillion Correlations Feasible in Feature Grouping and Selection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2016
Location and Scatter Matching for Dataset Shift in Text Mining
Publisher: IEEE
Date: 12-2010
DOI: 10.1109/ICDM.2010.72
Maximum Margin/Volume Outlier Detection
Publisher: IEEE
Date: 11-2011
Region-Based Saliency Detection and Its Application in Object Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2014
Well-M$^3$N: A Maximum-Margin Approach to Unsupervised Structured Prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
A Feature Selection Method for Multivariate Performance Measures
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2013
Feature Disentangling Machine - A Novel Approach of Feature Selection and Disentangling in Facial Expression Analysis
Publisher: Springer International Publishing
Date: 2014
MINIMUM VIABLE GOVERNANCE FOR DATA SCIENCE INITIATIVES A TRANSPORT FOR NSW CASE STUDY
Publisher: International Project Management Association, Serbian Project Management Association
Date: 12-2022
DOI: 10.56889/VJTU9918
Abstract: Too much governance can stifle innovation in organizations. Too little governance can waste precious organizational resources. Business agility demands empowerment of people to take decisions on initiatives designed to deliver innovative products and services. Traditional monthly and quarterly governance forums such as steering committees and program boards for decision-making potentially impede the flow of work when the delivery of a program or project is done using agile methods in two-weekly sprints and decisions are required at a different and more frequent cadence. Data Science Initiatives (DSIs) which are exploratory and innovative in nature follow agile delivery methods. This paper is an exploratory study of implementing governance for DSIs based on a single case study. It investigates agile governance at project, program, and portfolio level for DSIs and suggests eight guiding principles focusing on product and portfolio governance. It is targeted at practitioners to guide them in setting minimum viable governance to ensure value is realized from their DSIs and for academics to advance research in governance of DSIs.
Optimizing Performance Measures for Feature Selection
Publisher: IEEE
Date: 12-2011
Towards the Learning of Weighted Multi-label Associative Classifiers
Publisher: IEEE
Date: 07-2018
Kernel relevant component analysis for distance metric learning
Publisher: IEEE
Date: 2005
Spectral Embedded Clustering: A Framework for In-Sample and Out-of-Sample Spectral Clustering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2011
Feature Weighting via Optimal Thresholding for Video Analysis
Publisher: IEEE
Date: 12-2013
Robust Plackett–Luce model for k-ary crowdsourced preferences
Publisher: Springer Science and Business Media LLC
Date: 25-10-2017
Learning node representations against perturbations
Publisher: Elsevier BV
Date: 2024
Efficient Hyperkernel Learning Using Second-Order Cone Programming
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2006
Large-Scale Maximum Margin Discriminant Analysis Using Core Vector Machines
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2008
SVDD-Based Pattern Denoising
Publisher: MIT Press - Journals
Date: 07-2007
DOI: 10.1162/NECO.2007.19.7.1919
Abstract: The support vector data description (SVDD) is one of the best-known one-class support vector learning methods, in which one tries the strategy of using balls defined on the feature space in order to distinguish a set of normal data from all other possible abnormal objects. The major concern of this letter is to extend the main idea of SVDD to pattern denoising. Combining the geodesic projection to the spherical decision boundary resulting from the SVDD, together with solving the preimage problem, we propose a new method for pattern denoising. We first solve SVDD for the training data and then for each noisy test pattern, obtain its denoised feature by moving its feature vector along the geodesic on the manifold to the nearest decision boundary of the SVDD ball. Finally we find the location of the denoised pattern by obtaining the pre-image of the denoised feature. The applicability of the proposed method is illustrated by a number of toy and real-world data sets.
