ORCID Profile
0000-0002-6937-6300
Current Organisation
Monash University
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)
Cybersecurity and privacy not elsewhere classified | Signal Processing | Deep learning | Computer Graphics | Computer vision | Machine learning | Computer Vision | Artificial Intelligence and Image Processing
ANZSRC Socio-Economic Objective (SEO)
Manufacturing not elsewhere classified | Electronic Information Storage and Retrieval Services | Animation and Computer Generated Imagery Services |
Related Links
Publications
Dictionary learning and sparse coding on Grassmann Manifolds: An extrinsic solution
Publisher: IEEE
Date: 12-2013
A Differentiable Distance Approximation for Fairer Image Classification
Publisher: Springer Nature Switzerland
Date: 2023
A hybrid model for face recognition using facial components
Publisher: IEEE
Date: 02-2007
Devon: Deformable volume network for learning optical flow
Publisher: IEEE
Date: 03-2020
Multi-shot person re-identification via relational Stein divergence
Publisher: IEEE
Date: 09-2013
Optimizing over radial kernels on compact manifolds
Publisher: IEEE
Date: 06-2014
Material Classification on Symmetric Positive Definite Manifolds
Publisher: IEEE
Date: 2015
Dual-Channel Circuit Mapping Reveals Sensorimotor Convergence in the Primary Motor Cortex
Publisher: Society for Neuroscience
Date: 11-03-2015
DOI: 10.1523/JNEUROSCI.3741-14.2015
Abstract: Cortical cells integrate synaptic input from multiple sources, but how these different inputs are distributed across in idual neurons is largely unknown. Differences in input might account for erse responses in neighboring neurons during behavior. We present a strategy for comparing the strengths of multiple types of input onto the same neuron. We developed methods for independent dual-channel photostimulation of synaptic inputs using ChR2 together with ReaChR, a red-shifted channelrhodopsin. We used dual-channel photostimulation to probe convergence of sensory information in the mouse primary motor cortex. Input from somatosensory cortex and thalamus converges in in idual neurons. Similarly, inputs from distinct somatotopic regions of the somatosensory cortex are integrated at the level of single motor cortex neurons. We next developed a ReaChR transgenic mouse under the control of both Flp- and Cre-recombinases that is an effective tool for circuit mapping. Our approach to dual-channel photostimulation enables quantitative comparison of the strengths of multiple pathways across all length scales of the brain.
Combined Learning of Salient Local Descriptors and Distance Metrics for Image Set Face Verification
Publisher: IEEE
Date: 09-2012
DOI: 10.1109/AVSS.2012.23
On Modulating the Gradient for Meta-learning
Publisher: Springer International Publishing
Date: 2020
Improved image set classification via joint sparse approximated nearest subspaces
Publisher: IEEE
Date: 06-2013
DOI: 10.1109/CVPR.2013.65
Novelty detection in human tracking based on spatiotemporal oriented energies
Publisher: Elsevier BV
Date: 03-2015
Generalized rank pooling for activity recognition
Publisher: IEEE
Date: 07-2017
A Robust Distance Measure for Similarity-Based Classification on the SPD Manifold
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2020
Expanding the family of Grassmannian kernels: An embedding perspective
Publisher: Springer International Publishing
Date: 2014
Image-set face recognition based on transductive learning
Publisher: IEEE
Date: 09-2010
Bregman divergences for infinite dimensional covariance matrices
Publisher: IEEE
Date: 06-2014
Ensemble Learning for Object Recognition and Tracking
Publisher: Springer Berlin Heidelberg
Date: 2011
Optimal Local Basis: A Reinforcement Learning Approach for Face Recognition
Publisher: Springer Science and Business Media LLC
Date: 19-08-2008
Sparse coding and dictionary learning for symmetric positive definite matrices: A kernel approach
Publisher: Springer Berlin Heidelberg
Date: 2012
Face recognition from still images to video sequences: A local-feature-based framework
Publisher: Springer Science and Business Media LLC
Date: 2011
DOI: 10.1155/2011/790598
Learning from noisy labels via discrepant collaborative training
Publisher: IEEE
Date: 03-2020
Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Publisher: Springer International Publishing
Date: 2021
Ensemble of furthest subspace pairs for enhanced image set matching
Publisher: IEEE
Date: 09-2011
Learning Log-Determinant Divergences for Positive Definite Matrices
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Geometry Aware Constrained Optimization Techniques for Deep Learning
Publisher: IEEE
Date: 06-2018
Devon: Deformable volume network for learning optical flow
Publisher: Springer International Publishing
Date: 2019
