Search Results for author: Conrad Sanderson

Found 48 papers, 2 papers with code

On Robust Face Recognition via Sparse Encoding: the Good, the Bad, and the Ugly

no code implementations7 Mar 2013 Yongkang Wong, Mehrtash T. Harandi, Conrad Sanderson

Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems.

Face Recognition Face Verification +1

Spatio-Temporal Covariance Descriptors for Action and Gesture Recognition

no code implementations25 Mar 2013 Andres Sanin, Conrad Sanderson, Mehrtash T. Harandi, Brian C. Lovell

We propose a new action and gesture recognition method based on spatio-temporal covariance descriptors and a weighted Riemannian locality preserving projection approach that takes into account the curved space formed by the descriptors.

General Classification Gesture Recognition +1

Video Face Matching using Subset Selection and Clustering of Probabilistic Multi-Region Histograms

no code implementations26 Mar 2013 Sandra Mau, Shaokang Chen, Conrad Sanderson, Brian C. Lovell

This paper presents a video face recognition system based on probabilistic Multi-Region Histograms to characterise performance trade-offs in: (i) selecting a subset of faces compared to using all faces, and (ii) combining information from all faces via clustering.

Clustering Computational Efficiency +3

Improved Anomaly Detection in Crowded Scenes via Cell-based Analysis of Foreground Speed, Size and Texture

no code implementations3 Apr 2013 Vikas Reddy, Conrad Sanderson, Brian C. Lovell

The motion and size features are modelled by an approximated version of kernel density estimation, which is computationally efficient even for large training datasets.

Anomaly Detection Density Estimation +2

Patch-based Probabilistic Image Quality Assessment for Face Selection and Improved Video-based Face Recognition

no code implementations3 Apr 2013 Yongkang Wong, Shaokang Chen, Sandra Mau, Conrad Sanderson, Brian C. Lovell

In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence.

Face Image Quality Face Image Quality Assessment +3

Shadow Detection: A Survey and Comparative Evaluation of Recent Methods

no code implementations4 Apr 2013 Andres Sanin, Conrad Sanderson, Brian C. Lovell

Furthermore, we propose the use of tracking performance as an unbiased approach for determining the practical usefulness of shadow detection methods.

object-detection Object Detection +2

Classification of Human Epithelial Type 2 Cell Indirect Immunofluoresence Images via Codebook Based Descriptors

no code implementations4 Apr 2013 Arnold Wiliem, Yongkang Wong, Conrad Sanderson, Peter Hobson, Shaokang Chen, Brian C. Lovell

In this paper, we propose a cell classification system comprised of a dual-region codebook-based descriptor, combined with the Nearest Convex Hull Classifier.

General Classification

Dynamic Amelioration of Resolution Mismatches for Local Feature Based Identity Inference

no code implementations8 Apr 2013 Yongkang Wong, Conrad Sanderson, Sandra Mau, Brian C. Lovell

While existing face recognition systems based on local features are robust to issues such as misalignment, they can exhibit accuracy degradation when comparing images of differing resolutions.

Face Recognition

Sparse Coding and Dictionary Learning for Symmetric Positive Definite Matrices: A Kernel Approach

1 code implementation16 Apr 2013 Mehrtash T. Harandi, Conrad Sanderson, Richard Hartley, Brian C. Lovell

Recent advances suggest that a wide range of computer vision problems can be addressed more appropriately by considering non-Euclidean geometry.

Dictionary Learning Face Recognition +3

Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution

no code implementations18 Oct 2013 Mehrtash Harandi, Conrad Sanderson, Chunhua Shen, Brian C. Lovell

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry.

Action Recognition Dictionary Learning +5

Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds

no code implementations31 Jan 2014 Mehrtash Harandi, Richard Hartley, Chunhua Shen, Brian Lovell, Conrad Sanderson

With the aim of building a bridge between the two realms, we address the problem of sparse coding and dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds.

Action Recognition Classification +6

Object Tracking via Non-Euclidean Geometry: A Grassmann Approach

no code implementations3 Mar 2014 Sareh Shirazi, Mehrtash T. Harandi, Brian C. Lovell, Conrad Sanderson

A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream.

Object Object Tracking +1

Matching Image Sets via Adaptive Multi Convex Hull

no code implementations3 Mar 2014 Shaokang Chen, Arnold Wiliem, Conrad Sanderson, Brian C. Lovell

We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set.

Clustering General Classification

Summarisation of Short-Term and Long-Term Videos using Texture and Colour

no code implementations3 Mar 2014 Johanna Carvajal, Chris McCool, Conrad Sanderson

We present a novel approach to video summarisation that makes use of a Bag-of-visual-Textures (BoT) approach.

Random Projections on Manifolds of Symmetric Positive Definite Matrices for Image Classification

no code implementations4 Mar 2014 Azadeh Alavi, Arnold Wiliem, Kun Zhao, Brian C. Lovell, Conrad Sanderson

Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance.

