no code implementations • 7 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.
no code implementations • 12 Mar 2013 • Conrad Sanderson, Mehrtash T. Harandi, Yongkang Wong, Brian C. Lovell
In contrast to comparing faces via single exemplars, matching sets of face images increases robustness and discrimination performance.
no code implementations • 25 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.
Ranked #2 on Hand Gesture Recognition on Cambridge
no code implementations • 26 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.
no code implementations • 3 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.
no code implementations • 3 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.
no code implementations • 4 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.
no code implementations • 4 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.
no code implementations • 8 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.
1 code implementation • 16 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.
no code implementations • CVPR 2013 • Shaokang Chen, Conrad Sanderson, Mehrtash T. Harandi, Brian C. Lovell
We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold.
no code implementations • 18 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.
no code implementations • 31 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.
no code implementations • 3 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.
no code implementations • 3 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.
no code implementations • 3 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.
no code implementations • 4 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.
no code implementations • 4 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.
no code implementations • 5 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.
no code implementations • 15 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.
no code implementations • 9 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.
no code implementations • 19 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.
no code implementations • 11 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.
no code implementations • 30 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.
no code implementations • 6 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.
no code implementations • 27 Feb 2015 • ZongYuan Ge, Chris McCool, Conrad Sanderson, Peter Corke
We propose a local modelling approach using deep convolutional neural networks (CNNs) for fine-grained image classification.
no code implementations • 9 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.
no code implementations • 30 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).
no code implementations • 4 Feb 2016 • Johanna Carvajal, Arnold Wiliem, Chris McCool, Brian Lovell, Conrad Sanderson
We evaluate these action recognition techniques under ideal conditions, as well as their sensitivity in more challenging conditions (variations in scale and translation).
no code implementations • 4 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.
no code implementations • 26 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?
no code implementations • 1 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.
no code implementations • 28 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.
no code implementations • 25 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.
1 code implementation • 22 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.
no code implementations • 8 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.
no code implementations • 9 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.
no code implementations • 14 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.
no code implementations • 19 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.
no code implementations • 25 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.
no code implementations • 18 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.
no code implementations • 14 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.
no code implementations • 17 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.
no code implementations • 2 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.
no code implementations • 17 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.
no code implementations • 10 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.
no code implementations • 11 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.
no code implementations • 16 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.