Skip to main content

Research Repository

Advanced Search

Outputs (236)

Using theoretical ROC curves for analysing machine learning binary classifiers (2019)
Journal Article
Omar, L., & Ivrissimtzis, I. (2019). Using theoretical ROC curves for analysing machine learning binary classifiers. Pattern Recognition Letters, 128, 447-451. https://doi.org/10.1016/j.patrec.2019.10.004

Most binary classifiers work by processing the input to produce a scalar response and comparing it to a threshold value. The various measures of classifier performance assume, explicitly or implicitly, probability distributions Ps and Pn of the respo... Read More about Using theoretical ROC curves for analysing machine learning binary classifiers.

re-OBJ:Jointly learning the foreground and background for object instance re-identification (2019)
Presentation / Conference Contribution
James, S. (2019, September). re-OBJ:Jointly learning the foreground and background for object instance re-identification. Presented at Image Analysis and Processing – ICIAP 2019, Trento, Italy

Conventional approaches to object instance re-identification rely on matching appearances of the target objects among a set of frames. However, learning appearances of the objects alone might fail when there are multiple objects with similar appearan... Read More about re-OBJ:Jointly learning the foreground and background for object instance re-identification.

Lazy Stencil Integration in multigrid algorithms (2019)
Presentation / Conference Contribution
Murray, C., & Weinzierl, T. (2019, December). Lazy Stencil Integration in multigrid algorithms. Presented at 13th INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING AND APPLIED MATHEMATICS, Bialystok, Poland

2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling (2019)
Journal Article
Angelini, F., Fu, Z., Long, Y., Shao, L., & Naqvi, S. M. (2020). 2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling. IEEE Transactions on Multimedia, 22(6), 1433-1446. https://doi.org/10.1109/tmm.2019.2944745

Human Action Recognition (HAR) for CCTV-oriented applications is still a challenging problem. Real-world scenarios HAR implementations is difficult because of the gap between Deep Learning data requirements and what the CCTV-based frameworks can offe... Read More about 2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling.

DeGraF-Flow: Extending DeGraF Features for Accurate and Efficient Sparse-to-Dense Optical Flow Estimation (2019)
Presentation / Conference Contribution
Stephenson, F., Breckon, T., & Katramados, I. (2019, September). DeGraF-Flow: Extending DeGraF Features for Accurate and Efficient Sparse-to-Dense Optical Flow Estimation. Presented at 26th IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan

Modern optical flow methods make use of salient scene feature points detected and matched within the scene as a basis for sparse-to-dense optical flow estimation. Current feature detectors however either give sparse, non uniform point clouds (resulti... Read More about DeGraF-Flow: Extending DeGraF Features for Accurate and Efficient Sparse-to-Dense Optical Flow Estimation.

A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks (2019)
Presentation / Conference Contribution
Wang, Q., Ning, J., & Breckon, T. (2019, September). A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks. Presented at 26th IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan

Recent studies on multi-label image classification have focused on designing more complex architectures of deep neural networks such as the use of attention mechanisms and region proposal networks. Although performance gains have been reported, the b... Read More about A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks.

Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection (2019)
Presentation / Conference Contribution
Akcay, A., Atapour-Abarghouei, A., & Breckon, T. P. (2019, July). Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection. Presented at Proc. Int. Joint Conference on Neural Networks, Budapest, Hungary

Despite inherent ill-definition, anomaly detection is a research endeavour of great interest within machine learning and visual scene understanding alike. Most commonly, anomaly detection is considered as the detection of outliers within a given data... Read More about Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection.

Simple games versus weighted voting games: bounding the critical threshold value (2019)
Journal Article
Hof, F., Kern, W., Kurz, S., Pashkovich, K., & Paulusma, D. (2020). Simple games versus weighted voting games: bounding the critical threshold value. Social Choice and Welfare, 54(4), 609-621. https://doi.org/10.1007/s00355-019-01221-6

A simple game (N; v) is given by a set N of n players and a partition of 2N into a set L of losing coalitions L with value v(L) = 0 that is closed under taking subsets and a set W of winning coalitions W with value v(W) = 1. We let = minp>0;p6=0 maxW... Read More about Simple games versus weighted voting games: bounding the critical threshold value.

Clique-width and well-quasi ordering of triangle-free graph classes (2019)
Journal Article
Dabrowski, K., Lozin, V., & Paulusma, D. (2020). Clique-width and well-quasi ordering of triangle-free graph classes. Journal of Computer and System Sciences, 108, 64-91. https://doi.org/10.1016/j.jcss.2019.09.001

We obtain a complete classification of graphs H for which the class of -free graphs is well-quasi-ordered by the induced subgraph relation and an almost complete classification of graphs H for which the class of -free graphs has bounded clique-width.... Read More about Clique-width and well-quasi ordering of triangle-free graph classes.