Outputs (93)

LMZMPM: Local Modified Zernike Moment Per-unit Mass for Robust Human Face Recognition (2020)
Journal Article
Kar, A., Pramanik, S., Chakraborty, A., Bhattacharjee, D., Ho, E. S., & Shum, H. P. (2020). LMZMPM: Local Modified Zernike Moment Per-unit Mass for Robust Human Face Recognition. IEEE Transactions on Information Forensics and Security, 16, 495-509. https://doi.org/10.1109/tifs.2020.3015552

In this work, we proposed a novel method, called Local Modified Zernike Moment per unit Mass (LMZMPM), for face recognition, which is invariant to illumination, scaling, noise, in-plane rotation, and translation, along with other orthogonal and inher... Read More about LMZMPM: Local Modified Zernike Moment Per-unit Mass for Robust Human Face Recognition.

Cumuliform Cloud Formation Control using Parameter-Predicting Convolutional Neural Network (2020)
Journal Article
Zhang, Z., Ma, Y., Li, Y., Li, F. W., Shum, H. P., Yang, B., …Liang, X. (2020). Cumuliform Cloud Formation Control using Parameter-Predicting Convolutional Neural Network. Graphical Models, 111, Article 101083. https://doi.org/10.1016/j.gmod.2020.101083

Physically-based cloud simulation is an effective approach for synthesizing realistic cloud. However, generating clouds with desired shapes requires a time-consuming process for selecting the appropriate simulation parameters. This paper addresses su... Read More about Cumuliform Cloud Formation Control using Parameter-Predicting Convolutional Neural Network.

Sparse Metric-based Mesh Saliency (2020)
Journal Article
Hu, S., Liang, X., Shum, H. P., Li, F. W., & Aslam, N. (2020). Sparse Metric-based Mesh Saliency. Neurocomputing, 400, 11-23. https://doi.org/10.1016/j.neucom.2020.02.106

In this paper, we propose an accurate and robust approach to salient region detection for 3D polygonal surface meshes. The salient regions of a mesh are those that geometrically stand out from their contexts and therefore are semantically important f... Read More about Sparse Metric-based Mesh Saliency.

A Unified Deep Metric Representation for Mesh Saliency Detection and Non-rigid Shape Matching (2019)
Journal Article
Hu, S., Shum, H., Aslam, N., Li, F. W., & Liang, X. (2020). A Unified Deep Metric Representation for Mesh Saliency Detection and Non-rigid Shape Matching. IEEE Transactions on Multimedia, 22(9), 2278-2292. https://doi.org/10.1109/tmm.2019.2952983

In this paper, we propose a deep metric for unifying the representation of mesh saliency detection and non-rigid shape matching. While saliency detection and shape matching are two closely related and fundamental tasks in shape analysis, previous met... Read More about A Unified Deep Metric Representation for Mesh Saliency Detection and Non-rigid Shape Matching.

Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling (2019)
Journal Article
Wang, H., Ho, E. S., Shum, H. P., & Zhu, Z. (2021). Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling. IEEE Transactions on Visualization and Computer Graphics, 27(1), 216 - 227. https://doi.org/10.1109/tvcg.2019.2936810

Data-driven modeling of human motions is ubiquitous in computer graphics and vision applications. Such problems can be approached by deep learning on a large amount data. However, existing methods can be sub-optimal for two reasons. First, skeletal i... Read More about Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling.

Interaction-Based Human Activity Comparison (2019)
Journal Article
Shen, Y., Yang, L., Ho, E. S., & Shum, H. P. (2020). Interaction-Based Human Activity Comparison. IEEE Transactions on Visualization and Computer Graphics, 26(8), 2620-2633. https://doi.org/10.1109/tvcg.2019.2893247

Traditional methods for motion comparison consider features from individual characters. However, the semantic meaning of many human activities is usually defined by the interaction between them, such as a high-five interaction of two characters. Ther... Read More about Interaction-Based Human Activity Comparison.

Automatic Musculoskeletal and Neurological Disorder Diagnosis With Relative Joint Displacement From Human Gait (2018)
Journal Article
Rueangsirarak, W., Zhang, J., Aslam, N., Ho, E. S., & Shum, H. P. (2018). Automatic Musculoskeletal and Neurological Disorder Diagnosis With Relative Joint Displacement From Human Gait. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(12), 2387-2396. https://doi.org/10.1109/tnsre.2018.2880871

Musculoskeletal and neurological disorders are common devastating companions of ageing, leading to a reduction in quality of life and increased mortality. Gait analysis is a popular method for diagnosing these disorders. However, manually analyzing t... Read More about Automatic Musculoskeletal and Neurological Disorder Diagnosis With Relative Joint Displacement From Human Gait.

Action Recognition From Arbitrary Views Using Transferable Dictionary Learning (2018)
Journal Article
Zhang, J., Shum, H. P., Han, J., & Shao, L. (2018). Action Recognition From Arbitrary Views Using Transferable Dictionary Learning. IEEE Transactions on Image Processing, 27(10), 4709-4723. https://doi.org/10.1109/tip.2018.2836323

Human action recognition is crucial to many practical applications, ranging from human-computer interaction to video surveillance. Most approaches either recognize the human action from a fixed view or require the knowledge of view angle, which is us... Read More about Action Recognition From Arbitrary Views Using Transferable Dictionary Learning.

Data-Driven Crowd Motion Control With Multi-Touch Gestures (2018)
Journal Article
Shen, Y., Henry, J., Wang, H., Ho, E. S., Komura, T., & Shum, H. P. (2018). Data-Driven Crowd Motion Control With Multi-Touch Gestures. Computer Graphics Forum, 37(6), 382-394. https://doi.org/10.1111/cgf.13333

Manifold Regularized Experimental Design for Active Learning (2016)
Journal Article
Zhang, L., Shum, H. P., & Shao, L. (2017). Manifold Regularized Experimental Design for Active Learning. IEEE Transactions on Image Processing, 26(2), 969-981. https://doi.org/10.1109/tip.2016.2635440

Various machine learning and data mining tasks in classification require abundant data samples to be labeled for training. Conventional active learning methods aim at labeling the most informative samples for alleviating the labor of the user. Many p... Read More about Manifold Regularized Experimental Design for Active Learning.