Jiawei Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiawei Zhang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Jinwei Wang
Nankai University, Tianjin, China
7 shared publications - Xiangyang Luo
Information Engineering University, Zhengzhou, China
7 shared publications - Bin Ma
Qilu University of Technology (Shandong Academy of Sciences)
5 shared publications - Hao Wang
School of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian, China
5 shared publications - Hao Wu
Information Engineering University, Zhengzhou, Henan, China
5 shared publications - Lin Yuan
Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11508-11516
HybridSyncNet: Beyond the Alignment-Uniformity Trade-Off in Audio-Visual Synchronization via Multi-Level Contrastive Learning
Audio–visual synchronization aims to accurately determine the temporal alignment between lip motions and the corresponding speech signal. However, existing approaches often struggle to achieve an optimal balance between in-sync and out-of-sync detection accuracy. In this paper, we provide a formal analysis of this performance bottleneck and rigorously show that both clip-level and frame-level synchronization models are inherently constrained by the alignment–uniformity trade-off on the representation hypersphere. To overcome this fundamental limitation, we propose HybridSyncNet, an efficient hybrid-level synchronization paradigm that leverages adaptive gating and multi-level contrastive learning to fuse the complementary strengths of clip-level and frame-level information in alignment and uniformity. Crucially, we theoretically demonstrate that, compared with single-level models, the proposed HybridSyncNet simultaneously achieves alignment improvement and uniformity gain. Extensive experiments validate the effectiveness of our approach. With only 2.46M parameters, HybridSyncNet outperforms state-of-the-art audio–visual synchronization models on the CREMA-D and HDTF benchmarks, establishing a new paradigm for audio–visual synchronization. The code is available at~https://github.com/tlemangen/HybridSyncNet.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11508-11516
Open AccessHybridSyncNet: Beyond the Alignment-Uniformity Trade-Off in Audio-Visual Synchronization via Multi-Level Contrastive Learning
Audio–visual synchronization aims to accurately determine the temporal alignment between lip motions and the corresponding speech signal. However, existing approaches often struggle to achieve an optimal balance between in-sync and out-of-sync detection accuracy. In this paper, we provide a formal analysis of this performance bottleneck and rigorously show that both clip-level and frame-level synchronization models are inherently constrained by the alignment–uniformity trade-off on the representation hypersphere. To overcome this fundamental limitation, we propose HybridSyncNet, an efficient hybrid-level synchronization paradigm that leverages adaptive gating and multi-level contrastive learning to fuse the complementary strengths of clip-level and frame-level information in alignment and uniformity. Crucially, we theoretically demonstrate that, compared with single-level models, the proposed HybridSyncNet simultaneously achieves alignment improvement and uniformity gain. Extensive experiments validate the effectiveness of our approach. With only 2.46M parameters, HybridSyncNet outperforms state-of-the-art audio–visual synchronization models on the CREMA-D and HDTF benchmarks, establishing a new paradigm for audio–visual synchronization. The code is available at~https://github.com/tlemangen/HybridSyncNet.
- 2 November 2026
- Published by Elsevier in Future Generation Computer Systems
- Vol. 189
Cloud task priority triage under class imbalance: An explainable stacked ensemble approach
- 2 November 2026
- Published by Elsevier in Future Generation Computer Systems
- Vol. 189
Cloud task priority triage under class imbalance: An explainable stacked ensemble approach
- 16 July 2026
- Published by Elsevier in Information Sciences
- Vol. 757
Silent corruption: Logic collapse and attribution fidelity failure in compressed intrusion detection systems
- 16 July 2026
- Published by Elsevier in Information Sciences
- Vol. 757
Silent corruption: Logic collapse and attribution fidelity failure in compressed intrusion detection systems
- 16 February 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 170
Anti-forensic for quantization steps estimation based on direct and preemptive adversarial attacks
- 16 February 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 170
Anti-forensic for quantization steps estimation based on direct and preemptive adversarial attacks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4005-4020
HENet: A Heterogeneous Encoding Network for General and Robust Adversarial Example Generation
Generator-based adversarial attack methods aim to fool deep neural networks (DNNs) by training a generator for crafting adversarial examples (AEs). However, as DNNs evolve from Convolutional Neural Networks (CNNs) to Transformers, the existing generator-based methods can hardly achieve satisfactory attack performance against different target model architectures in semi-whitebox attack scenarios. In addition, the generated AEs are susceptible to various distortions (especially for JPEG compression with low quality factors), which deteriorate the attack ability and increase the unreliability. To address these issues, we propose a dual-branch guided generative model called Heterogeneous Encoding Network (HENet) to form a robust generator-based adversarial attack framework. Specifically, our HENet introduces an Adaptive Feature Fusion Module (AFFM) to solve the dimensions and representativeness contradictions between CNNs and Transformers, which steers the perturbation generation based on a richer latent space and achieves better general attack ability. To further improve the robustness against JPEG compression, we design and integrate a Dynamic Differentiable JPEG Simulator (DDJS), which introduces an adaptive quantization mask to determine the flow of the gradient backpropagation in each frequency position. Extensive experiments prove the proposed method achieves a better attack success rate, lower perturbation magnitude, and higher robustness for various target network architectures under compressed, distorted, and lossless scenarios. Our codes will be made publicly available.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4005-4020
