Du Zhang

Dr. Du Zhang


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
19 March 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Open access
ZCZhigang Chen
Zhigang Chen
BENJIA ZHOUBENJIA ZHOU
BENJIA ZHOU
YHYiqing Huang
Yiqing Huang
JWJun Wan
Jun Wan
YHYibo Hu
Yibo Hu
DZDu Zhang
Du Zhang
Sign Language Representation Learning (SLRL) is crucial for a range of sign language-related downstream tasks such as Sign Language Translation (SLT) and Sign Language Retrieval (SLRet). Recently, many gloss-based and gloss-free SLRL methods have been proposed, showing promising performance. Among them, the gloss-free approach shows promise for strong scalability without relying on gloss annotations. However, it currently faces suboptimal solutions due to challenges in encoding the intricate, context-sensitive characteristics of sign language videos, mainly struggling to discern essential sign features using a non-monotonic video-text alignment strategy. Therefore, we introduce an innovative pretraining paradigm for gloss-free SLRL, called C2RL, in this paper. Specifically, rather than merely incorporating a non-monotonic semantic alignment of video and text to learn language-oriented sign features, we emphasize two pivotal aspects of SLRL: Implicit Content Learning (ICL) and Explicit Context Learning (ECL). ICL delves into the content of communication, capturing the nuances, emphasis, timing, and rhythm of the signs. In contrast, ECL focuses on understanding the contextual meaning of signs and converting them into equivalent sentences. Despite its simplicity, extensive experiments confirm that the joint optimization of ICL and ECL results in robust sign language representation and significant performance gains in gloss-free SLT and SLRet tasks. Notably, C2RL improves the BLEU-4 score by +5.3 on P14T, +10.6 on CSL-daily, +6.2 on OpenASL, and +1.3 on How2Sign. It also boosts the R@1 score by +8.3 on P14T, +14.4 on CSL-daily, and +5.9 on How2Sign. Additionally, we set a new baseline for the OpenASL dataset in the SLRet task.

15 July 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
GXGuiyu Xia
Guiyu Xia
PXPeng Xue
Peng Xue
HSHuaijiang Sun
Huaijiang Sun
YSYubao Sun
Yubao Sun
DZDu Zhang
Du Zhang
QLQingshan Liu
Qingshan Liu
Deep subspace learning is an important branch of self-supervised learning and has been a hot research topic in recent years, but current methods do not fully consider the individualities of temporal data and related tasks. In this paper, by transforming the individualities of motion capture data and segmentation task as the supervision, we propose the local self-expression subspace learning network. Specifically, considering the temporality of motion data, we use the temporal convolution module to extract temporal features. To implement the local validity of self-expression in temporal tasks, we design the local self-expression layer which only maintains the representation relations with temporally adjacent motion frames. To simulate the interpolatability of motion data in the feature space, we impose a group sparseness constraint on the local self-expression layer to impel the representations only using selected keyframes. Besides, based on the subspace assumption, we propose the subspace projection loss, which is induced from distances of each frame projected to the fitted subspaces, to penalize the potential clustering errors. The superior performances of the proposed model on the segmentation task of synthetic data and three tasks of real motion capture data demonstrate the feature learning ability of our model.

