Author name cluster

Weidong Zhang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

1 author row

EAAI Journal 2026 Journal Article

Multi-scale feature enhancement network for object detection in severe foggy weather

Yingjun Wang
Xiaopeng Yang
Yingjian Wang
Peixian Zhuang
Wenyi Zhao
Haoxiang Lu
Weidong Zhang

Foggy conditions degrade image quality through light scattering and absorption, along with particle-induced noise, leading to low contrast, color distortion, and blurred structures that hinder reliable object detection. To address these challenges, we propose a Multi-Scale Feature Enhanced Object Detection Network (MFENet). Specifically, we design a Spatial-Frequency Feature Recovery Module (SFRM) that performs multi-scale enhancement and global context modeling in both spatial and frequency domains, strengthening representations of fog-degraded features. Furthermore, a Dual-Dimensional Interaction Module (DIM) is introduced to enhance feature interaction and improve fine-grained feature extraction. To mitigate false and missed detections under severe occlusion, an Occlusion-Aware Detection Head (OADH) is incorporated to further improve detection accuracy. Experimental results show that MFENet achieves a mean Average Precision (mAP) at 50% Intersection over Union (IoU) of 78. 85% on the synthetic Pattern Analysis, Statistical Modeling and Computational Learning Visual Object Classes (PASCAL VOC)-fog dataset and 75. 89% on the Real-world Task-driven Testing Set (RTTS). In addition, cross-domain generalization evaluations on the Foggy Driving Dataset (FDD) and a curated subset of the Berkeley DeepDrive dataset (BDD100K*) demonstrate consistent and strong generalization performance. With only 7. 8 million parameters and an inference speed of 117 Frames Per Second (FPS), MFENet achieves an effective trade-off between efficiency and performance for real-time applications. The code is publicly available at: https: //github. com/AmorFatio/MFENet.

Details DOI

EAAI Journal 2024 Journal Article

Unified multi-color-model-learning-based deep support vector machine for underwater image classification

Weidong Zhang
Baiqiang Yu
Guohou Li
Peixian Zhuang
Zheng Liang
Wenyi Zhao

Underwater images face various quality degradation issues due to the complex underwater physicalization environment. However, most existing underwater image clarification methods cannot effectively enhance all degradation types of underwater images, which is significant for designing dedicated degradation classes of underwater image clarification methods. To effectively solve the classification issue of underwater images driving the design of specialized underwater image clarification methods, we present a Unified multi-color-model-learning-based Deep Support Vector Machine (UDSVM) for underwater image classification. Specifically, we propose a multi-color model feature encode strategy, combining features from different color models into a unified feature model to enrich the diversity of feature representation capabilities. Whereafter, we design a deep support vector machine considering the deep network structure with better nonlinear modeling performance. Meanwhile, we embed the unified multi-color model into the deep support vector machine with gradient descent backward optimization, which solves the issues of insufficient learning features and low classification accuracy of the single-color model. Besides, we built a large-scale underwater image classification dataset (UICD) including 6630 underwater images, which have the characteristics of different degradation classes and different degradation levels of the same degradation class. Our UDSVM is compared with NNCO, CSDBN, AlexNet, GoogleNet, ResNet, EfficientNet, VGG19, CoatNet, DAMNet, and MCANet, experiments on UICD demonstrate that our UDSVM achieves the highest classification accuracy of 99. 21 % and 98. 25 % for rough and fine classifications, respectively. Additionally, our method outperforms the ten compared methods.

Details DOI

AAAI Conference 2023 Conference Paper

CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics

Yiren Song
Xuning Shao
Kang Chen
Weidong Zhang
Zhongliang Jing
Minzhe Li

Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative models to ensure the quality of results, because CLIP alone cannot provide enough guidance information for fine-scale pixel-level changes. In this paper, we introduce CLIPVG, a text-guided image manipulation framework using differentiable vector graphics, which is also the first CLIP-based general image manipulation framework that does not require any additional generative models. We demonstrate that CLIPVG can not only achieve state-of-art performance in both semantic correctness and synthesis quality, but also is flexible enough to support various applications far beyond the capability of all existing methods.

