Xinhui 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
Research Subjects
Xinhui Li has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Nian Hu
School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China
4 shared publications - Chen Li
Tianjin University of Technology, Tianjin, China
3 shared publications - Yibo Zhao
School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China
3 shared publications - Chunjie Ma
Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
2 shared publications - Cong Liu
Nova Information Management School, Universidade Nova de Lisboa, Lisbon, Portugal
2 shared publications - Zan Gao
School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China and Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong Province, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7526-7535
PhysDiff: Physics-Inspired Diffusion Framework with Dense Captioning for Controllable X-ray Image Generation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7526-7535
Open AccessPhysDiff: Physics-Inspired Diffusion Framework with Dense Captioning for Controllable X-ray Image Generation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7717-7726
HoTFlow: Taming Higher-Order Temporal Action Dynamics via an Improved MeanFlow Policy
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7717-7726
Open AccessHoTFlow: Taming Higher-Order Temporal Action Dynamics via an Improved MeanFlow Policy
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 558-567
Unsupervised 2D Image-Based 3D Model Retrieval via Decision Boundary Alignment and Graph Semantic Propagation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 558-567
Open AccessUnsupervised 2D Image-Based 3D Model Retrieval via Decision Boundary Alignment and Graph Semantic Propagation
- Open Access
- 12 June 2026
- Published by Elsevier in SSRN Electronic Journal
Frequency-Guided Cross-View Interaction Network for Efficient Legal
Legal Judgment Prediction aims to automatically infer judicial outcomes—including accusation charges, relevant statutes, and sentencing terms—from factual descriptions of criminal cases. Although large pretrained transformer models such as BERT achieve strong performance, their substantial computational cost and parameter scale hinder deployment in resource-constrained judicial environments. Existing lightweight architectures improve efficiency but often struggle to simultaneously capture global semantic context and fine-grained structural dependencies in lengthy legal texts.To address this challenge, we propose a Frequency-Guided Cross-View Interaction Network (FGCVIN), a lightweight framework that models complementary representations from multiple structural perspectives. FGCVIN first learns multi-scale semantic representations through a Global Contextual Abstraction Encoder and a Local Dependency Aggregation Encoder, which capture global contextual patterns and coherent local dependencies within legal fact descriptions. To introduce structural priors without increasing parameter complexity, a Frequency-Guided Prior Encoder extracts informative low-frequency signals via windowed Fast Fourier Transform and statistical pooling. Building upon these representations, a Cross-View Residual Attention Fusion module adaptively integrates semantic and structural features through gated residual fusion and attention refinement. A progressive three-stage training strategy further stabilizes the interaction among these components.Experiments on the CAIL benchmark datasets show that FGCVIN consistently outperforms several representative lightweight architectures demonstrating its effectiveness for resource-constrained legal intelligence systems.
- 12 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFrequency-Guided Cross-View Interaction Network for Efficient Legal
Legal Judgment Prediction aims to automatically infer judicial outcomes—including accusation charges, relevant statutes, and sentencing terms—from factual descriptions of criminal cases. Although large pretrained transformer models such as BERT achieve strong performance, their substantial computational cost and parameter scale hinder deployment in resource-constrained judicial environments. Existing lightweight architectures improve efficiency but often struggle to simultaneously capture global semantic context and fine-grained structural dependencies in lengthy legal texts.To address this challenge, we propose a Frequency-Guided Cross-View Interaction Network (FGCVIN), a lightweight framework that models complementary representations from multiple structural perspectives. FGCVIN first learns multi-scale semantic representations through a Global Contextual Abstraction Encoder and a Local Dependency Aggregation Encoder, which capture global contextual patterns and coherent local dependencies within legal fact descriptions. To introduce structural priors without increasing parameter complexity, a Frequency-Guided Prior Encoder extracts informative low-frequency signals via windowed Fast Fourier Transform and statistical pooling. Building upon these representations, a Cross-View Residual Attention Fusion module adaptively integrates semantic and structural features through gated residual fusion and attention refinement. A progressive three-stage training strategy further stabilizes the interaction among these components.Experiments on the CAIL benchmark datasets show that FGCVIN consistently outperforms several representative lightweight architectures demonstrating its effectiveness for resource-constrained legal intelligence systems.
- 2 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 7635-7646
Learning Generalized Knowledge From a Single Domain on Urban-Scene Segmentation
Deep neural networks have made significant progress in various tasks under the assumption of the same distribution between training and testing data. However, the obtained domain-specific knowledge often suffers from performance degradation when facing out-of-distribution data. Towards addressing the degradation, a critical requirement of such networks is the generalization capability to unseen domains, which is the goal of domain generalization (DG). This paper attempts to learn generalized knowledge from a single synthetic domain and then apply it to real and unknown scenarios. Specifically, we propose a contour-aware instance normalization module to effectively learn domain-invariant features via a novel weight-updating strategy, which can largely exploit the generalized information from the observed data. In addition, a category-level contrastive learning mechanism is proposed through understanding the semantic discrepancy and relevance among samples to mitigate the interference of domain-specific features on classification. Extensive experiments together with ablation studies on widely-adopted datasets are conducted to demonstrate the effectiveness of our design and show the superiority of our method over other state-of-the-art schemes on the task of urban-scene segmentation. The source code is available at https://github.com/leelxh/DG-LGK .
- 2 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 7635-7646
Learning Generalized Knowledge From a Single Domain on Urban-Scene Segmentation
Deep neural networks have made significant progress in various tasks under the assumption of the same distribution between training and testing data. However, the obtained domain-specific knowledge often suffers from performance degradation when facing out-of-distribution data. Towards addressing the degradation, a critical requirement of such networks is the generalization capability to unseen domains, which is the goal of domain generalization (DG). This paper attempts to learn generalized knowledge from a single synthetic domain and then apply it to real and unknown scenarios. Specifically, we propose a contour-aware instance normalization module to effectively learn domain-invariant features via a novel weight-updating strategy, which can largely exploit the generalized information from the observed data. In addition, a category-level contrastive learning mechanism is proposed through understanding the semantic discrepancy and relevance among samples to mitigate the interference of domain-specific features on classification. Extensive experiments together with ablation studies on widely-adopted datasets are conducted to demonstrate the effectiveness of our design and show the superiority of our method over other state-of-the-art schemes on the task of urban-scene segmentation. The source code is available at https://github.com/leelxh/DG-LGK .