Event Detection Using Multi-level Relevance Labels and Multiple Features
Publisher: IEEE
Date: 06-2014
DOI: 10.1109/CVPR.2014.20
A Convex Method for Locating Regions of Interest with Multi-instance Learning
Publisher: Springer Berlin Heidelberg
Date: 2009
Exploratory analysis of cell-based screening data for phenotype identification in drug-siRNA study
Publisher: Inderscience Publishers
Date: 2011
Textual Query of Personal Photos Facilitated by Large-Scale Web Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2011
Flexible Manifold Embedding: A Framework for Semi-Supervised and Unsupervised Dimension Reduction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2010
Text-based image retrieval using progressive multi-instance learning
Publisher: IEEE
Date: 11-2011
Generalized Core Vector Machines
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2006
Incremental Subgraph Feature Selection for Graph Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2017
Late Fusion via Subspace Search With Consistency Preservation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Support, sensitivity, satisfaction: Filipino, Turkish and Vietnamese women's experiences of postnatal hospital stay
Publisher: Elsevier BV
Date: 09-1998
DOI: 10.1016/S0266-6138(98)90029-8
Abstract: To assess Filipino, Turkish and Vietnamese women's views about their care during the postnatal hospital stay. Interviews were conducted with recent mothers in the language of the women's choice, 6-9 months after birth, by three bilingual interviewers. Three hundred and eighteen women born in the Philippines (107), Turkey (107) and Vietnam (104) who had migrated to Australia. Women were recruited from the postnatal wards of three maternity teaching hospitals in Melbourne, Australia, and interviewed at home. Overall satisfaction with care was low, and one in three women left hospital feeling that they required more support and assistance with both baby care and their own personal needs. The method of baby feeding varied between the groups, with women giving some insight into the reason for their choice. A significant minority wanted more help with feeding, irrespective of the method. The need for rest was a recurrent theme, with women stating that staff's attitudes to in idual preferences, coupled with lack of assistance, made this difficult. The majority of comments women made regarding their postnatal stay focused on the attitude and behaviour of staff and about routine aspects of care. Issues related to culture and cultural practices were not of primary concern to women. Maternity services need to consider ways in which care can focus on the in idual needs and preferences of women.
VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
An evolutionary search paradigm that learns with past experiences
Publisher: IEEE
Date: 06-2012
Efficient federated multi-view learning
Publisher: Elsevier BV
Date: 11-2022
Memes as building blocks: a case study on evolutionary optimization + transfer learning for routing problems
Publisher: Springer Science and Business Media LLC
Date: 05-08-2015
Laplacian Sparse Coding, Hypergraph Laplacian Sparse Coding, and Applications
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2013
Tag-based image retrieval improved by augmented features and group-based refinement
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2012
Deep Representations to Model User ‘Likes’
Publisher: Springer International Publishing
Date: 2015
Noisy Label Learning With Provable Consistency for a Wider Family of Losses
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Kernel Sparse Representation for Image Classification and Face Recognition
Publisher: Springer Berlin Heidelberg
Date: 2010
Discovering Low-Rank Shared Concept Space for Adapting Text Mining Models
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2013
A unified probabilistic framework for robust manifold learning and embedding
Publisher: Springer Science and Business Media LLC
Date: 23-12-2016
High-order proximity preserving information network hashing
Publisher: ACM
Date: 19-07-2018
Soft Margin Multiple Kernel Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2013
An Efficient Exact Nearest Neighbor Search by Compounded Embedding
Publisher: Springer International Publishing
Date: 2018
Domain Adaption via Feature Selection on Explicit Feature Map
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Minimax Sparse Logistic Regression for Very High-Dimensional Feature Selection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2013
Metric Learning for Multi-Output Tasks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2019
A Class of Single-Class Minimax Probability Machines for Novelty Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2007
Generalized Multiple Kernel Learning With Data-Dependent Priors
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2015
Auto-weighted multi-view clustering via kernelized graph learning
Publisher: Elsevier BV
Date: 04-2019
Domain Adaptation via Transfer Component Analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2011
Domain adaptation from multiple sources via auxiliary classifiers
Publisher: ACM
Date: 14-06-2009
Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2014
Maximum Penalized Likelihood Kernel Regression for Fast Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2009
Error Correcting Input and Output Hashing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2019
Local features are not lonely – Laplacian sparse coding for image classification
Publisher: IEEE
Date: 06-2010
The Pre-Image Problem in Kernel Methods
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2004
Spectral Embedded Hashing for Scalable Image Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2014
Fusing Images With Different Focuses Using Support Vector Machines