PDF Details DOI

EAAI Journal 2023 Journal Article

Multi-layer additive tensor decomposition of infrared video for titanium alloy tensile testing

Tao Zhang
Jian Liu
Yibo Ai
Weidong Zhang

Infrared video (in mathematics terms, tensor) has been widely used in the tensile testing of metallic materials, such as titanium alloy and steel. The infrared video of the tensile testing process can effectively and efficiently determine the properties of metallic materials, e. g. , Young’s modulus, Poisson’s ratio, yield strength, etc. The infrared video with structural properties, such as smoothness and sparsity, can be used to characterize the tensile testing process. To extract the features in the infrared video with structural properties, we propose a multi-layer additive tensor decomposition (MLATD) method based on regularization tensor regression for tensile testing. It decomposes a tensor into three classes of components: the multi-smooth layers (including background and foreground), the sparse layers (including between-tensor and in-tensor), and the noise layer. The scree plot is proposed to determine the number of multi-smooth layers, which is a downward curve of the difference between the smooth layers and the sparse layer. The alternating direction method of multipliers (ADMM) algorithm is proposed to solve the proposed method. The decomposition results of the simulation data and real-world case study revealed that the proposed method outperforms the existing state-of-the-art methods.

Details DOI

AAAI Conference 2023 Conference Paper

Underwater Ranker: Learn Which Is Better and How to Be Better

Chunle Guo
Ruiqi Wu
Xin Jin
Linghao Han
Weidong Zhang
Zhi Chai
Chongyi Li

In this paper, we present a ranking-based underwater image quality assessment (UIQA) method, abbreviated as URanker. The URanker is built on the efficient conv-attentional image Transformer. In terms of underwater images, we specially devise (1) the histogram prior that embeds the color distribution of an underwater image as histogram token to attend global degradation and (2) the dynamic cross-scale correspondence to model local degradation. The final prediction depends on the class tokens from different scales, which comprehensively considers multi-scale dependencies. With the margin ranking loss, our URanker can accurately rank the order of underwater images of the same scene enhanced by different underwater image enhancement (UIE) algorithms according to their visual quality. To achieve that, we also contribute a dataset, URankerSet, containing sufficient results enhanced by different UIE algorithms and the corresponding perceptual rankings, to train our URanker. Apart from the good performance of URanker, we found that a simple U-shape UIE network can obtain promising performance when it is coupled with our pre-trained URanker as additional supervision. In addition, we also propose a normalization tail that can significantly improve the performance of UIE networks. Extensive experiments demonstrate the state-of-the-art performance of our method. The key designs of our method are discussed. Our code and dataset are available at https://li-chongyi.github.io/URanker_files/.

PDF Details DOI

EAAI Journal 2021 Journal Article

General type-2 fuzzy multi-switching synchronization of fractional-order chaotic systems

Mohammad Hosein Sabzalian
Ardashir Mohammadzadeh
Weidong Zhang
Kittisak Jermsittiparsert

In this study, the problem of multi-switching synchronization of the chaotic systems (CSs) with fractional-order dynamics is considered. Unlike to the most studies, the dynamics of slave chaotic systems are unknown and also the master systems are not fixed but are switched between several synchronization modes. A general type-2 (GT2) fuzzy neural network (FNN) is proposed to approximate the unknown nonlinearities. The stability and robustness is investigated by the Lyapunov theorem and the fractional-order adaptation laws are obtained to optimize the rules of GT2FNNs. The robustness of the proposed scheme against approximation errors and variation of synchronization modes is guaranteed by the proposed compensators. The good performance of schemed method is demonstrated by several simulations and comparison with recent presented control techniques.

Details DOI

AAAI Conference 2021 Conference Paper

SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

Mengzuo Huang
Feng Li
Wuhe Zou
Weidong Zhang

Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission. In this paper, we investigate the incomplete utterance restoration which has brought general improvement over multi-turn dialogue systems in recent studies. Meanwhile, jointly inspired by the autoregression for text generation and the sequence labeling for text editing, we propose a novel semi autoregressive generator (SARG) with the high efficiency and flexibility. Moreover, experiments on two benchmarks show that our proposed model significantly outperforms the state-of-the-art models in terms of quality and inference speed.

PDF Details

EAAI Journal 2021 Journal Article

The object-oriented dynamic task assignment for unmanned surface vessels

Bin Du
Yu Lu
Xiaotong Cheng
Weidong Zhang
Xuesong Zou

This paper investigates the task assignment and guidance issues of unmanned surface vessels (USVs) interception. When the USVs formation is invaded by some moving objects during its escort, it is necessary for the unmanned systems to assign defenders to prevent attackers approaching the vulnerable target in antagonistic scenarios. This action requires efficient guidance and task assignment strategies. With this in mind, this paper presents the Integral Proportional Navigation Guidance (IPNG) with Tabu Dynamic Consensus-Based Auction Algorithm (TDCBAA) in marine interception scenario. First, IPNG is introduced in the interception game considering the USV kinematic model, which can effectively reduce the individual interception time. Second, a new bidding function is designed for moving objects interception with the consideration of the attackers’ types, positions and interception time. Finally, a TDCBAA is designed to solve the task assignment subproblem, resulting in a shorter overall interception time and a higher interception success rate. Simulations demonstrate that the proposed algorithm can optimize the allocation of defenders in real-time and intercept the attackers more quickly compared with other classical algorithms, which is more suitable in situations where attackers are approaching from all directions.

