Xumeng Wang
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
Research Subjects
Research Interests
Xumeng Wang has a total of 75 co-authors. Here are the top co-authors by number of shared publications:
- Wei Chen
Zhejiang University, Hangzhou, Zhejiang, China
11 shared publications - Fei-Yue Wang
Institute of Automation, Chinese Academy of Sciences
4 shared publications - Kwan-Liu Ma
Department of Computer Science, University of California, Davis, USA
3 shared publications - Xingxia Wang
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
3 shared publications - Chris Bryan
Arizona State University
2 shared publications - Minfeng Zhu
Zhejiang University, Hangzhou, Zhejiang, China
2 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (10) , 8352-8363
PatternSight: A Perceptual Grouping Effectiveness Assessment Approach for Elements in Charts
The boom in visualization generation tools has significantly lowered the threshold for chart authoring. However, without a solid grasp of perceptual mechanisms, chart authors may struggle to assess the effectiveness of their designs and to select a suitable representation for conveying intended data patterns. To address this issue, we propose a perceptual grouping simulation model that can predict how chart viewers perceptu ally organize visual elements into element groups perceived as graphical patterns. The perceptual grouping simulation model integrates perceptual grouping principles into visual feature extraction of chart elements to provide interpretable model outcomes. Empirical evaluation with human participants demon strated that our model can effectively learn the perceptual grouping tendencies of most viewers and accommodate a diversity of perceptual grouping outcomes. We also embed the model into a prototype interface called PatternSight to facilitate chart authors in assessing whether the chart design can satisfy their pattern representation requirements and determining feasible improvements of visual design. According to user experiment results, PatternSight can effectively assist chart authors in optimizing chart design for representing data patterns.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (10) , 8352-8363
PatternSight: A Perceptual Grouping Effectiveness Assessment Approach for Elements in Charts
The boom in visualization generation tools has significantly lowered the threshold for chart authoring. However, without a solid grasp of perceptual mechanisms, chart authors may struggle to assess the effectiveness of their designs and to select a suitable representation for conveying intended data patterns. To address this issue, we propose a perceptual grouping simulation model that can predict how chart viewers perceptu ally organize visual elements into element groups perceived as graphical patterns. The perceptual grouping simulation model integrates perceptual grouping principles into visual feature extraction of chart elements to provide interpretable model outcomes. Empirical evaluation with human participants demon strated that our model can effectively learn the perceptual grouping tendencies of most viewers and accommodate a diversity of perceptual grouping outcomes. We also embed the model into a prototype interface called PatternSight to facilitate chart authors in assessing whether the chart design can satisfy their pattern representation requirements and determining feasible improvements of visual design. According to user experiment results, PatternSight can effectively assist chart authors in optimizing chart design for representing data patterns.
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23  (5) , 11796-11807
PrivAnalogy: An Analogy Mechanism-Based Privacy Protection Framework for LLM Prompts
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23  (5) , 11796-11807
PrivAnalogy: An Analogy Mechanism-Based Privacy Protection Framework for LLM Prompts
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (8) , 7577-7591
VidGuard3D: A Visual Risk Analysis Approach for Protecting 3D Assets Against Video-Based Reconstruction Attacks
The unauthorized acquisition of 3D assets by means of advanced techniques in 3D reconstruction is a major but often overlooked threat to publishers of videos. Preventing such threats is challenging due to the uninterpretable nature of 3D reconstruction and the diversity in requirements of 3D model demonstration. In this paper, we introduce VidGuard3D—a visual risk analysis approach that quantifies and locates the sources of risk for video-based 3D asset reconstruction attacks. Our approach uses attack simulation to support users in formulating a comprehensive understanding of 3D asset leakage risks, with a particular focus on the correlations between video segments and exposure risks of user-specified areas in the asset. We also proposed a prototype system that integrates this approach to facilitate video editing according to the knowledge of correlations. Two operations of video editing can be swiftly applied by users to form editing plans and minimize detected leakage risks. Finally, we conducted a user study and case studies that demonstrated the practicality and effectiveness of our approach. Our source code is provided at https://github.com/wyysteelhead/VidGuard3D.