Face Recognition General Classification +3

Multi-Shot Person Re-Identification via Relational Stein Divergence

no code implementations4 Mar 2014 Azadeh Alavi, Yan Yang, Mehrtash Harandi, Conrad Sanderson

The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately.

General Classification Person Re-Identification

K-Tangent Spaces on Riemannian Manifolds for Improved Pedestrian Detection

no code implementations5 Mar 2014 Andres Sanin, Conrad Sanderson, Mehrtash T. Harandi, Brian C. Lovell

For covariance-based image descriptors, taking into account the curvature of the corresponding feature space has been shown to improve discrimination performance.

Pedestrian Detection

Automatic Classification of Human Epithelial Type 2 Cell Indirect Immunofluorescence Images using Cell Pyramid Matching

no code implementations15 Mar 2014 Arnold Wiliem, Conrad Sanderson, Yongkang Wong, Peter Hobson, Rodney F. Minchin, Brian C. Lovell

This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol.

General Classification Image Classification

Log-Euclidean Bag of Words for Human Action Recognition

no code implementations9 Jun 2014 Masoud Faraki, Maziar Palhang, Conrad Sanderson

Representing videos by densely extracted local space-time features has recently become a popular approach for analysing actions.

Action Recognition Optical Flow Estimation +1

MRF-based Background Initialisation for Improved Foreground Detection in Cluttered Surveillance Videos

no code implementations19 Jun 2014 Vikas Reddy, Conrad Sanderson, Andres Sanin, Brian C. Lovell

Robust foreground object segmentation via background modelling is a difficult problem in cluttered environments, where obtaining a clear view of the background to model is almost impossible.

Object Tracking Semantic Segmentation

Bags of Affine Subspaces for Robust Object Tracking

no code implementations11 Aug 2014 Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash T. Harandi

We propose an adaptive tracking algorithm where the object is modelled as a continuously updated bag of affine subspaces, with each subspace constructed from the object's appearance over several consecutive frames.

Object Object Tracking

Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences

no code implementations30 Aug 2014 Mehrtash Harandi, Richard Hartley, Brian Lovell, Conrad Sanderson

This paper introduces sparse coding and dictionary learning for Symmetric Positive Definite (SPD) matrices, which are often used in machine learning, computer vision and related areas.

Action Recognition Dictionary Learning +4

Multi-Action Recognition via Stochastic Modelling of Optical Flow and Gradients

no code implementations6 Feb 2015 Johanna Carvajal, Conrad Sanderson, Chris McCool, Brian C. Lovell

In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification.

Action Recognition Classification +4

Subset Feature Learning for Fine-Grained Category Classification

no code implementations9 May 2015 Zongyuan Ge, Christopher Mccool, Conrad Sanderson, Peter Corke

Fine-grained categorisation has been a challenging problem due to small inter-class variation, large intra-class variation and low number of training images.

Classification General Classification +1

Fine-Grained Classification via Mixture of Deep Convolutional Neural Networks

no code implementations30 Nov 2015 ZongYuan Ge, Alex Bewley, Christopher Mccool, Ben Upcroft, Peter Corke, Conrad Sanderson

We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN).

Classification Fine-Grained Image Classification +1

Joint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors

no code implementations4 Feb 2016 Johanna Carvajal, Chris McCool, Brian Lovell, Conrad Sanderson

The final classification decision for each frame is then obtained by integrating the class probabilities at the frame level, which exploits the overlapping of the temporal windows.

Action Recognition General Classification +1

Towards Miss Universe Automatic Prediction: The Evening Gown Competition

no code implementations26 Apr 2016 Johanna Carvajal, Arnold Wiliem, Conrad Sanderson, Brian Lovell

Can we predict the winner of Miss Universe after watching how they stride down the catwalk during the evening gown competition?

Exploiting Temporal Information for DCNN-based Fine-Grained Object Classification

no code implementations1 Aug 2016 ZongYuan Ge, Chris McCool, Conrad Sanderson, Peng Wang, Lingqiao Liu, Ian Reid, Peter Corke

Fine-grained classification is a relatively new field that has concentrated on using information from a single image, while ignoring the enormous potential of using video data to improve classification.

Classification General Classification

An Open Source C++ Implementation of Multi-Threaded Gaussian Mixture Models, k-Means and Expectation Maximisation

no code implementations28 Jul 2017 Conrad Sanderson, Ryan Curtin

We provide an overview of a fast and robust implementation of GMMs in the C++ language, employing multi-threaded versions of the Expectation Maximisation (EM) and k-means training algorithms.

Diversified Late Acceptance Search

no code implementations25 Jun 2018 Majid Namazi, Conrad Sanderson, M. A. Hakim Newton, M. M. A. Polash, Abdul Sattar

The well-known Late Acceptance Hill Climbing (LAHC) search aims to overcome the main downside of traditional Hill Climbing (HC) search, which is often quickly trapped in a local optimum due to strictly accepting only non-worsening moves within each iteration.

ensmallen: a flexible C++ library for efficient function optimization

1 code implementation22 Oct 2018 Shikhar Bhardwaj, Ryan R. Curtin, Marcus Edel, Yannis Mentekidis, Conrad Sanderson

We present ensmallen, a fast and flexible C++ library for mathematical optimization of arbitrary user-supplied functions, which can be applied to many machine learning problems.

