Jun Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jun Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Huan Li
Zhejiang University
2 shared publications - Ke Chen
Zhejiang University
2 shared publications - Lidan Shou
Zhejiang University
2 shared publications - Chunjie Cao
Hainan University
1 shared publication - Dingyu Yang
Zhejiang University
1 shared publication - Gang Chen
Zhejiang University
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 956-967
Road-Constrained Vehicle Trajectory Recovery from Traffic Video Using Spatio-Temporal Voxel Representation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 956-967
Open AccessRoad-Constrained Vehicle Trajectory Recovery from Traffic Video Using Spatio-Temporal Voxel Representation
- 14 May 2025
- Published by Springer Nature in The VLDB Journal
- Vol. 34 (4) , 1-26
HMI: hierarchical knowledge management for efficient multi-tenant inference in pretrained language models
- 14 May 2025
- Published by Springer Nature in The VLDB Journal
- Vol. 34 (4) , 1-26
HMI: hierarchical knowledge management for efficient multi-tenant inference in pretrained language models
- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (6) , 3088-3102
CHASe: Client Heterogeneity-Aware Data Selection for Effective Federated Active Learning
Active learning (AL) reduces human annotation costs for machine learning systems by strategically selecting the most informative unlabeled data for annotation, but performing it individually may still be insufficient due to restricted data diversity and annotation budget. Federated Active Learning (FAL) addresses this by facilitating collaborative data selection and model training, while preserving the confidentiality of raw data samples. Yet, existing FAL methods fail to account for the heterogeneity of data distribution across clients and the associated fluctuations in global and local model parameters, adversely affecting model accuracy. To overcome these challenges, we propose${\sf CHASe}$ (Client Heterogeneity-Aware Data Selection), specifically designed for FAL.${\sf CHASe}$ focuses on identifying those unlabeled samples with high epistemic variations (EVs), which notably oscillate around the decision boundaries during training. To achieve both effectiveness and efficiency,${\sf CHASe}$ encompasses techniques for 1) tracking EVs by analyzing inference inconsistencies across training epochs, 2) calibrating decision boundaries of inaccurate models with a new alignment loss, and 3) enhancing data selection efficiency via a data freeze and awaken mechanism with subset sampling. Experiments show that${\sf CHASe}$ surpasses various established baselines in terms of effectiveness and efficiency, validated across diverse datasets, model complexities, and heterogeneous federation settings.- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (6) , 3088-3102
CHASe: Client Heterogeneity-Aware Data Selection for Effective Federated Active Learning
Active learning (AL) reduces human annotation costs for machine learning systems by strategically selecting the most informative unlabeled data for annotation, but performing it individually may still be insufficient due to restricted data diversity and annotation budget. Federated Active Learning (FAL) addresses this by facilitating collaborative data selection and model training, while preserving the confidentiality of raw data samples. Yet, existing FAL methods fail to account for the heterogeneity of data distribution across clients and the associated fluctuations in global and local model parameters, adversely affecting model accuracy. To overcome these challenges, we propose${\sf CHASe}$ (Client Heterogeneity-Aware Data Selection), specifically designed for FAL.${\sf CHASe}$ focuses on identifying those unlabeled samples with high epistemic variations (EVs), which notably oscillate around the decision boundaries during training. To achieve both effectiveness and efficiency,${\sf CHASe}$ encompasses techniques for 1) tracking EVs by analyzing inference inconsistencies across training epochs, 2) calibrating decision boundaries of inaccurate models with a new alignment loss, and 3) enhancing data selection efficiency via a data freeze and awaken mechanism with subset sampling. Experiments show that${\sf CHASe}$ surpasses various established baselines in terms of effectiveness and efficiency, validated across diverse datasets, model complexities, and heterogeneous federation settings.- Open Access
- 1 January 2019
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2019 (1)
Adaptive Robust Blind Watermarking Scheme Improved by Entropy‐Based SVM and Optimized Quantum Genetic Algorithm
With the intensive study of machine learning in digital watermarking, its ability to balance the robustness and transparency of watermarking technology has attracted researchers’ attention. Therefore, quantum genetic algorithm, which serves as an intelligent optimized scheme combined with biological genetic mechanism and quantum computing, is widely used in various fields. In this study, an adaptive robust blind watermarking algorithm by means of optimized quantum genetics (OQGA) and entropy classification‐based SVM (support vector machine) is proposed. The host image was divided into two parts according to the odd and even rows of the host image. One part was transformed by DCT (discrete cosine transform), and then the embedding intensity and position were separately trained by entropy‐based SVM and OQGA; the other part was by DWT (discrete wavelet transform), in which the key fusion was achieved by an ergodic matrix to embed the watermark. Simulation results indicate the proposed algorithm ensures the watermark scheme transparency as well as having better resistance to common attacks such as lossy JPEG compression, image darken, Gaussian low‐pass filtering, contrast decreasing, salt‐pepper noise, and geometric attacks such as rotation and cropping.
- 1 January 2019
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2019 (1)
Open AccessAdaptive Robust Blind Watermarking Scheme Improved by Entropy‐Based SVM and Optimized Quantum Genetic Algorithm
With the intensive study of machine learning in digital watermarking, its ability to balance the robustness and transparency of watermarking technology has attracted researchers’ attention. Therefore, quantum genetic algorithm, which serves as an intelligent optimized scheme combined with biological genetic mechanism and quantum computing, is widely used in various fields. In this study, an adaptive robust blind watermarking algorithm by means of optimized quantum genetics (OQGA) and entropy classification‐based SVM (support vector machine) is proposed. The host image was divided into two parts according to the odd and even rows of the host image. One part was transformed by DCT (discrete cosine transform), and then the embedding intensity and position were separately trained by entropy‐based SVM and OQGA; the other part was by DWT (discrete wavelet transform), in which the key fusion was achieved by an ergodic matrix to embed the watermark. Simulation results indicate the proposed algorithm ensures the watermark scheme transparency as well as having better resistance to common attacks such as lossy JPEG compression, image darken, Gaussian low‐pass filtering, contrast decreasing, salt‐pepper noise, and geometric attacks such as rotation and cropping.