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (8) , 7577-7591
VidGuard3D: A Visual Risk Analysis Approach for Protecting 3D Assets Against Video-Based Reconstruction Attacks
The unauthorized acquisition of 3D assets by means of advanced techniques in 3D reconstruction is a major but often overlooked threat to publishers of videos. Preventing such threats is challenging due to the uninterpretable nature of 3D reconstruction and the diversity in requirements of 3D model demonstration. In this paper, we introduce VidGuard3D—a visual risk analysis approach that quantifies and locates the sources of risk for video-based 3D asset reconstruction attacks. Our approach uses attack simulation to support users in formulating a comprehensive understanding of 3D asset leakage risks, with a particular focus on the correlations between video segments and exposure risks of user-specified areas in the asset. We also proposed a prototype system that integrates this approach to facilitate video editing according to the knowledge of correlations. Two operations of video editing can be swiftly applied by users to form editing plans and minimize detected leakage risks. Finally, we conducted a user study and case studies that demonstrated the practicality and effectiveness of our approach. Our source code is provided at https://github.com/wyysteelhead/VidGuard3D.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
TSEditor: Interactive Time Series Editing for Privacy Preservation
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessTSEditor: Interactive Time Series Editing for Privacy Preservation
- Retraction
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. PP  (23798858) , 1
Retraction Notice: Sora for Intelligent Vehicles: A Step From Constraint-Based Simulation to Artificiofactual Experiments Through Dynamic Visualization
Scenario simulation plays an integral role in the development, application, and management of intelligent vehicles. However, planning agents and customizing scenarios for complex systems are laborious, making it challenging to implement high-performance simulations. The striking progress made by Sora, a large-scale text-to-video model, suggests a research opportunity for high-performance simulation through dynamic visualizations. This paper reports the prospective effects of Sora on the scenario simulation of intelligent vehicles. Specifically, we review the achievements of Sora, picture the perspectives of artificiofactual experiments on intelligent vehicles based on the performance of Sora-type techniques, and discuss how far are we now.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. PP  (23798858) , 1
RetractionRetraction Notice: Sora for Intelligent Vehicles: A Step From Constraint-Based Simulation to Artificiofactual Experiments Through Dynamic Visualization
Scenario simulation plays an integral role in the development, application, and management of intelligent vehicles. However, planning agents and customizing scenarios for complex systems are laborious, making it challenging to implement high-performance simulations. The striking progress made by Sora, a large-scale text-to-video model, suggests a research opportunity for high-performance simulation through dynamic visualizations. This paper reports the prospective effects of Sora on the scenario simulation of intelligent vehicles. Specifically, we review the achievements of Sora, picture the perspectives of artificiofactual experiments on intelligent vehicles based on the performance of Sora-type techniques, and discuss how far are we now.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (2) , 2366-2378
A Utility-Aware Privacy-Preserving Method for Trajectory Publication
The security of individual privacy is paramount for trajectory publication, while preserving trajectory utility is also essential to serve analysis tasks such as urban planning and transportation development. To assess and maintain trajectory utility, existing studies consider geographic context. However, innate semantic characteristics of trajectories (e.g., origin, destination, stay point, path) have been overlooked, which prevents data owners from specifying task-specific utility measurements and, consequently, from achieving a delicate balance between privacy and utility. This paper proposes an interactive trajectory publishing approach driven by flexible utility considerations, which processes trajectory points according to their semantics to fulfill diverse utility requirements. Concretely, we decouple trajectories into origin–destination (OD) and path components: ODs are generalized into regions to satisfy $k$-anonymity, and paths are sanitized within each OD group using road-network–aware differential privacy under predefined privacy constraints. We also develop a visual interface to support exploration and comprehension of privacy-preserving solutions, through which we incorporate human knowledge into the privacy scheme. Experiments on real-world urban datasets demonstrate the effectiveness of our approach.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (2) , 2366-2378