BIG-bench Machine Learning

A Cooperative Coordination Solver for Travelling Thief Problems

no code implementations8 Nov 2019 Majid Namazi, Conrad Sanderson, M. A. Hakim Newton, Abdul Sattar

A thief performs a cyclic tour through a set of cities, and pursuant to a collection plan, collects a subset of items into a rented knapsack with finite capacity.

Flexible numerical optimization with ensmallen

no code implementations9 Mar 2020 Ryan R. Curtin, Marcus Edel, Rahul Ganesh Prabhu, Suryoday Basak, Zhihao Lou, Conrad Sanderson

The library provides a fast and flexible C++ framework for mathematical optimization of arbitrary user-supplied functions.

Surrogate Assisted Optimisation for Travelling Thief Problems

no code implementations14 May 2020 Majid Namazi, Conrad Sanderson, M. A. Hakim Newton, Abdul Sattar

The TSP solution (cyclic tour) is typically changed in a deterministic way, while changes to the KP solution typically involve a random search, effectively resulting in a quasi-meandering exploration of the TTP solution space.

A Multi-UAV System for Exploration and Target Finding in Cluttered and GPS-Denied Environments

no code implementations19 Jul 2021 Xiaolong Zhu, Fernando Vanegas, Felipe Gonzalez, Conrad Sanderson

Performance of the system with an increasing number of UAVs in several indoor scenarios with obstacles is tested.

Opportunistic Emulation of Computationally Expensive Simulations via Deep Learning

no code implementations25 Aug 2021 Conrad Sanderson, Dan Pagendam, Brendan Power, Frederick Bennett, Ross Darnell

While the opportunistic data available from past modelling activities provides a large and useful dataset for exploring APSIM emulation, it may not be sufficiently rich enough for successful deep learning of more complex model dynamics.

Software Engineering for Responsible AI: An Empirical Study and Operationalised Patterns

no code implementations18 Nov 2021 Qinghua Lu, Liming Zhu, Xiwei Xu, Jon Whittle, David Douglas, Conrad Sanderson

These patterns provide concrete, operationalised guidance that facilitate the development of responsible AI systems.

Ethics

AI Ethics Principles in Practice: Perspectives of Designers and Developers

no code implementations14 Dec 2021 Conrad Sanderson, David Douglas, Qinghua Lu, Emma Schleiger, Jon Whittle, Justine Lacey, Glenn Newnham, Stefan Hajkowicz, Cathy Robinson, David Hansen

As consensus across the various published AI ethics principles is approached, a gap remains between high-level principles and practical techniques that can be readily adopted to design and develop responsible AI systems.

Ethics Fairness

A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models

no code implementations17 Jun 2022 Andrew Bolt, Carolyn Huston, Petra Kuhnert, Joel Janek Dabrowski, James Hilton, Conrad Sanderson

We propose a dedicated spatio-temporal neural network based framework for model emulation, able to capture the complex behaviour of fire spread models.

Data Augmentation

Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfires

no code implementations2 Dec 2022 Joel Janek Dabrowski, Daniel Edward Pagendam, James Hilton, Conrad Sanderson, Daniel MacKinlay, Carolyn Huston, Andrew Bolt, Petra Kuhnert

We show that popular optimisation cost functions used in the literature can result in PINNs that fail to maintain temporal continuity in modelled fire-fronts when there are extreme changes in exogenous forcing variables such as wind direction.

Uncertainty Quantification

Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects

no code implementations17 Apr 2023 Conrad Sanderson, David Douglas, Qinghua Lu

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems.

Ethics Fairness

A Neural Emulator for Uncertainty Estimation of Fire Propagation

no code implementations10 May 2023 Andrew Bolt, Conrad Sanderson, Joel Janek Dabrowski, Carolyn Huston, Petra Kuhnert

When compared to a related neural model (emulator) which was employed to generate probability maps via ensembles of emulated fires, the proposed approach produces competitive Jaccard similarity scores while being approximately an order of magnitude faster.

Solving Travelling Thief Problems using Coordination Based Methods

no code implementations11 Oct 2023 Majid Namazi, M. A. Hakim Newton, Conrad Sanderson, Abdul Sattar

In TTP, city selection and item selection decisions need close coordination since the thief's travelling speed depends on the knapsack's weight and the order of visiting cities affects the order of item collection.

Resolving Ethics Trade-offs in Implementing Responsible AI

no code implementations16 Jan 2024 Conrad Sanderson, Emma Schleiger, David Douglas, Petra Kuhnert, Qinghua Lu

While the operationalisation of high-level AI ethics principles into practical AI/ML systems has made progress, there is still a theory-practice gap in managing tensions between the underlying AI ethics aspects.

Ethics

Cannot find the paper you are looking for? You can Submit a new open access paper.