Xingyuan Li
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
Xingyuan Li has a total of 91 co-authors. Here are the top co-authors by number of shared publications:
- Jinyuan Liu
Dalian University of Technology, Dalian, China
9 shared publications - Xiang Chen
Zhejiang University, Hangzhou, Zhejiang, China
4 shared publications - Yang Zou
National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology and the College of Computer Science, Northwestern Polytechnical University, Xian, ShaanXi, China
4 shared publications - Zhiying Jiang
Dalian Maritime University, Dalian, China
4 shared publications - Chunming Wu
Zhejiang University, Hangzhou, China
3 shared publications - Jiajie Su
Zhejiang University
3 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 113-128
Medivh: Harnessing Compatible and Accurate Sketch-based Network Measurement with Sparsity-based Virtualization
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 113-128
Open AccessMedivh: Harnessing Compatible and Accurate Sketch-based Network Measurement with Sparsity-based Virtualization
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11278-11286
SGPDFuse: Semantically-Guided Physics-Disentanglement General Multi-Modal Image Fusion
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11278-11286
Open AccessSGPDFuse: Semantically-Guided Physics-Disentanglement General Multi-Modal Image Fusion
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 747-755
SketchScan: Harnessing Accurate and Low-Cost Multimodal Anomaly Detection in Blockchain Networks
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 747-755
Open AccessSketchScan: Harnessing Accurate and Low-Cost Multimodal Anomaly Detection in Blockchain Networks
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14118-14127
Decoupling Corruption from Observation: A Physics-Informed Generative Model for Infrared Image Super-Resolution
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14118-14127
Open AccessDecoupling Corruption from Observation: A Physics-Informed Generative Model for Infrared Image Super-Resolution
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 15161-15178
Symbiotic Evolutionary Learning for Task-Adaptive Infrared and Visible Image Fusion
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 15161-15178
Symbiotic Evolutionary Learning for Task-Adaptive Infrared and Visible Image Fusion
- 15 September 2026
- Published by Springer Nature
- p. 279-298
Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-Step Diffusion Framework
- 15 September 2026
- Published by Springer Nature
- p. 279-298
Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-Step Diffusion Framework
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13123-13134
OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization
\noindent Network planning optimization is a fundamental problem across diverse domains, including transportation systems, communication networks, and power grids. It requires simultaneous optimization of multiple competing objectives under complex constraints. Existing network planning optimization frameworks rely on mixed integer programming (MIP) solvers, heuristics, and deep reinforcement learning (DRL) models to compute planning decisions. However, they lack effective adaptability to diverse and dynamic user intents, thus leading to the trade-off between execution time and optimality. In this paper, we propose OmniPlan, an adaptive framework that achieves both timeliness and near-optimality in network planning optimization. To achieve the adaptability lacking in existing solutions, OmniPlan employs a large language model (LLM)-based interpreter to convert heterogeneous natural-language intents into a unified and quantifiable user-preference vector. Then it employs a mixture-of-experts architecture that integrates MIP solvers, heuristics, and DRL models as specialized experts, where OmniPlan adapts to diverse intents by dynamically selecting timely and near-optimal experts. Finally, it incorporates a DRL-based expert configuration module that fine-tunes optimization objective weights to align planning decisions with user-specific preferences. We evaluate OmniPlan with a representative real-world workload, i.e., distributed machine learning (ML), where we leverage OmniPlan to offload a wide spectrum of ML inference tasks, e.g., decision trees, SVM, naive Bayes, XGBoost, and random forests, onto a network of hardware devices. Our experiments on a real-world testbed indicate that OmniPlan achieves near-optimal and low-execution-time offloading for real-world ML inference tasks, reducing latency by up to 97.8% and network device resource consumption by up to 11.5%.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13123-13134
Open AccessOmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization
\noindent Network planning optimization is a fundamental problem across diverse domains, including transportation systems, communication networks, and power grids. It requires simultaneous optimization of multiple competing objectives under complex constraints. Existing network planning optimization frameworks rely on mixed integer programming (MIP) solvers, heuristics, and deep reinforcement learning (DRL) models to compute planning decisions. However, they lack effective adaptability to diverse and dynamic user intents, thus leading to the trade-off between execution time and optimality. In this paper, we propose OmniPlan, an adaptive framework that achieves both timeliness and near-optimality in network planning optimization. To achieve the adaptability lacking in existing solutions, OmniPlan employs a large language model (LLM)-based interpreter to convert heterogeneous natural-language intents into a unified and quantifiable user-preference vector. Then it employs a mixture-of-experts architecture that integrates MIP solvers, heuristics, and DRL models as specialized experts, where OmniPlan adapts to diverse intents by dynamically selecting timely and near-optimal experts. Finally, it incorporates a DRL-based expert configuration module that fine-tunes optimization objective weights to align planning decisions with user-specific preferences. We evaluate OmniPlan with a representative real-world workload, i.e., distributed machine learning (ML), where we leverage OmniPlan to offload a wide spectrum of ML inference tasks, e.g., decision trees, SVM, naive Bayes, XGBoost, and random forests, onto a network of hardware devices. Our experiments on a real-world testbed indicate that OmniPlan achieves near-optimal and low-execution-time offloading for real-world ML inference tasks, reducing latency by up to 97.8% and network device resource consumption by up to 11.5%.