Bilinear Attention Networks for Person Retrieval
Publisher: IEEE
Date: 10-2019
M2SGD: Learning to Learn Important Weights
Publisher: IEEE
Date: 06-2020
Riemannian coding and dictionary learning: Kernels to the rescue
Publisher: IEEE
Date: 06-2015
Curved Geometric Networks for Visual Anomaly Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Numerical calibration of the HCN-star formation correlation
Publisher: Oxford University Press (OUP)
Date: 23-06-2018
Image set classification by symmetric positive semi-definite matrices
Publisher: IEEE
Date: 03-2016
Curvature-Adaptive Meta-Learning for Fast Adaptation to Manifold Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2023
Learning Domain Invariant Embeddings by Matching Distributions
Publisher: Springer International Publishing
Date: 2017
Using temporal information for recognizing actions from still images
Publisher: Elsevier BV
Date: 12-2019
Impulse noise removal based on long-range correlation in an image
Publisher: IEEE
Date: 2003
Semi-Supervised Domain Adaptation via Asymmetric Joint Distribution Matching
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2021
Cross-Correlated Attention Networks for Person Re-Identification
Publisher: Elsevier BV
Date: 08-2020
Scalable deep k-subspace clustering
Publisher: Springer International Publishing
Date: 2019
Machine learning applications in computer vision
Publisher: IGI Global
Date: 2012
DOI: 10.4018/978-1-4666-1833-6.CH007
Abstract: Recognizing objects based on their appearance (visual recognition) is one of the most significant abilities of many living creatures. In this study, recent advances in the area of automated object recognition are reviewed the authors specifically look into several learning frameworks to discuss how they can be utilized in solving object recognition paradigms. This includes reinforcement learning, a biologically-inspired machine learning technique to solve sequential decision problems and transductive learning, and a framework where the learner observes query data and potentially exploits its structure for classification. The authors also discuss local and global appearance models for object recognition, as well as how similarities between objects can be learnt and evaluated.
Learning to Optimize on Riemannian Manifolds
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Constrained Stochastic Gradient Descent: The Good Practice
Publisher: IEEE
Date: 11-2017
Sparse Coding on Symmetric Positive Definite Manifolds Using Bregman Divergences
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2016
Learning Discriminative αβ-Divergences for Positive Definite Matrices
Publisher: IEEE
Date: 10-2017
Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond
Publisher: Springer International Publishing
Date: 2018
Characterizing Subtle Facial Movements via Riemannian Manifold
Publisher: Association for Computing Machinery (ACM)
Date: 30-11-2019
DOI: 10.1145/3342227
Abstract: Characterizing subtle facial movements from videos is one of the most intensive topics in computer vision research. It is, however, challenging, since (1) the intensity of subtle facial muscle movement is usually low, (2) the duration may be transient, and (3) datasets containing spontaneous subtle movements with reliable annotations are painful to obtain and often of small sizes. This article is targeted at addressing these problems for characterizing subtle facial movements from both the aspects of motion elucidation and description. First, we propose an efficient method for elucidating hidden and repressed movements to make them easier to get noticed. We explore the feasibility of linearizing motion magnification and temporal interpolation, which is obscured by the architecture of existing methods. On this basis, we propose a consolidated framework, termed MOTEL, to expand temporal duration and lify subtle facial movements simultaneously. Second, we make our contribution to dynamic description. One major challenge is to capture the intrinsic temporal variations caused by movements and omit extrinsic ones caused by different in iduals and various environments. To diminish the influences of such extrinsic ersity, we propose the tangent delta descriptor to characterize the dynamics of short-term movements using the differences between points on the tangent spaces to the manifolds, rather than the points themselves. We then relax the trajectory-smooth assumption of the conventional manifold-based trajectory modeling methods and incorporate the tangent delta descriptor with the sequential inference approaches to cover the period of facial movements. The proposed motion modeling approach is validated by a series of experiments on publicly available datasets in the tasks of micro-expression recognition and visual speech recognition .
