Meng Zhang

Ms. Meng Zhang

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
11 September 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
YSYi Shao
Yi Shao
WYWenzhong Yang
Wenzhong Yang
JWJiajia Wang
Jiajia Wang
HLHouwang Lu
Houwang Lu
Meng ZhangMeng Zhang
Meng Zhang
DCDanny Chen
Danny Chen
As an essential component of the global economic crop, cotton is highly susceptible to the impact of diseases on its yield and quality. In recent years, artificial intelligence technology has been widely used in cotton crop disease recognition, but in complex backgrounds, existing technologies have certain limitations in accuracy and efficiency. To overcome these challenges, this study proposes an innovative cotton disease recognition method called CANnet, and we independently collected and constructed an image dataset containing multiple cotton diseases. Firstly, we introduced the innovatively designed Reception Field Space Channel (RFSC) module to replace traditional convolution kernels. This module combines dynamic receptive field features with traditional convolutional features to effectively utilize spatial channel attention, helping CANnet capture local and global features of images more comprehensively, thereby enhancing the expressive power of features. At the same time, the module also solves the problem of parameter sharing. To further optimize feature extraction and reduce the impact of spatial channel attention redundancy in the RFSC module, we connected a self-designed Precise Coordinate Attention (PCA) module after the RFSC module to achieve redundancy reduction. In the design of the classifier, CANnet abandoned the commonly used MLP in traditional models and instead adopted improved Kolmogorov Arnold Networks-s (KANs) for classification operations. KANs technology helps CANnet to more finely utilize extracted features for classification tasks through learnable activation functions. This is the first application of the KAN concept in crop disease recognition and has achieved excellent results. To comprehensively evaluate the performance of CANnet, we conducted extensive experiments on our cotton disease dataset and a publicly available cotton disease dataset. Numerous experimental results have shown that CANnet outperforms other advanced methods in the accuracy of cotton disease identification. Specifically, on the self-built dataset, the accuracy reached 96.3%; On the public dataset, the accuracy reached 98.6%. These results fully demonstrate the excellent performance of CANnet in cotton disease identification tasks.

12 February 2025 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
Meng ZhangMeng Zhang
Meng Zhang
WYWenzhong Yang
Wenzhong Yang
LWLiejun Wang
Liejun Wang
ZWZhonghua Wu
Zhonghua Wu
DCDanny Chen
Danny Chen
Micro-expressions (MEs) are unconscious and involuntary reactions that genuinely reflect an individual’s inner emotional state, making them valuable in the fields of emotion analysis and behavior recognition. MEs are characterized by subtle changes within specific facial action units, and effective feature learning and fusion tailored to these characteristics still require in-depth research. To address this challenge, this paper proposes a novel hierarchical feature aggregation network (HFA-Net). In the local branch, the multi-scale attention (MSA) block is proposed to capture subtle facial changes and local information. The global branch introduces the retentive meet transformers (RMT) block to establish dependencies between holistic facial features and structural information. Considering that single-scale features are insufficient to fully capture the subtleties of MEs, a multi-level feature aggregation (MLFA) module is proposed to extract and fuse features from different levels across the two branches, preserving more comprehensive feature information. To enhance the representation of key features, an adaptive attention feature fusion (AAFF) module is designed to focus on the most useful and relevant feature channels. Extensive experiments conducted on the SMIC, CASME II, and SAMM benchmark databases demonstrate that the proposed HFA-Net outperforms current state-of-the-art methods. Additionally, ablation studies confirm the superior discriminative capability of HFA-Net when learning feature representations from limited ME samples. Our code is publicly available at https://github.com/tairuwu/HFA-Net.

20 May 2024 in Entropy
Verified
Journal Article
Open access
PDF file
Meng ZhangMeng Zhang
Meng Zhang
WYWenzhong Yang
Wenzhong Yang
DCDanny Chen
Danny Chen
FCFu Chenghao
Fu Chenghao
FWFuyuan Wei
Fuyuan Wei
Traditional methods for pest recognition have certain limitations in addressing the challenges posed by diverse pest species, varying sizes, diverse morphologies, and complex field backgrounds, resulting in a lower recognition accuracy. To overcome these limitations, this paper proposes a novel pest recognition method based on attention mechanism and multi-scale feature fusion (AM-MSFF). By combining the advantages of attention mechanism and multi-scale feature fusion, this method significantly improves the accuracy of pest recognition. Firstly, we introduce the relation-aware global attention (RGA) module to adaptively adjust the feature weights of each position, thereby focusing more on the regions relevant to pests and reducing the background interference. Then, we propose the multi-scale feature fusion (MSFF) module to fuse feature maps from different scales, which better captures the subtle differences and the overall shape features in pest images. Moreover, we introduce generalized-mean pooling (GeMP) to more accurately extract feature information from pest images and better distinguish different pest categories. In terms of the loss function, this study proposes an improved focal loss (FL), known as balanced focal loss (BFL), as a replacement for cross-entropy loss. This improvement aims to address the common issue of class imbalance in pest datasets, thereby enhancing the recognition accuracy of pest identification models. To evaluate the performance of the AM-MSFF model, we conduct experiments on two publicly available pest datasets (IP102 and D0). Extensive experiments demonstrate that our proposed AM-MSFF outperforms most state-of-the-art methods. On the IP102 dataset, the accuracy reaches 72.64%, while on the D0 dataset, it reaches 99.05%.