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 9848-9861
AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation
Object pose estimation is a fundamental task in computer vision and plays an important role in various applications such as robotics, augmented reality, and autonomous manipulation. Existing studies often demand complex inputs or depend on correspondence-based matching between 2D image features and 3D object representations. While effective, these methods rely strongly on explicit appearance matching, often requiring multi-view inputs, depth sensors, or CAD models, which limits their scalability and robustness. Building on top of the pioneering generative studies, we propose AxisPose, a model-free, matching-free, and single-view 6D pose estimation framework that departs from conventional correspondence-based paradigms. Unlike existing methods, AxisPose directly infers a pose representation by learning a latent distribution of object orientation axes through a diffusion model. Specifically, AxisPose introduces an Axis Generation Module (AGM) that progressively denoises tri-axial orientation fields guided by geometric consistency constraints, and a Triaxial Back-projection Module (TBM) to recover the final 6D pose from the generated orientation axes without relying on explicit 2D- 2D/3D correspondences. AxisPose achieves strong cross-instance generalization, enabling a single model to handle multiple object categories without retraining. Extensive experiments on LINEMOD and YCB-Video datasets demonstrate that AxisPose improves the Average Distance Deviation score from 0.733 to 0.814 over the strong baseline NOPE, using only a single RGB input. The code is available at https://github.com/pubyLu/AxisPose/tree/main.
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 9848-9861
AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation
Object pose estimation is a fundamental task in computer vision and plays an important role in various applications such as robotics, augmented reality, and autonomous manipulation. Existing studies often demand complex inputs or depend on correspondence-based matching between 2D image features and 3D object representations. While effective, these methods rely strongly on explicit appearance matching, often requiring multi-view inputs, depth sensors, or CAD models, which limits their scalability and robustness. Building on top of the pioneering generative studies, we propose AxisPose, a model-free, matching-free, and single-view 6D pose estimation framework that departs from conventional correspondence-based paradigms. Unlike existing methods, AxisPose directly infers a pose representation by learning a latent distribution of object orientation axes through a diffusion model. Specifically, AxisPose introduces an Axis Generation Module (AGM) that progressively denoises tri-axial orientation fields guided by geometric consistency constraints, and a Triaxial Back-projection Module (TBM) to recover the final 6D pose from the generated orientation axes without relying on explicit 2D- 2D/3D correspondences. AxisPose achieves strong cross-instance generalization, enabling a single model to handle multiple object categories without retraining. Extensive experiments on LINEMOD and YCB-Video datasets demonstrate that AxisPose improves the Average Distance Deviation score from 0.733 to 0.814 over the strong baseline NOPE, using only a single RGB input. The code is available at https://github.com/pubyLu/AxisPose/tree/main.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- p. 1
Degradation-aware Infrared Image Super-Resolution
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- p. 1
Open AccessDegradation-aware Infrared Image Super-Resolution
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1268-1277
Toward a Training-Free Plug-and-Play Refinement Framework for Infrared and Visible Image Registration and Fusion
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1268-1277
Open AccessToward a Training-Free Plug-and-Play Refinement Framework for Infrared and Visible Image Registration and Fusion