Guijuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Guijuan Zhang has a total of 95 co-authors. Here are the top co-authors by number of shared publications:
- Dianjie Lu
Shandong Normal University, Jinan, China
32 shared publications Dianjie Lu
Shandong Normal University
10 shared publications- Zhuoran Zheng
Sun Yat-sen University
10 shared publications Hong Liu
School of Information Science and Engineering, Shandong Normal University, Jinan, China
7 shared publications- Hong Liu
Shandong Normal University, Jinan, China
7 shared publications - Chen Wu
National university of defense technology, Changsha, China
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2998-3006
UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2998-3006
Open AccessUHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
- 4 March 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56  (5) , 125
Panic emotion aware path planning for crowd evacuation
- 4 March 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56  (5) , 125
Panic emotion aware path planning for crowd evacuation
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64  (01962892) , 1-15
FS-FlowNet: Frequency–Spatial Dual-Domain Residual Flow Network for Remote Sensing Dehazing
Atmospheric haze and cloud cover severely degrade remote sensing image quality, adversely affecting critical tasks like object recognition and change detection. Existing dehazing methods face significant challenges with such images: traditional physical models often cause over-dehazing and color distortion, while single-stage deep learning models generalize poorly due to fixed regression paths. To address these limitations, this paper proposes FS-FlowNet, a dual-domain frequency-spatial residual flow network for remote sensing image dehazing. We innovatively combine frequency-spatial domain processing with multi-stage ordinary differential equation optimization within an efficient end-to-end architecture. First, during coarse dehazing, an enhanced U-Net encoder–decoder conducts multi-layer feature extraction with skip connections to capture haze-related features while preserving spatial structures. Next, a dual-domain module extracts amplitude and phase spectra via FFT, using a dual-branch (frequency-spatial) strategy to improve high-frequency detail. We employ a flow matching algorithm to cast dehazing as a multi-stage flow-field optimization problem; Here, a fourth-order Runge–Kutta (RK4) solver is used to activate/solve the underlying ordinary differential equations, yielding smooth and physically plausible flow transformations. Extensive experiments on the real world benchmark and multiple synthetic datasets demonstrate superior performance in both real and synthetic scenarios.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64  (01962892) , 1-15
FS-FlowNet: Frequency–Spatial Dual-Domain Residual Flow Network for Remote Sensing Dehazing
Atmospheric haze and cloud cover severely degrade remote sensing image quality, adversely affecting critical tasks like object recognition and change detection. Existing dehazing methods face significant challenges with such images: traditional physical models often cause over-dehazing and color distortion, while single-stage deep learning models generalize poorly due to fixed regression paths. To address these limitations, this paper proposes FS-FlowNet, a dual-domain frequency-spatial residual flow network for remote sensing image dehazing. We innovatively combine frequency-spatial domain processing with multi-stage ordinary differential equation optimization within an efficient end-to-end architecture. First, during coarse dehazing, an enhanced U-Net encoder–decoder conducts multi-layer feature extraction with skip connections to capture haze-related features while preserving spatial structures. Next, a dual-domain module extracts amplitude and phase spectra via FFT, using a dual-branch (frequency-spatial) strategy to improve high-frequency detail. We employ a flow matching algorithm to cast dehazing as a multi-stage flow-field optimization problem; Here, a fourth-order Runge–Kutta (RK4) solver is used to activate/solve the underlying ordinary differential equations, yielding smooth and physically plausible flow transformations. Extensive experiments on the real world benchmark and multiple synthetic datasets demonstrate superior performance in both real and synthetic scenarios.
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 6622-6639
Integrating Adaptive Rewiring and Compulsory Regulating: Co-Evolutionary Epidemic Dynamics Driven by Multi-Source Information
Effective epidemic control depends on understanding how individuals respond to multi-source information. However, existing research often treats two key behavioral responses—compulsory regulating and adaptive rewiring— separately, overlooking the co-evolution of network topology with the individual states. To address this, we propose a novel Unaware-Aware-Unaware and Susceptible-Infected-Susceptible (UAU-SIS) model that integrates these dual behavioral mechanisms, driven by cognitive and official information. Our model's framework, where the network topology is regenerated at each discrete timestep, is a key simplification for mathematical tractability. Within each step, however, the connection process is highly adaptive, governed by state-dependent rules rather than pure randomness. This setup, analyzed via the microscopic Markov chain approach (MMCA), enables us to analytically derive the epidemic threshold under their combined effects. Experimental results reveal their complementary properties: adaptive rewiring excels at preventing outbreaks by raising the epidemic threshold, whereas compulsory regulating is vital for mitigating prevalence during an ongoing epidemic. Importantly, strong adaptive rewiring can substantially suppress epidemic spread even under weak compulsory regulation. Furthermore, we validate the effectiveness and robustness of our proposed model on diverse real-world networks. Overall, this study provides a rigorous theoretical framework for understanding information-behavior-epidemic co-dynamics, offering critical insights for designing effective hybrid intervention strategies.
