Outputs (120)

STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising (2021)
Conference Proceeding
Zhou, K., Cheng, Z., Shum, H. P., Li, F. W., & Liang, X. (2021). STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising. . https://doi.org/10.1109/ismar52148.2021.00018

Hand object interaction in mixed reality (MR) relies on the accurate tracking and estimation of human hands, which provide users with a sense of immersion. However, raw captured hand motion data always contains errors such as joints occlusion, disloc... Read More about STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising.

Human-centric Autonomous Driving in an AV-Pedestrian Interactive Environment Using SVO (2021)
Conference Proceeding
Crosato, L., Wei, C., Ho, E. S., & Shum, H. P. (2021). Human-centric Autonomous Driving in an AV-Pedestrian Interactive Environment Using SVO. . https://doi.org/10.1109/ichms53169.2021.9582640

As Autonomous Vehicles (AV) are becoming a reality, the design of efficient motion control algorithms will have to deal with the unpredictable and interactive nature of other road users. Current AV motion planning algorithms suffer from the freezing... Read More about Human-centric Autonomous Driving in an AV-Pedestrian Interactive Environment Using SVO.

Privacy & Cloud Services: Are We There Yet? (2021)
Conference Proceeding
Marikyan, D., Llanos, J., Barati, M., Aujla, G. S., Li, Y., Adu-Duodu, K., …Carr, M. (2021). Privacy & Cloud Services: Are We There Yet?. . https://doi.org/10.1109/sose52839.2021.00006

The General Data Protection Regulation (GDPR) remains an important requirement for many electronic services which utilise user data. GDPR compliance verification for a cloud provider is aimed to confirm that personal data provided by a user is shared... Read More about Privacy & Cloud Services: Are We There Yet?.

Two musical episodes at the piano keyboard in the study of human information-processing: Information as ‘cognitive good’ in interdisciplinary research (2021)
Conference Proceeding
Bell, E. (2021). Two musical episodes at the piano keyboard in the study of human information-processing: Information as ‘cognitive good’ in interdisciplinary research.

In the early 1950s, the biologist Henry Quastler asked pianists to sight-read randomly generated musical scores as quickly and as accurately as possible. Quastler computed their performance as their “information transmission rate,” measured in bits-p... Read More about Two musical episodes at the piano keyboard in the study of human information-processing: Information as ‘cognitive good’ in interdisciplinary research.

Infinite Balanced Allocation via Finite Capacities (2021)
Conference Proceeding
Berenbrink, P., Friedetzky, T., Hahn, C., Hintze, L., Kaaser, D., Kling, P., & Nagel, L. (2021). Infinite Balanced Allocation via Finite Capacities. . https://doi.org/10.1109/icdcs51616.2021.00096

We analyze the following infinite load balancing process, modeled as a classical balls-into-bins game: There are n bins (servers) with a limited capacity (buffer) of size c=c(n)∈N . Given a fixed arrival rate λ=λ(n)∈(0,1) , in every round λn new ball... Read More about Infinite Balanced Allocation via Finite Capacities.

PANDA: Perceptually Aware Neural Detection of Anomalies (2021)
Conference Proceeding
Barker, J., & Breckon, T. (2021). PANDA: Perceptually Aware Neural Detection of Anomalies. . https://doi.org/10.1109/ijcnn52387.2021.9534399

Semi-supervised methods of anomaly detection have seen substantial advancement in recent years. Of particular interest are applications of such methods to diverse, real-world anomaly detection problems where anomalous variations can vary from the vis... Read More about PANDA: Perceptually Aware Neural Detection of Anomalies.

On the Evaluation of Semi-Supervised 2D Segmentation for Volumetric 3D Computed Tomography Baggage Security Screening (2021)
Conference Proceeding
Wang, Q., & Breckon, T. (2021). On the Evaluation of Semi-Supervised 2D Segmentation for Volumetric 3D Computed Tomography Baggage Security Screening. In 2021 International Joint Conference on Neural Networks (IJCNN) Proceedings. https://doi.org/10.1109/ijcnn52387.2021.9533631

We address the automatic contraband material detection problem within volumetric 3D Computed Tomography (CT) data for baggage security screening. Distinct from the prohibited item detection using object detection techniques, contraband material detec... Read More about On the Evaluation of Semi-Supervised 2D Segmentation for Volumetric 3D Computed Tomography Baggage Security Screening.

A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data (2021)
Conference Proceeding
Sun, Z., Harit, A., Yu, J., Cristea, A., & Al Moubayed, N. (2021). A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data. . https://doi.org/10.1109/ijcnn52387.2021.9533981

This research focuses on semi-supervised classification tasks, specifically for graph-structured data under datascarce situations. It is known that the performance of conventional supervised graph convolutional models is mediocre at classification ta... Read More about A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data.

Autoencoders Without Reconstruction for Textural Anomaly Detection (2021)
Conference Proceeding
Adey, P., Akcay, S., Bordewich, M., & Breckon, T. (2021). Autoencoders Without Reconstruction for Textural Anomaly Detection. . https://doi.org/10.1109/ijcnn52387.2021.9533804

Automatic anomaly detection in natural textures is a key component within quality control for a range of high-speed, high-yield manufacturing industries that rely on camera-based visual inspection techniques. Targeting anomaly detection through the u... Read More about Autoencoders Without Reconstruction for Textural Anomaly Detection.

Acyclic, star and injective colouring: bounding the diameter (2021)
Conference Proceeding
Brause, C., Golovach, P., Martin, B., Paulusma, D., & Smith, S. (2021). Acyclic, star and injective colouring: bounding the diameter. In Ł. Kowalik, M. Pilipczuk, & P. Rzążewski (Eds.), Graph-Theoretic Concepts in Computer Science: 47th International Workshop, WG 2021, Warsaw, Poland, June 23–25, 2021, Revised Selected Papers (336-348). https://doi.org/10.1007/978-3-030-86838-3_26

We examine the effect of bounding the diameter for wellstudied variants of the Colouring problem. A colouring is acyclic, star, or injective if any two colour classes induce a forest, star forest or disjoint union of vertices and edges, respectively.... Read More about Acyclic, star and injective colouring: bounding the diameter.