4 November 2021 in Energies
Verified
Journal Article
Open access
PDF file
XXxiaoming xie
xiaoming xie
MLMeiping Li
Meiping Li
DZDu Zhang
Du Zhang
The price of electricity is an important factor in the electricity market. Accurate electricity price forecasting (EPF) is very important to all competing electricity market parties. Decision-making in the electricity market is highly dependent on electricity prices, making an EPF model an important part of the orderly and efficient operation of the electricity market. Especially during the COVID-19 pandemic, the prices of raw materials for electricity production, such as coal, have risen sharply. Forecasting electricity prices has become particularly important. Currently, existing EPF prediction models face two main challenges: First, how to integrate multiscale electricity price data to obtain a higher prediction accuracy. Second, how to solve the problem of data noise caused by the fusion of EPF samples and multiscale data. To solve the above problems, we innovatively propose a tensor decomposition method to integrate multiscale electricity price data and use L1 regularization and wavelet transform to remove data noise. In general, this paper proposes a deep learning EPF prediction model, named the WT_TDLSTM model, based on tensor decomposition, a wavelet transform, and long short-term memory (LSTM). Among them, the LSTM method is used to predict electricity prices. We conducted experiments on three datasets. The experimental results of three data prove that the WT_TDLSTM model is better than the compared EPF model. The indicators of MSE and RMSE are 33.65–99.97% better than the comparison model. We believe that the WT_TDLSTM model is a good supplement to the EPF model.

5 May 2023 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Closed access
PDF file
TZTianle Zhang
Tianle Zhang
ZLZhen Liu
Zhen Liu
ZPZhiqiang Pu
Zhiqiang Pu
JYJianqiang Yi
Jianqiang Yi
YLYanyan Liang
Yanyan Liang
DZDu Zhang
Du Zhang

24 December 2021 in Sustainability
Verified
Journal Article
Open access
PDF file
MLMeiping Li
Meiping Li
XXxiaoming xie
xiaoming xie
DZDu Zhang
Du Zhang
Electricity loads are basic and important information for power generation facilities and traders, especially in terms of production plans, daily operations, unit commitments, and economic dispatches. Short-term load forecasting (STLF), which predicts power loads for a few days, plays a vital role in the reliable, safe, and efficient operation of a power system. Currently, two main challenges are faced by existing STLF prediction models. The first involves how to fuse multiscale electricity load data to obtain a high-performance model and remove data noise after integration. The second involves how to improve the local optimal solution despite the sample quality problem. To address the above issues, this paper proposes a multiscale electricity load data fusion- and STLF-based short time series prediction model built on a sparse deep autoencoder and self-paced learning (SPL). A sparse deep autoencoder was used to solve the multiscale data fusion problem with data noise. Furthermore, SPL was utilized to solve the local optimal solution problem. The experimental results showed that our model was better than the existing STLF prediction models by more than 15.89% in terms of the mean squared error (MSE) indicator.

12 February 2022 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
XSXibin Sun
Xibin Sun
DZDu Zhang
Du Zhang
HQHaiou Qin
Haiou Qin
JTJiahua Tang
Jiahua Tang
With successful machine learning applications in many fields, researchers tried to introduce machine learning into intrusion detection systems for building classification models. Although experimental results showed that these classification models could produce higher accuracy in predicting network attacks on the offline datasets, compared with the operational intrusion detection systems, machine learning is rarely deployed in the real intrusion detection environment. This is what we call the last mile problem with the machine learning approach to network intrusion detection, the discrepancy between the strength and requirements of machine learning and network operational semantics. In this paper, we aim to bridge the aforementioned gap. In particular, an LCC-RF-RFEX feature selection approach is proposed to select optimal features of the specific type of attacks from dataset, and then, an intrusion-specific approach is introduced to convert them into detection patterns that can be used by the nonmachine-learning detector for the corresponding specific attack detection in the real-world network environment. To substantiate our approach, we take Snort, KDDCup’99 dataset, and Dos attacks as the experimental subjects to demonstrate how to close the last-mile gap. For the specific type of Dos attacks in the KDDCup’99 dataset, we use the LCC-RF-RFEX method to select optimal feature subset and utilize our intrusion-specific approach to generate new rules in Snort by using them. Comparing performance differences between the existing Snort rule set and our augmented Snort rule set with regard to Dos attacks, the experimental results showed that our approach expanded Snort’s detection capability of Dos attacks, on average, reduced up to 25.28% false-positive alerts for Teardrop attacks and Synflood attacks, and decreased up to 98.87% excessive alerts for Mail bomb attacks.