A Utility-Aware Privacy-Preserving Method for Trajectory Publication
The security of individual privacy is paramount for trajectory publication, while preserving trajectory utility is also essential to serve analysis tasks such as urban planning and transportation development. To assess and maintain trajectory utility, existing studies consider geographic context. However, innate semantic characteristics of trajectories (e.g., origin, destination, stay point, path) have been overlooked, which prevents data owners from specifying task-specific utility measurements and, consequently, from achieving a delicate balance between privacy and utility. This paper proposes an interactive trajectory publishing approach driven by flexible utility considerations, which processes trajectory points according to their semantics to fulfill diverse utility requirements. Concretely, we decouple trajectories into origin–destination (OD) and path components: ODs are generalized into regions to satisfy $k$-anonymity, and paths are sanitized within each OD group using road-network–aware differential privacy under predefined privacy constraints. We also develop a visual interface to support exploration and comprehension of privacy-preserving solutions, through which we incorporate human knowledge into the privacy scheme. Experiments on real-world urban datasets demonstrate the effectiveness of our approach.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31  (1) , 448-458
Defogger: A Visual Analysis Approach for Data Exploration of Sensitive Data Protected by Differential Privacy
Differential privacy ensures the security of individual privacy but poses challenges to data exploration processes because the limited privacy budget incapacitates the flexibility of exploration and the noisy feedback of data requests leads to confusing uncertainty. In this study, we take the lead in describing corresponding exploration scenarios, including underlying requirements and available exploration strategies. To facilitate practical applications, we propose a visual analysis approach to the formulation of exploration strategies. Our approach applies a reinforcement learning model to provide diverse suggestions for exploration strategies according to the exploration intent of users. A novel visual design for representing uncertainty in correlation patterns is integrated into our prototype system to support the proposed approach. Finally, we implemented a user study and two case studies. The results of these studies verified that our approach can help develop strategies that satisfy the exploration intent of users.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31  (1) , 448-458
Defogger: A Visual Analysis Approach for Data Exploration of Sensitive Data Protected by Differential Privacy
Differential privacy ensures the security of individual privacy but poses challenges to data exploration processes because the limited privacy budget incapacitates the flexibility of exploration and the noisy feedback of data requests leads to confusing uncertainty. In this study, we take the lead in describing corresponding exploration scenarios, including underlying requirements and available exploration strategies. To facilitate practical applications, we propose a visual analysis approach to the formulation of exploration strategies. Our approach applies a reinforcement learning model to provide diverse suggestions for exploration strategies according to the exploration intent of users. A novel visual design for representing uncertainty in correlation patterns is integrated into our prototype system to support the proposed approach. Finally, we implemented a user study and two case studies. The results of these studies verified that our approach can help develop strategies that satisfy the exploration intent of users.
- Retracted
- 3 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9  (3) , 4249-4253
Retracted: Sora for Intelligent Vehicles: A Step From Constraint-Based Simulation to Artificiofactual Experiments Through Dynamic Visualization
Scenario simulation plays an integral role in the development, application, and management of intelligent vehicles. However, planning agents and customizing scenarios for complex systems are laborious, making it challenging to implement high-performance simulations. The striking progress made by Sora, a large-scale text-to-video model, suggests a research opportunity for high-performance simulation through dynamic visualizations. This paper reports the prospective effects of Sora on the scenario simulation of intelligent vehicles. Specifically, we review the achievements of Sora, picture the perspectives of artificiofactual experiments on intelligent vehicles based on the performance of Sora-type techniques, and discuss how far are we now.