28 September 2025 in Entropy
Verified
Journal Article
Open access
PDF file
Meng ZhangMeng Zhang
Meng Zhang
LYLong Yao
Long Yao
WYWenzhong Yang
Wenzhong Yang
YYYabo Yin
Yabo Yin
Micro-expressions are extremely subtle and short-lived facial muscle movements that often reveal an individual’s genuine emotions. However, micro-expression recognition (MER) remains highly challenging due to its short duration, low motion intensity, and the imbalanced distribution of training samples. To address these issues, this paper proposes a Global–Local Feature Fusion Network (GLFNet) to effectively extract discriminative features for MER. Specifically, GLFNet consists of three core modules: the Global Attention (LA) module, which captures subtle variations across the entire facial region; the Local Block (GB) module, which partitions the feature map into four non-overlapping regions to emphasize salient local movements while suppressing irrelevant information; and the Adaptive Feature Fusion (AFF) module, which employs an attention mechanism to dynamically adjust channel-wise weights for efficient global–local feature integration. In addition, a class-balanced loss function is introduced to replace the conventional cross-entropy loss, mitigating the common issue of class imbalance in micro-expression datasets. Extensive experiments are conducted on three benchmark databases, SMIC, CASME II, and SAMM, under two evaluation protocols. The experimental results demonstrate that under the Composite Database Evaluation protocol, GLFNet consistently outperforms existing state-of-the-art methods in overall performance. Specifically, the unweighted F1-scores on the Combined, SAMM, CASME II, and SMIC datasets are improved by 2.49%, 2.02%, 0.49%, and 4.67%, respectively, compared to the current best methods. These results strongly validate the effectiveness and superiority of the proposed global–local feature fusion strategy in micro-expression recognition tasks.

6 February 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
Meng ZhangMeng Zhang
Meng Zhang
TZTao Zhu
Tao Zhu
HGHuan Gong
Huan Gong
WYWenzhong Yang
Wenzhong Yang
FWFuyuan Wei
Fuyuan Wei
LYLong Yao
Long Yao
Micro-expressions are caused by brief and subtle facial muscle movements and can reveal an individual’s concealed genuine emotions. Therefore, micro-expression recognition plays an important role in emotion analysis and behavior understanding. Although existing methods have achieved notable progress in spatiotemporal feature modeling, effectively capturing subtle facial muscle motions while simultaneously achieving robust fusion between motion features and facial spatial structure remains a key challenge in this field. To address this issue, we propose a Spatial Feature–Guided Motion Learning Network (SFML-Net). The proposed network adopts a dual-branch architecture with temporal and spatial branches. In the temporal branch, a Local Block (LB) module is designed to divide optical-flow features into multiple local regions, thereby emphasizing locally salient motion variations. In the spatial branch, Single-Head Vision Transformer (SHViT) is introduced to extract spatial positional information from the onset frame, modeling global long-range dependencies while preserving part of the original spatial features to enhance spatial perception. In addition, we propose a Self-Guided (SG) module that leverages spatial features as priors to guide motion feature learning, thereby facilitating effective alignment between facial spatial structures and motion dynamics and enabling complementary enhancement of both feature types. Extensive experiments on multiple benchmark datasets, including SMIC, CASME II, SAMM, and Composite, demonstrate that SFML-Net consistently outperforms existing state-of-the-art methods. Furthermore, ablation studies validate the effectiveness of the proposed network design, showing that the method exhibits stronger generalization and discriminative capability under limited training samples. Our code is publicly available at https://github.com/tairuwu/SFML-Net.

9 March 2025 in Entropy
Verified
Journal Article
Open access
PDF file
ZWZhonghua Wu
Zhonghua Wu
WYWenzhong Yang
Wenzhong Yang
Meng ZhangMeng Zhang
Meng Zhang
FWFuyuan Wei
Fuyuan Wei
XLXinfang Liu
Xinfang Liu
Event temporal relation extraction is a crucial task in natural language processing, aimed at recognizing the temporal relations between event triggers in a text. Despite extensive efforts in this area, the existing methods face two main issues. Firstly, the previous models for event temporal relation extraction mainly rely on a classification framework, which fails to output the crucial contextual words necessary for predicting the temporal relations between two event triggers. Secondly, the prior research that formulated natural language processing tasks as text generation problems usually trained the generative models by maximum likelihood estimation. However, this approach encounters potential difficulties when the optimization objective is misaligned with the task performance metrics. To resolve these limitations, we introduce a reinforcement learning-based generative framework for event temporal relation extraction. Specifically, to output the important contextual words from the input sentence for temporal relation identification, we introduce dependency path generation as an auxiliary task to complement event temporal relation extraction. This task is solved alongside temporal relation prediction to enhance model performance. To achieve this, we reformulate the event temporal relation extraction task as a text generation problem, aiming to generate both event temporal relation labels and dependency path words based on the input sentence. To bridge the gap between the optimization objective and task performance metrics, we employ the REINFORCE algorithm to optimize our generative model, designing a novel reward function to simultaneously capture the accuracy of temporal prediction and the quality of generation. Lastly, to mitigate the high variance issue encountered when using the REINFORCE algorithm in multi-task generative model training, we propose a baseline policy gradient algorithm to improve the stability and efficiency of the training process. Experimental results on two widely used datasets, MATRES and TB-DENSE, show that our approach exhibits competitive performance.