HENet: A Heterogeneous Encoding Network for General and Robust Adversarial Example Generation
Generator-based adversarial attack methods aim to fool deep neural networks (DNNs) by training a generator for crafting adversarial examples (AEs). However, as DNNs evolve from Convolutional Neural Networks (CNNs) to Transformers, the existing generator-based methods can hardly achieve satisfactory attack performance against different target model architectures in semi-whitebox attack scenarios. In addition, the generated AEs are susceptible to various distortions (especially for JPEG compression with low quality factors), which deteriorate the attack ability and increase the unreliability. To address these issues, we propose a dual-branch guided generative model called Heterogeneous Encoding Network (HENet) to form a robust generator-based adversarial attack framework. Specifically, our HENet introduces an Adaptive Feature Fusion Module (AFFM) to solve the dimensions and representativeness contradictions between CNNs and Transformers, which steers the perturbation generation based on a richer latent space and achieves better general attack ability. To further improve the robustness against JPEG compression, we design and integrate a Dynamic Differentiable JPEG Simulator (DDJS), which introduces an adaptive quantization mask to determine the flow of the gradient backpropagation in each frequency position. Extensive experiments prove the proposed method achieves a better attack success rate, lower perturbation magnitude, and higher robustness for various target network architectures under compressed, distorted, and lossless scenarios. Our codes will be made publicly available.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8769-8777
DVW: Diffusion Visible Watermark
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8769-8777
Open AccessDVW: Diffusion Visible Watermark
- 23 April 2025
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 110
A GAN-based anti-forensics method by modifying the quantization table in JPEG header file
- 23 April 2025
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 110
A GAN-based anti-forensics method by modifying the quantization table in JPEG header file
- 10 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (7) , 1761-1775
Defense Against Adversarial Faces at the Source: Strengthened Faces Based on Hidden Disturbances
Face Recognition (FR) systems, while widely used across various sectors, are vulnerable to adversarial attacks, particularly those based on deep neural networks. Despite existing efforts to enhance the robustness of FR models, they still face the risk of secondary adversarial attacks. To address this, we propose a novel approach employing “strengthened face” with preemptive defensive perturbations. Strengthened face ensures original recognition accuracy while safeguarding FR systems against secondary attacks. In the white-box scenario, the strengthened face utilizes gradient-based and optimization-based methods to minimize feature representation differences between face pairs. For the black-box scenario, we propose Shielded Gradient Sign Descent (SGSD) to optimize the gradient update direction of strengthened faces, ensuring the transferability and effectiveness against unknown adversarial attacks. Experimental results demonstrate the efficacy of strengthened faces in defending against adversarial faces without compromising the performance of FR models or face image visual quality. Moreover, SGSD outperforms conventional methods, achieving an average performance improvement of 4% in transferability across different attack intensities.
- 10 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (7) , 1761-1775
Defense Against Adversarial Faces at the Source: Strengthened Faces Based on Hidden Disturbances
Face Recognition (FR) systems, while widely used across various sectors, are vulnerable to adversarial attacks, particularly those based on deep neural networks. Despite existing efforts to enhance the robustness of FR models, they still face the risk of secondary adversarial attacks. To address this, we propose a novel approach employing “strengthened face” with preemptive defensive perturbations. Strengthened face ensures original recognition accuracy while safeguarding FR systems against secondary attacks. In the white-box scenario, the strengthened face utilizes gradient-based and optimization-based methods to minimize feature representation differences between face pairs. For the black-box scenario, we propose Shielded Gradient Sign Descent (SGSD) to optimize the gradient update direction of strengthened faces, ensuring the transferability and effectiveness against unknown adversarial attacks. Experimental results demonstrate the efficacy of strengthened faces in defending against adversarial faces without compromising the performance of FR models or face image visual quality. Moreover, SGSD outperforms conventional methods, achieving an average performance improvement of 4% in transferability across different attack intensities.