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 6622-6639
Integrating Adaptive Rewiring and Compulsory Regulating: Co-Evolutionary Epidemic Dynamics Driven by Multi-Source Information
Effective epidemic control depends on understanding how individuals respond to multi-source information. However, existing research often treats two key behavioral responses—compulsory regulating and adaptive rewiring— separately, overlooking the co-evolution of network topology with the individual states. To address this, we propose a novel Unaware-Aware-Unaware and Susceptible-Infected-Susceptible (UAU-SIS) model that integrates these dual behavioral mechanisms, driven by cognitive and official information. Our model's framework, where the network topology is regenerated at each discrete timestep, is a key simplification for mathematical tractability. Within each step, however, the connection process is highly adaptive, governed by state-dependent rules rather than pure randomness. This setup, analyzed via the microscopic Markov chain approach (MMCA), enables us to analytically derive the epidemic threshold under their combined effects. Experimental results reveal their complementary properties: adaptive rewiring excels at preventing outbreaks by raising the epidemic threshold, whereas compulsory regulating is vital for mitigating prevalence during an ongoing epidemic. Importantly, strong adaptive rewiring can substantially suppress epidemic spread even under weak compulsory regulation. Furthermore, we validate the effectiveness and robustness of our proposed model on diverse real-world networks. Overall, this study provides a rigorous theoretical framework for understanding information-behavior-epidemic co-dynamics, offering critical insights for designing effective hybrid intervention strategies.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- p. 1-12
Label Distribution Learning via Deep Confident Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- p. 1-12
Label Distribution Learning via Deep Confident Learning
- 9 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-14
NSDSAM: Noise-Suppression-Driven SAM for Infrared Small Target Detection
Although Segment Anything Model (SAM) have recently achieved remarkable progress, their generalization capability in infrared small target detection remains limited due to the inherently high noise levels in infrared imagery. To preserve the generalization and noise suppression ability of the model, we propose an method called NSDSAM, a noise-suppression-driven approach that enhances SAM at both internal and external levels. Internally, we develop a Hybrid Adapter for suppressing the noise of feature maps, consisting of an MLP adapter and a self-attention adapter. The self-attention adapter first performs entropy-aware reconstruction of features from noisy inputs and employs a gating mechanism for soft-attention fusion, mitigating SAM’s sensitivity to noise. Externally, we design a Spatial-Frequency hybrid Module (SFHM) that jointly processes spatial and frequency domains to overcome the self-attention model’s bias toward low-frequency components, further strengthening the suppression of background clutter and noise. Extensive experiments on multiple infrared datasets demonstrate that the proposed method achieves state-of-the-art (SOTA) performance in infrared small target detection. The project code is available upon acceptance.
- 9 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-14
NSDSAM: Noise-Suppression-Driven SAM for Infrared Small Target Detection
Although Segment Anything Model (SAM) have recently achieved remarkable progress, their generalization capability in infrared small target detection remains limited due to the inherently high noise levels in infrared imagery. To preserve the generalization and noise suppression ability of the model, we propose an method called NSDSAM, a noise-suppression-driven approach that enhances SAM at both internal and external levels. Internally, we develop a Hybrid Adapter for suppressing the noise of feature maps, consisting of an MLP adapter and a self-attention adapter. The self-attention adapter first performs entropy-aware reconstruction of features from noisy inputs and employs a gating mechanism for soft-attention fusion, mitigating SAM’s sensitivity to noise. Externally, we design a Spatial-Frequency hybrid Module (SFHM) that jointly processes spatial and frequency domains to overcome the self-attention model’s bias toward low-frequency components, further strengthening the suppression of background clutter and noise. Extensive experiments on multiple infrared datasets demonstrate that the proposed method achieves state-of-the-art (SOTA) performance in infrared small target detection. The project code is available upon acceptance.