Details DOI

AAAI Conference 2018 Conference Paper

Latent Discriminant Subspace Representations for Multi-View Outlier Detection

Kai Li
Sheng Li
Zhengming Ding
Weidong Zhang
Yun Fu

Identifying multi-view outliers is challenging because of the complex data distributions across different views. Existing methods cope this problem by exploiting pairwise constraints across different views to obtain new feature representations, based on which certain outlier score measurements are de- ﬁned. Due to the use of pairwise constraint, it is complicated and time-consuming for existing methods to detect outliers from three or more views. In this paper, we propose a novel method capable of detecting outliers from any number of data views. Our method ﬁrst learns latent discriminant representations for all view data and deﬁnes a novel outlier score function based on the latent discriminant representations. Speciﬁcally, we represent multi-view data by a global low-rank representation shared by all views and residual representations speciﬁc to each view. Through analyzing the view-speciﬁc residual representations of all views, we can get the outlier score for every sample. Moreover, we raise the problem of detecting a third type of multi-view outliers which are neglected by existing methods. Experiments on six datasets show our method outperforms the existing ones in identifying all types of multi-view outliers, often by large margins.

PDF Details

EAAI Journal 2018 Journal Article

ThermalNet: A deep reinforcement learning-based combustion optimization system for coal-fired boiler

Yin Cheng
Yuexin Huang
Bo Pang
Weidong Zhang

This paper presents a combustion optimization system for coal-fired boilers that includes a trade-off between emissions control and boiler efficiency. Designing an optimizer for this nonlinear, multiple-input multiple-output problem is challenging. This paper describes the development of an integrated combustion optimization system called ThermalNet, which is based on a deep Q-network (DQN) and a long short-term memory (LSTM) module. ThermalNet is a highly automated system consisting of an LSTM–ConvNet predictor and a DQN optimizer. The LSTM–ConvNet extracts the features of boiler behavior from the distributed control system (DCS) operational data of a supercritical thermal plant. The DQN reinforcement learning optimizer contributes to the online development of policies based on static and dynamic states. ThermalNet establishes a sequence of control actions that both reduce emissions and simultaneously enhance fuel utilization. The internal structure of the DQN optimizer demonstrates a greater representation capacity than does the shallow multilayer optimizer. The presented experiments indicate the effectiveness of the proposed optimization system.

Details DOI

JBHI Journal 2014 Journal Article

sEMG-Based Joint Force Control for an Upper-Limb Power-Assist Exoskeleton Robot

Zhijun Li
Baocheng Wang
Fuchun Sun
Chenguang Yang
Qing Xie
Weidong Zhang

This paper investigates two surface electromyogram (sEMG)-based control strategies developed for a power-assist exoskeleton arm. Different from most of the existing position control approaches, this paper develops force control methods to make the exoskeleton robot behave like humans in order to provide better assistance. The exoskeleton robot is directly attached to a user’s body and activated by the sEMG signals of the user’s muscles, which reflect the user’s motion intention. In the first proposed control method, the forces of agonist and antagonist muscles pair are estimated, and their difference is used to produce the torque of the corresponding joints. In the second method, linear discriminant analysis-based classifiers are introduced as the indicator of the motion type of the joints. Then, the classifier’s outputs together with the estimated force of corresponding active muscle determine the torque control signals. Different from the conventional approaches, one classifier is assigned to each joint, which decreases the training time and largely simplifies the recognition process. Finally, the extensive experiments are conducted to illustrate the effectiveness of the proposed approaches.

Details DOI

EAAI Journal 2007 Journal Article

Network partition for switched industrial Ethernet using genetic algorithm

Qizhi Zhang
Weidong Zhang

The network partition problem in switched industrial Ethernet is analyzed, which is shown to be equivalent to a multi-objective optimization problem: the network partition should reduce the inter-network communication, and simultaneously make the network traffic be evenly distributed over the respective sub-networks. Furthermore, the switch capability must be respected when assigning devices to sub-networks, which sets constraints for the optimization problem. This is a new problem that has not been modeled before. Then genetic algorithm is proposed to search near-optimal solution for this network partition problem. When designing the fitness function and genetic operators, the communication characteristics of industrial control network, such as the existence of controller and one-way communication of field devices, are considered. Finally, a simulation research is carried out to investigate the effectiveness of the proposed genetic algorithm.

Details DOI