- 3 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9  (3) , 4249-4253
RetractedRetracted: Sora for Intelligent Vehicles: A Step From Constraint-Based Simulation to Artificiofactual Experiments Through Dynamic Visualization
Scenario simulation plays an integral role in the development, application, and management of intelligent vehicles. However, planning agents and customizing scenarios for complex systems are laborious, making it challenging to implement high-performance simulations. The striking progress made by Sora, a large-scale text-to-video model, suggests a research opportunity for high-performance simulation through dynamic visualizations. This paper reports the prospective effects of Sora on the scenario simulation of intelligent vehicles. Specifically, we review the achievements of Sora, picture the perspectives of artificiofactual experiments on intelligent vehicles based on the performance of Sora-type techniques, and discuss how far are we now.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 8  (11) , 4653-4663
Vehicular Visualization: Enhancing Mobility Decisions With Human–Machine Interactions
In the age of intelligence, humans pursue a safe and convenient mobility experience. Intelligent vehicles have integrated various machine intelligence to support humans in making decisions on mobility. However, the support fails to meet human expectations because machine intelligence lacks a method to communicate with humans—verify the understanding of human needs, and explain how machine intelligence works. In this study, we address this issue through vehicular visualizations. Specifically, we summarize the decision-making requirements of humans, introduce how can techniques of vehicular visualizations satisfy these needs, describe prospective application scenes, and discuss future directions of vehicular visualizations to inspire related scholars or developers.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 8  (11) , 4653-4663
Vehicular Visualization: Enhancing Mobility Decisions With Human–Machine Interactions
In the age of intelligence, humans pursue a safe and convenient mobility experience. Intelligent vehicles have integrated various machine intelligence to support humans in making decisions on mobility. However, the support fails to meet human expectations because machine intelligence lacks a method to communicate with humans—verify the understanding of human needs, and explain how machine intelligence works. In this study, we address this issue through vehicular visualizations. Specifically, we summarize the decision-making requirements of humans, introduce how can techniques of vehicular visualizations satisfy these needs, describe prospective application scenes, and discuss future directions of vehicular visualizations to inspire related scholars or developers.
- 27 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 29  (6) , 2849-2861
FraudAuditor: A Visual Analytics Approach for Collusive Fraud in Health Insurance
Collusive fraud, in which multiple fraudsters collude to defraud health insurance funds, threatens the operation of the healthcare system. However, existing statistical and machine learning-based methods have limited ability to detect fraud in the scenario of health insurance due to the high similarity of fraudulent behaviors to normal medical visits and the lack of labeled data. To ensure the accuracy of the detection results, expert knowledge needs to be integrated with the fraud detection process. By working closely with health insurance audit experts, we propose FraudAuditor , a three-stage visual analytics approach to collusive fraud detection in health insurance. Specifically, we first allow users to interactively construct a co-visit network to holistically model the visit relationships of different patients. Second, an improved community detection algorithm that considers the strength of fraud likelihood is designed to detect suspicious fraudulent groups. Finally, through our visual interface, users can compare, investigate, and verify suspicious patient behavior with tailored visualizations that support different time scales. We conducted case studies in a real-world healthcare scenario, i.e., to help locate the actual fraud group and exclude the false positive group. The results and expert feedback proved the effectiveness and usability of the approach.
- 27 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 29  (6) , 2849-2861
FraudAuditor: A Visual Analytics Approach for Collusive Fraud in Health Insurance
Collusive fraud, in which multiple fraudsters collude to defraud health insurance funds, threatens the operation of the healthcare system. However, existing statistical and machine learning-based methods have limited ability to detect fraud in the scenario of health insurance due to the high similarity of fraudulent behaviors to normal medical visits and the lack of labeled data. To ensure the accuracy of the detection results, expert knowledge needs to be integrated with the fraud detection process. By working closely with health insurance audit experts, we propose FraudAuditor , a three-stage visual analytics approach to collusive fraud detection in health insurance. Specifically, we first allow users to interactively construct a co-visit network to holistically model the visit relationships of different patients. Second, an improved community detection algorithm that considers the strength of fraud likelihood is designed to detect suspicious fraudulent groups. Finally, through our visual interface, users can compare, investigate, and verify suspicious patient behavior with tailored visualizations that support different time scales. We conducted case studies in a real-world healthcare scenario, i.e., to help locate the actual fraud group and exclude the false positive group. The results and expert feedback proved the effectiveness and usability of the approach.