- Open Access
DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal
Purple fringing, a persistent artifact caused by Longitudinal Chromatic Aberration (LCA) in camera lenses, has long degraded the clarity and realism of digital imaging. Traditional solutions rely on complex and expensive apochromatic (APO) lens hardware and the extraction of handcrafted features, ignoring the data-driven approach. To fill this gap, we introduce DCA-LUT, the first deep learning framework for purple fringing removal. Inspired by the physical root of the problem, the spatial misalignment of RGB color channels due to lens dispersion, we introduce a novel Chromatic-Aware Coordinate Transformation (CA-CT) module, learning an image-adaptive color space to decouple and isolate fringing into a dedicated dimension. This targeted separation allows the network to learn a precise ``purple fringe channel", which then guides the accurate restoration of the luminance channel. The final color correction is performed by a learned 5D Look-Up Table (5D LUT), enabling efficient and powerful% non-linear color mapping. To enable robust training and fair evaluation, we constructed a large-scale synthetic purple fringing dataset (PF-Synth). Extensive experiments in synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance in purple fringing removal.
Open AccessDCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal
Purple fringing, a persistent artifact caused by Longitudinal Chromatic Aberration (LCA) in camera lenses, has long degraded the clarity and realism of digital imaging. Traditional solutions rely on complex and expensive apochromatic (APO) lens hardware and the extraction of handcrafted features, ignoring the data-driven approach. To fill this gap, we introduce DCA-LUT, the first deep learning framework for purple fringing removal. Inspired by the physical root of the problem, the spatial misalignment of RGB color channels due to lens dispersion, we introduce a novel Chromatic-Aware Coordinate Transformation (CA-CT) module, learning an image-adaptive color space to decouple and isolate fringing into a dedicated dimension. This targeted separation allows the network to learn a precise ``purple fringe channel", which then guides the accurate restoration of the luminance channel. The final color correction is performed by a learned 5D Look-Up Table (5D LUT), enabling efficient and powerful% non-linear color mapping. To enable robust training and fair evaluation, we constructed a large-scale synthetic purple fringing dataset (PF-Synth). Extensive experiments in synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance in purple fringing removal.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7757-7765
UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7757-7765
Open AccessUniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
- Open Access
Foggy Crowd Counting: Combining Physical Priors and KAN-Graph
Aiming at the key challenges of crowd counting in foggy environments, such as long-range target blurring, local feature degradation, and image contrast attenuation, this paper proposes a crowd-counting method with a physical a priori of atmospheric scattering, which improves crowd counting accuracy under complex meteorological conditions through the synergistic optimization of the physical mechanism and data-driven.Specifically, first, the method introduces a differentiable atmospheric scattering model and employs transmittance dynamic estimation and scattering parameter adaptive calibration techniques to accurately quantify the nonlinear attenuation laws of haze on targets with different depths of field.Secondly, the MSA-KAN was designed based on the Kolmogorov-Arnold Representation Theorem to construct a learnable edge activation function. By integrating a multi-layer progressive architecture with adaptive skip connections, it significantly enhances the model's nonlinear representation capability in feature-degraded regions, effectively suppressing feature confusion under fog interference.Finally, we further propose a weather-aware GCN that dynamically constructs spatial adjacency matrices using deep features extracted by MSA-KAN. Experiments on four public datasets demonstrate that our method achieves a 12.2\%-27.5\% reduction in MAE metrics compared to mainstream algorithms in dense fog scenarios.
Open AccessFoggy Crowd Counting: Combining Physical Priors and KAN-Graph
Aiming at the key challenges of crowd counting in foggy environments, such as long-range target blurring, local feature degradation, and image contrast attenuation, this paper proposes a crowd-counting method with a physical a priori of atmospheric scattering, which improves crowd counting accuracy under complex meteorological conditions through the synergistic optimization of the physical mechanism and data-driven.Specifically, first, the method introduces a differentiable atmospheric scattering model and employs transmittance dynamic estimation and scattering parameter adaptive calibration techniques to accurately quantify the nonlinear attenuation laws of haze on targets with different depths of field.Secondly, the MSA-KAN was designed based on the Kolmogorov-Arnold Representation Theorem to construct a learnable edge activation function. By integrating a multi-layer progressive architecture with adaptive skip connections, it significantly enhances the model's nonlinear representation capability in feature-degraded regions, effectively suppressing feature confusion under fog interference.Finally, we further propose a weather-aware GCN that dynamically constructs spatial adjacency matrices using deep features extracted by MSA-KAN. Experiments on four public datasets demonstrate that our method achieves a 12.2\%-27.5\% reduction in MAE metrics compared to mainstream algorithms in dense fog scenarios.