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2004
Sparse Representation With Kernels
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2013
Using large-scale web data to facilitate textual query based retrieval of consumer photos
Publisher: ACM
Date: 19-10-2009
Learning Target Predictive Function without Target Labels
Publisher: IEEE
Date: 12-2012
DOI: 10.1109/ICDM.2012.77
Co-labeling: A New Multi-view Learning Approach for Ambiguous Problems
Publisher: IEEE
Date: 12-2012
DOI: 10.1109/ICDM.2012.78
The Emerging Big Dimensionality
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2014
Partial Hash Update via Hamming Subspace Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2017
Infinite Decision Agent Ensemble Learning System for Credit Risk Analysis
Publisher: IEEE
Date: 12-2011
Visual event recognition in videos by learning from web data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2012
Progressive Stochastic Learning for Noisy Labels
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2018
Extracting discriminative concepts for domain adaptation in text mining
Publisher: ACM
Date: 28-06-2009
Defragging Subgraph Features for Graph Classification
Publisher: ACM
Date: 17-10-2015
Millionaire: a hint-guided approach for crowdsourcing
Publisher: Springer Science and Business Media LLC
Date: 19-12-2018
A maximum entropy-least squares estimator for elastic origin-destination trip matrix estimation
Publisher: Elsevier BV
Date: 2011
Combating Negative Transfer From Predictive Distribution Differences
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2013
Maximum margin clustering made practical
Publisher: ACM
Date: 20-06-2007
Efficient Discriminative Learning of Class Hierarchy for Many Class Prediction
Publisher: Springer Berlin Heidelberg
Date: 2013
Privacy-Preserving Stochastic Gradual Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2021
Deep Learning from Noisy Image Labels with Quality Embedding.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Improving Web Image Search by Bag-Based Reranking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2011
Predictive Distribution Matching SVM for Multi-domain Learning
Publisher: Springer Berlin Heidelberg
Date: 2010
Multilabel Prediction via Cross-View Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
Efficient Multitemplate Learning for Structured Prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2013
Laplacian Embedded Regression for Scalable Manifold Regularization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2012
Linear dependency between Σ and the input noise in Σ-support vector regression
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2003
Stagewise learning for noisy k-ary preferences
Publisher: Springer Science and Business Media LLC
Date: 11-05-2018
Objective-Guided Image Annotation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2013
Transfer Ordinal Label Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2013
Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2014
A Hybrid PSO-BFGS Strategy for Global Optimization of Multimodal Functions
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2011
Handling Ambiguity via Input-Output Kernel Learning
Publisher: IEEE
Date: 12-2012
Hyperspectral imagery classification via stochastic HHSVMs
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2019
Efficient Optimization of Performance Measures by Classifier Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2013
Unseen Land Cover Classification from High-Resolution Orthophotos Using Integration of Zero-Shot Learning and Convolutional Neural Networks
Publisher: MDPI AG
Date: 23-05-2020
DOI: 10.3390/RS12101676
Abstract: Zero-shot learning (ZSL) is an approach to classify objects unseen during the training phase and shown to be useful for real-world applications, especially when there is a lack of sufficient training data. Only a limited amount of works has been carried out on ZSL, especially in the field of remote sensing. This research investigates the use of a convolutional neural network (CNN) as a feature extraction and classification method for land cover mapping using high-resolution orthophotos. In the feature extraction phase, we used a CNN model with a single convolutional layer to extract discriminative features. In the second phase, we used class attributes learned from the Word2Vec model (pre-trained by Google News) to train a second CNN model that performed class signature prediction by using both the features extracted by the first CNN and class attributes during training and only the features during prediction. We trained and tested our models on datasets collected over two subareas in the Cameron Highlands (training dataset, first test dataset) and Ipoh (second test dataset) in Malaysia. Several experiments have been conducted on the feature extraction and classification models regarding the main parameters, such as the network’s layers and depth, number of filters, and the impact of Gaussian noise. As a result, the best models were selected using various accuracy metrics such as top-k categorical accuracy for k = [1,2,3], Recall, Precision, and F1-score. The best model for feature extraction achieved 0.953 F1-score, 0.941 precision, 0.882 recall for the training dataset and 0.904 F1-score, 0.869 precision, 0.949 recall for the first test dataset, and 0.898 F1-score, 0.870 precision, 0.838 recall for the second test dataset. The best model for classification achieved an average of 0.778 top-one, 0.890 top-two and 0.942 top-three accuracy, 0.798 F1-score, 0.766 recall and 0.838 precision for the first test dataset and 0.737 top-one, 0.906 top-two, 0.924 top-three, 0.729 F1-score, 0.676 recall and 0.790 precision for the second test dataset. The results demonstrated that the proposed ZSL is a promising tool for land cover mapping based on high-resolution photos.