Face recognition using reinforcement learning
Publisher: IEEE
Date: 2004
Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning
Publisher: Springer Nature Switzerland
Date: 2022
Sparse Coding and Dictionary Learning with Linear Dynamical Systems
Publisher: IEEE
Date: 06-2016
Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs
Publisher: IEEE
Date: 12-2015
Domain Adaptation on the Statistical Manifold
Publisher: IEEE
Date: 06-2014
Multimorbidity Content-Based Medical Image Retrieval and Disease Recognition Using Multi-Label Proxy Metric Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Unsupervised Domain Adaptation by Domain Invariant Projection
Publisher: IEEE
Date: 12-2013
Large-Scale Metric Learning: A Voyage From Shallow to Deep
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
Siamese networks: The tale of two manifolds
Publisher: IEEE
Date: 10-2019
On robust face recognition via sparse coding: The good, the bad and the ugly
Publisher: Institution of Engineering and Technology (IET)
Date: 12-2014
Toward Efficient Action Recognition: Principal Backpropagation for Training Two-Stream Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Left frontal hub connectivity delays cognitive impairment in autosomal-dominant and sporadic Alzheimer’s disease
Publisher: Oxford University Press (OUP)
Date: 15-02-2018
DOI: 10.1093/BRAIN/AWY008
A Comprehensive Look at Coding Techniques on Riemannian Manifolds
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2018
Directed Random Subspace Method for Face Recognition
Publisher: IEEE
Date: 08-2010
Relational divergence based classification on Riemannian manifolds
Publisher: IEEE
Date: 2013
K-tangent spaces on Riemannian manifolds for improved pedestrian detection
Publisher: IEEE
Date: 09-2012
Spatio-temporal covariance descriptors for action and gesture recognition
Publisher: IEEE
Date: 2013
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
Publisher: IEEE
Date: 06-2013
DOI: 10.1109/CVPR.2013.17
No fuss metric learning, a Hilbert space scenario
Publisher: Elsevier BV
Date: 10-2017
On robust biometric identity verification via sparse encoding of faces: Holistic vs local approaches
Publisher: IEEE
Date: 06-2012
Approximate infinite-dimensional Region Covariance Descriptors for image classification
Publisher: IEEE
Date: 04-2015
Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds
Publisher: Springer Science and Business Media LLC
Date: 07-06-2015
Discriminative Non-Linear Stationary Subspace Analysis for Video Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2014
Learning to optimize on SPD manifolds
Publisher: IEEE
Date: 06-2020
More about VLAD: A leap from Euclidean to Riemannian manifolds
Publisher: IEEE
Date: 06-2015
Attention in Attention Networks for Person Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Adaptive subspaces for few-shot learning
Publisher: IEEE
Date: 06-2020
Domain Neural Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Dictionary Learning on Grassmann Manifolds
Publisher: Springer International Publishing
Date: 2016
Domain Adaptation by Joint Distribution Invariant Projections
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Going deeper into action recognition
Publisher: Elsevier BV
Date: 04-2017
Coordinate coding on the riemannian manifold of symmetric positive-definite matrices for image classification
Publisher: Springer International Publishing
Date: 2015
Min-Max Statistical Alignment for Transfer Learning
Publisher: IEEE
Date: 06-2019
Discrepant collaborative training by Sinkhorn divergences
Publisher: Elsevier BV
Date: 08-2021
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Publisher: IEEE
Date: 06-2018
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation
Publisher: Springer Science and Business Media LLC
Date: 13-07-2023
Machine learning applications in computer vision
Publisher: IGI Global
Date: 2013
DOI: 10.4018/978-1-4666-3994-2.CH045
Abstract: Recognizing objects based on their appearance (visual recognition) is one of the most significant abilities of many living creatures. In this study, recent advances in the area of automated object recognition are reviewed the authors specifically look into several learning frameworks to discuss how they can be utilized in solving object recognition paradigms. This includes reinforcement learning, a biologically-inspired machine learning technique to solve sequential decision problems and transductive learning, and a framework where the learner observes query data and potentially exploits its structure for classification. The authors also discuss local and global appearance models for object recognition, as well as how similarities between objects can be learnt and evaluated.
Combining multiple manifold-valued descriptors for improved object recognition
Publisher: IEEE
Date: 11-2013
Directional space-time oriented gradients for 3D visual pattern analysis
Publisher: Springer Berlin Heidelberg
Date: 2012
From manifold to manifold: Geometry-aware dimensionality reduction for SPD matrices
Publisher: Springer International Publishing
Date: 2014
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2015
A Hierarchical Face Identification System Based on Facial Components
Publisher: IEEE
Date: 05-2007
Learning an invariant Hilbert space for domain adaptation
Publisher: IEEE
Date: 07-2017
Learning Saliency from Single Noisy Labelling: A Robust Model Fitting Perspective
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
A view of 21st century healthcare industry and software quality improvement practices
Publisher: Inderscience Publishers
Date: 2011
An Input Residual Connection for Simplifying Gated Recurrent Neural Networks
Publisher: IEEE
Date: 07-2020
Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
A framework for shape analysis via hilbert space embedding
Publisher: IEEE
Date: 12-2013
Related Organisations
Related Funding Activities
Discovery Projects - Grant ID: DP150104645
Start Date: 06-2015
End Date: 03-2019
Amount: $370,100.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP230101176
Start Date: 2023
End Date: 12-2025
Amount: $420,000.00
Funder: Australian Research Council
View Funded Activity