Zhengwei Wang

Zhengwei Wang

Auto-generated profile, based on publicly available information

Zhengwei Wang

Insight Centre for Data Analytics Dublin City University Dublin 9 Ireland

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 February 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
EBEoin Brophy
Eoin Brophy
ZWZhengwei Wang
Zhengwei Wang
QSQi She
Qi She
TWTomas Ward
Tomas Ward
Generative adversarial network (GAN) studies have grown exponentially in the past few years. Their impact has been seen mainly in the computer vision field with realistic image and video manipulation, especially generation, making significant advancements. Although these computer vision advances have garnered much attention, GAN applications have diversified across disciplines such as time series and sequence generation. As a relatively new niche for GANs, fieldwork is ongoing to develop high-quality, diverse, and private time series data. In this article, we review GAN variants designed for time series related applications. We propose a classification of discrete-variant GANs and continuous-variant GANs, in which GANs deal with discrete time series and continuous time series data. Here we showcase the latest and most popular literature in this field—their architectures, results, and applications. We also provide a list of the most popular evaluation metrics and their suitability across applications. Also presented is a discussion of privacy measures for these GANs and further protections and directions for dealing with sensitive data. We aim to frame clearly and concisely the latest and state-of-the-art research in this area and their applications to real-world technologies.

9 February 2021 in ACM Computing Surveys
Verified
Journal Article
Open access
ZWZhengwei Wang
Zhengwei Wang
QSQi She
Qi She
TWTomás E. Ward
Tomás E. Ward
Generative adversarial networks (GANs) have been extensively studied in the past few years. Arguably their most significant impact has been in the area of computer vision where great advances have been made in challenges such as plausible image generation, image-to-image translation, facial attribute manipulation, and similar domains. Despite the significant successes achieved to date, applying GANs to real-world problems still poses significant challenges, three of which we focus on here. These are as follows: (1) the generation of high quality images, (2) diversity of image generation, and (3) stabilizing training. Focusing on the degree to which popular GAN technologies have made progress against these challenges, we provide a detailed review of the state-of-the-art in GAN-related research in the published scientific literature. We further structure this review through a convenient taxonomy we have adopted based on variations in GAN architectures and loss functions. While several reviews for GANs have been presented to date, none have considered the status of this field based on their progress toward addressing practical challenges relevant to computer vision. Accordingly, we review and critically discuss the most popular architecture-variant, and loss-variant GANs, for tackling these challenges. Our objective is to provide an overview as well as a critical analysis of the status of GAN research in terms of relevant progress toward critical computer vision application requirements. As we do this we also discuss the most compelling applications in computer vision in which GANs have demonstrated considerable success along with some suggestions for future research directions. Codes related to the GAN-variants studied in this work is summarized on https://github.com/sheqi/GAN_Review.

8 August 2019 in Cognitive Computation
Verified
Journal Article
Closed access
PDF file
ZWZhengwei Wang
Zhengwei Wang
GHGraham Healy
Graham Healy
ASAlan Smeaton
Alan Smeaton
TWTomas Ward
Tomas Ward

1 September 2020 in Neurocomputing
Verified
Journal Article
Closed access
ZWZhengwei Wang
Zhengwei Wang
QSQi She
Qi She
ASAlan F. Smeaton
Alan F. Smeaton
TWTomás E. Ward
Tomás E. Ward
GHGraham Healy
Graham Healy

2 October 2018 in Brain-Computer Interfaces
Verified
Journal Article
Open access
ZWZhengwei Wang
Zhengwei Wang
GHGraham Healy
Graham Healy
ASAlan Smeaton
Alan Smeaton
TWTomas Ward
Tomas Ward
Rapid Serial Visual Presentation (RSVP) is a paradigm that supports the application of cortically coupled computer vision to image search. In RSVP, images are presented to participants which can evoke Event-related Potentials (ERPs) in their Electroencephalogram (EEG). Supervised spatial filtering techniques are often applied to enhance the discriminative information in the EEG. In this paper, we make two primary contributions: 1) We propose a novel spatial filtering method called Multiple Time Window LDA Beamformer (MTWLB); 2) We provide a comprehensive comparison of nine spatial filtering pipelines using three spatial filtering schemes, namely, MTWLB, xDAWN, Common Spatial Pattern (CSP) and three linear classification methods Linear Discriminant Analysis (LDA), Bayesian Linear Regression (BLR) and Logistic Regression (LR). The results reveal that MTWLB and xDAWN enhance the classification performance but CSP does not. The results also support the conclusion that LR can be effective for a RSVP-based BCI if discriminative features are available.

9 September 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
JXJing Xu
Jing Xu
WSWentao Shi
Wentao Shi
PGPan Gao
Pan Gao
QLQizhu Li
Qizhu Li
ZWZhengwei Wang
Zhengwei Wang
In recent works on semantic segmentation, there has been a significant focus on designing and integrating transformer-based encoders. However, less attention has been given to transformer-based decoders. We emphasize that the decoder stage is equally vital as the encoder in achieving superior segmentation performance. It disentangles and refines high-level cues, enabling precise object boundary delineation at the pixel level. In this paper, we introduce a novel transformer-based decoder called MUSTER, which seamlessly integrates with hierarchical encoders and consistently delivers high-quality segmentation results, regardless of the encoder architecture. Furthermore, we present a variant of MUSTER that reduces FLOPS while maintaining performance. MUSTER incorporates carefully designed multi-head skip attention (MSKA) units and introduces innovative upsampling operations. The MSKA units enable the fusion of multi-scale features from the encoder and decoder, facilitating comprehensive information integration. The upsampling operation leverages encoder features to enhance object localization and surpasses traditional upsampling methods, improving mIoU (mean Intersection over Union) by 0.4% to 3.2%. On the challenging ADE20K dataset, our best model achieves a single-scale mIoU of 50.23 and a multi-scale mIoU of 51.88, which is on-par with the current state-of-the-art model. Remarkably, we achieve this while significantly reducing the number of FLOPs by 61.3%.