Multi-layer group sparse coding — For concurrent image classification and annotation
Publisher: IEEE
Date: 06-2011
Relevance vector machine based infinite decision agent ensemble learning for credit risk analysis
Publisher: Elsevier BV
Date: 04-2012
Fast and Low Memory Cost Matrix Factorization: Algorithm, Analysis and Case Study
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2020
Online Heterogeneous Transfer by Hedge Ensemble of Offline and Online Decisions
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2017
Maximum Margin Clustering Made Practical
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2009
Incorporating the Loss Function Into Discriminative Clustering of Structured Outputs
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2010
Automatic image tagging via category label and web data
Publisher: ACM
Date: 25-10-2010
Understanding Deep Representations Learned in Modeling Users Likes
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2016
Simpler core vector machines with enclosing balls
Publisher: ACM
Date: 20-06-2007
Memetic Search With Interdomain Learning: A Realization Between CVRP and CARP
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2015
A Unified Feature Selection Framework for Graph Embedding on High Dimensional Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2015
Compact Multiple-Instance Learning
Publisher: ACM
Date: 06-11-2017
Video Concept Detection Using Support Vector Machine with Augmented Features
Publisher: IEEE
Date: 11-2010
Multi-instance dictionary learning via multivariate performance measure optimization
Publisher: Elsevier BV
Date: 06-2017
DEFEATnet—A Deep Conventional Image Representation for Image Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2016
Discrete ranking-based matrix factorization with self-paced learnings
Publisher: ACM
Date: 19-07-2018
Healing Sample Selection Bias by Source Classifier Selection
Publisher: IEEE
Date: 12-2011
DOI: 10.1109/ICDM.2011.73
Online Product Quantization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
MTKDN: Multi-Task Knowledge Disentanglement Network for Recommendation
Publisher: ACM
Date: 21-10-2023
Concurrent Single-Label Image Classification and Annotation via Efficient Multi-Layer Group Sparse Coding
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2014
Matching Pursuit LASSO Part II: Applications and Sparse Recovery Over Batch Signals
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2015
Objects co-segmentation: Propagated from simpler images
Publisher: IEEE
Date: 04-2015
‘Who Likes What and, Why?’ Insights into Modeling Users’ Personality Based on Image ‘Likes’
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Domain Adaptation From Multiple Sources: A Domain-Dependent Regularization Approach
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2012
Visual event recognition in videos by learning from web data
Publisher: IEEE
Date: 06-2010
Domain Transfer Multiple Kernel Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2012
DifFormer: Multi-Resolutional Differencing Transformer With Dynamic Ranging for Time Series Analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Co-Labeling for Multi-View Weakly Labeled Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2016
Position estimation for wireless sensor networks
Publisher: IEEE
Date: 2005
Pareto Rank Learning in Multi-objective Evolutionary Algorithms
Publisher: IEEE
Date: 06-2012
Tag-based web photo retrieval improved by batch mode re-tagging
Publisher: IEEE
Date: 06-2010
Matching Pursuit LASSO Part I: Sparse Recovery Over Big Dictionary
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2015
On the Convergence of a Family of Robust Losses for Stochastic Gradient Descent
Publisher: Springer International Publishing
Date: 2016
Discovering User Interests from Social Images
Publisher: Springer International Publishing
Date: 31-12-2016
Transductive Ordinal Regression
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2012
Batch mode Adaptive Multiple Instance Learning for computer vision tasks
Publisher: IEEE
Date: 06-2012
Related Organisations
Nanyang Technological University Singapore Center For Computational Intelligence
Location: Singapore
University Of Technology Sydney: Broadway, NSW, Australia
Location: Australia
Related Funding Activities
Towards Interpretable Deep Learning With Limited Examples
Start Date: 2018
End Date: 2020
Funder: Australian Research Council
View Funded ActivityInteraction Mining For Cyberbullying Detection On Social Networks
Start Date: 2015
End Date: 2017
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP200101328
Start Date: 2020
End Date: 12-2023
Amount: $390,000.00
Funder: Australian Research Council
View Funded ActivityARC Future Fellowships - Grant ID: FT130100746
Start Date: 03-2014
End Date: 05-2019
Amount: $624,616.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP150100671
Start Date: 06-2016
End Date: 12-2019
Amount: $550,000.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP180100106
Start Date: 2018
End Date: 12-2021
Amount: $392,884.00
Funder: Australian Research Council
View Funded Activity