Professor Hubert Shum's Outputs (16)

Bi-projection-based Foreground-aware Omnidirectional Depth Prediction (2021)
Presentation / Conference Contribution
Feng, Q., Shum, H. P., & Morishima, S. (2023, September). Bi-projection-based Foreground-aware Omnidirectional Depth Prediction. Presented at Visual Computing 2021, Online

Due to the increasing availability of commercial 360- degree cameras, accurate depth prediction for omnidirectional images can be beneficial to a wide range of applications including video editing and augmented reality. Regarding existing methods, so... Read More about Bi-projection-based Foreground-aware Omnidirectional Depth Prediction.

DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications (2021)
Presentation / Conference Contribution
Li, L., Ismail, K. N., Shum, H. P., & Breckon, T. P. (2021, December). DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications. Presented at International Conference on 3D Vision, Surrey / Online

We present DurLAR, a high-fidelity 128-channel 3D LiDAR dataset with panoramic ambient (near infrared) and reflectivity imagery, as well as a sample benchmark task using depth estimation for autonomous driving applications. Our driving platform is eq... Read More about DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications.

Semantics-STGCNN: A Semantics-guided Spatial-Temporal Graph Convolutional Network for Multi-class Trajectory Prediction (2021)
Presentation / Conference Contribution
Rainbow, B. A., Men, Q., & Shum, H. P. (2021, October). Semantics-STGCNN: A Semantics-guided Spatial-Temporal Graph Convolutional Network for Multi-class Trajectory Prediction. Presented at 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Melbourne, Australia

Predicting the movement trajectories of multiple classes of road users in real-world scenarios is a challenging task due to the diverse trajectory patterns. While recent works of pedestrian trajectory prediction successfully modelled the influence of... Read More about Semantics-STGCNN: A Semantics-guided Spatial-Temporal Graph Convolutional Network for Multi-class Trajectory Prediction.

A Pose-based Feature Fusion and Classification Framework for the Early Prediction of Cerebral Palsy in Infants (2021)
Journal Article
McCay, K. D., Hu, P., Shum, H. P., Woo, W. L., Marcroft, C., Embleton, N. D., Munteanu, A., & Ho, E. S. (2022). A Pose-based Feature Fusion and Classification Framework for the Early Prediction of Cerebral Palsy in Infants. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30, 8-19. https://doi.org/10.1109/tnsre.2021.3138185

The early diagnosis of cerebral palsy is an area which has recently seen significant multi-disciplinary research. Diagnostic tools such as the General Movements Assessment (GMA), have produced some very promising results. However, the prospect of aut... Read More about A Pose-based Feature Fusion and Classification Framework for the Early Prediction of Cerebral Palsy in Infants.

PyTorch-based Implementation of Label-aware Graph Representation for Multi-class Trajectory Prediction (2021)
Journal Article
Men, Q., & Shum, H. P. (2022). PyTorch-based Implementation of Label-aware Graph Representation for Multi-class Trajectory Prediction. Software impacts, 11, Article 100201. https://doi.org/10.1016/j.simpa.2021.100201

Trajectory Prediction under diverse patterns has attracted increasing attention in multiple real-world applications ranging from urban traffic analysis to human motion understanding, among which graph convolution network (GCN) is frequently adopted w... Read More about PyTorch-based Implementation of Label-aware Graph Representation for Multi-class Trajectory Prediction.

Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark (2021)
Presentation / Conference Contribution
Isaac-Medina, B. K., Poyser, M., Organisciak, D., Willcocks, C. G., Breckon, T. P., & Shum, H. P. (2021, October). Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark. Presented at 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, Canada

Unmanned Aerial Vehicles (UAV) can pose a major risk for aviation safety, due to both negligent and malicious use. For this reason, the automated detection and tracking of UAV is a fundamental task in aerial security systems. Common technologies for... Read More about Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark.

STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising (2021)
Presentation / Conference Contribution
Zhou, K., Cheng, Z., Shum, H. P., Li, F. W., & Liang, X. (2021, October). STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising. Presented at 2021 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Bari, Italy

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)
Presentation / Conference Contribution
Crosato, L., Wei, C., Ho, E. S., & Shum, H. P. (2021, September). Human-centric Autonomous Driving in an AV-Pedestrian Interactive Environment Using SVO. Presented at IEEE ICHMS 2021 - 2nd IEEE International Conference on Human-Machine Systems, Magdeburg, Germany

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.

GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction (2021)
Journal Article
Men, Q., Shum, H. P., Ho, E. S., & Leung, H. (2022). GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction. Computers and Graphics, 102, 634-645. https://doi.org/10.1016/j.cag.2021.09.014

Creating realistic characters that can react to the users’ or another character’s movement can benefit computer graphics, games and virtual reality hugely. However, synthesizing such reactive motions in human-human interactions is a challenging task... Read More about GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction.

Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention (2021)
Presentation / Conference Contribution
Zhu, M., Men, Q., Ho, E. S., Leung, H., & Shum, H. P. (2021, July). Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention. Presented at 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Athens, Greece

Early prediction of cerebral palsy is essential as it leads to early treatment and monitoring. Deep learning has shown promising results in biomedical engineering thanks to its capacity of modelling complicated data with its non-linear architecture.... Read More about Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention.

Spoofing Detection on Hand Images Using Quality Assessment (2021)
Journal Article
Bera, A., Dey, R., Bhattacharjee, D., Nasipuri, M. *., & Shum, H. (2021). Spoofing Detection on Hand Images Using Quality Assessment. Multimedia Tools and Applications, 80(19), 28603-28626. https://doi.org/10.1007/s11042-021-10976-z

Recent research on biometrics focuses on achieving a high success rate of authentication and addressing the concern of various spoofing attacks. Although hand geometry recognition provides adequate security over unauthorized access, it is susceptible... Read More about Spoofing Detection on Hand Images Using Quality Assessment.

Stable Hand Pose Estimation under Tremor via Graph Neural Network (2021)
Presentation / Conference Contribution
Leng, Z., Chen, J., Shum, H. P., Li, F. W., & Liang, X. (2021, March). Stable Hand Pose Estimation under Tremor via Graph Neural Network. Presented at 2021 IEEE Virtual Reality and 3D User Interfaces (VR), Lisboa

Hand pose estimation, which predicts the spatial location of hand joints, is a fundamental task in VR/AR applications. Although existing methods can recover hand pose competently, the tremor issue occurring in hand motion has not been completely solv... Read More about Stable Hand Pose Estimation under Tremor via Graph Neural Network.

Makeup Style Transfer on Low-quality Images with Weighted Multi-scale Attention (2021)
Presentation / Conference Contribution
Organisciak, D., Ho, E. S., & Shum, H. P. (2021, January). Makeup Style Transfer on Low-quality Images with Weighted Multi-scale Attention. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy

Facial makeup style transfer is an extremely challenging sub-field of image-to-image-translation. Due to this difficulty, state-of-the-art results are mostly reliant on the Face Parsing Algorithm, which segments a face into parts in order to easily e... Read More about Makeup Style Transfer on Low-quality Images with Weighted Multi-scale Attention.

A Two-Stream Recurrent Network for Skeleton-based Human Interaction Recognition (2021)
Presentation / Conference Contribution
Men, Q., Hoy, E. S., Shum, H. P., & Leung, H. (2021, January). A Two-Stream Recurrent Network for Skeleton-based Human Interaction Recognition. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy

This paper addresses the problem of recognizing human-human interaction from skeletal sequences. Existing methods are mainly designed to classify single human action. Many of them simply stack the movement features of two characters to deal with huma... Read More about A Two-Stream Recurrent Network for Skeleton-based Human Interaction Recognition.

3D car shape reconstruction from a contour sketch using GAN and lazy learning (2021)
Journal Article
Nozawa, N., Shum, H. P., Feng, Q., Ho, E. S., & Morishima, S. (2022). 3D car shape reconstruction from a contour sketch using GAN and lazy learning. Visual Computer, 38(4), 1317-1330. https://doi.org/10.1007/s00371-020-02024-y

3D car models are heavily used in computer games, visual effects, and even automotive designs. As a result, producing such models with minimal labour costs is increasingly more important. To tackle the challenge, we propose a novel system to reconstr... Read More about 3D car shape reconstruction from a contour sketch using GAN and lazy learning.

Two-stage human verification using HandCAPTCHA and anti-spoofed finger biometrics with feature selection (2021)
Journal Article
Bera, A., Bhattacharjee, D., & Shum, H. P. (2021). Two-stage human verification using HandCAPTCHA and anti-spoofed finger biometrics with feature selection. Expert Systems with Applications, 171, https://doi.org/10.1016/j.eswa.2021.114583

This paper presents a human verification scheme in two independent stages to overcome the vulnerabilities of attacks and to enhance security. At the first stage, a hand image-based CAPTCHA (HandCAPTCHA) is tested to avert automated bot-attacks on the... Read More about Two-stage human verification using HandCAPTCHA and anti-spoofed finger biometrics with feature selection.