- Open Access
- 24 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (2) , 1-22
Invisible Adversarial Watermarking: A Novel Security Mechanism for Enhancing Copyright Protection
Invisible watermarking can be used as an important tool for copyright certification in the Metaverse. However, with the advent of deep learning, Deep Neural Networks (DNNs) have posed new threats to this technique. For example, artificially trained DNNs can perform unauthorized content analysis and achieve illegal access to protected images. Furthermore, some specially crafted DNNs may even erase invisible watermarks embedded within the protected images, which eventually leads to the collapse of this protection and certification mechanism. To address these issues, inspired by the adversarial attack, we introduce Invisible Adversarial Watermarking (IAW), a novel security mechanism to enhance the copyright protection efficacy of watermarks. Specifically, we design an Adversarial Watermarking Fusion Model (AWFM) to efficiently generate Invisible Adversarial Watermark Images (IAWIs). By modeling the embedding of watermarks and adversarial perturbations as a unified task, the generated IAWIs can effectively defend against unauthorized identification, access, and erase via DNNs and identify the ownership by extracting the embedded watermark. Experimental results show that the proposed IAW presents superior extraction accuracy, attack ability, and robustness on different DNNs, and the protected images maintain good visual quality, which ensures its effectiveness as an image protection mechanism.
- 24 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (2) , 1-22
Open AccessInvisible Adversarial Watermarking: A Novel Security Mechanism for Enhancing Copyright Protection
Invisible watermarking can be used as an important tool for copyright certification in the Metaverse. However, with the advent of deep learning, Deep Neural Networks (DNNs) have posed new threats to this technique. For example, artificially trained DNNs can perform unauthorized content analysis and achieve illegal access to protected images. Furthermore, some specially crafted DNNs may even erase invisible watermarks embedded within the protected images, which eventually leads to the collapse of this protection and certification mechanism. To address these issues, inspired by the adversarial attack, we introduce Invisible Adversarial Watermarking (IAW), a novel security mechanism to enhance the copyright protection efficacy of watermarks. Specifically, we design an Adversarial Watermarking Fusion Model (AWFM) to efficiently generate Invisible Adversarial Watermark Images (IAWIs). By modeling the embedding of watermarks and adversarial perturbations as a unified task, the generated IAWIs can effectively defend against unauthorized identification, access, and erase via DNNs and identify the ownership by extracting the embedded watermark. Experimental results show that the proposed IAW presents superior extraction accuracy, attack ability, and robustness on different DNNs, and the protected images maintain good visual quality, which ensures its effectiveness as an image protection mechanism.
- Open Access
- 25 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 7867-7877
Adaptive Spatial Regularization Correlation Filters for UAV Tracking
As a tool for near-earth remote sensing, unmanned aerial vehicle (UAV) can be used to acquire images and data of the earth's surface. This provides a powerful support for Earth observation and resource management. Object tracking in UAV videos has been a topic of much interest in recent years. A large number of algorithms have been proposed. Among these algorithms, deep learning has achieved a high accuracy rate. However, it is difficult to carry hardware devices for UAV, which makes it difficult to be practically applied. The correlation filter does not require a graphic processing unit (GPU) to accelerate the computation, but it uses only manual features, which makes it difficult to achieve satisfactory performance. In order to solve the above problems, we proposed adaptive spatial regularization correlation filters, called DTSRT. Specifically, we first introduce deep features in the correlation filter instead of the original manual features, which can greatly improve the discriminative ability of the model. At the same time, in order to prevent affecting the real-time performance of the algorithm, we use histogram of oriented gradients (HOG) features to determine the target scale and deep features to determine the target location. In addition, considering the large inter-frame distance between targets in UAV videos, we use a saliency detection method to dynamically generate spatially constrained templates. The proposed DTSRT outperforms other state-of-the-art algorithms with area under curve (AUC) of 0.481, 0.431, and 0.474 on UAV123@10FPS, UAVDT, and DTB70 datasets, respectively.
- 25 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 7867-7877
Open AccessAdaptive Spatial Regularization Correlation Filters for UAV Tracking
As a tool for near-earth remote sensing, unmanned aerial vehicle (UAV) can be used to acquire images and data of the earth's surface. This provides a powerful support for Earth observation and resource management. Object tracking in UAV videos has been a topic of much interest in recent years. A large number of algorithms have been proposed. Among these algorithms, deep learning has achieved a high accuracy rate. However, it is difficult to carry hardware devices for UAV, which makes it difficult to be practically applied. The correlation filter does not require a graphic processing unit (GPU) to accelerate the computation, but it uses only manual features, which makes it difficult to achieve satisfactory performance. In order to solve the above problems, we proposed adaptive spatial regularization correlation filters, called DTSRT. Specifically, we first introduce deep features in the correlation filter instead of the original manual features, which can greatly improve the discriminative ability of the model. At the same time, in order to prevent affecting the real-time performance of the algorithm, we use histogram of oriented gradients (HOG) features to determine the target scale and deep features to determine the target location. In addition, considering the large inter-frame distance between targets in UAV videos, we use a saliency detection method to dynamically generate spatially constrained templates. The proposed DTSRT outperforms other state-of-the-art algorithms with area under curve (AUC) of 0.481, 0.431, and 0.474 on UAV123@10FPS, UAVDT, and DTB70 datasets, respectively.