Hui Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hui Sun has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Chao Liu
Institute of Systems Engineering, Academy of Military Sciences (AMS), People’s Liberation Army of China (PLA), Beijing 100080, China
4 shared publications - Hongtao Song
College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
2 shared publications - Hui Zhang
College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
2 shared publications - Jianguang Ma
Institute of Systems Engineering, Academy of Military Sciences (AMS), People’s Liberation Army of China (PLA), Beijing 100091, China
2 shared publications - Qilong Han
Harbin Engineering University, Harbin, China
2 shared publications - Chengzhi Wang
National Innovation Institute of Defense Technology, Academy of Military Sciences, Beijing 100091, China
1 shared publication
Latest Publications
- Open Access
- 22 September 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (10) , 323
BiMLI: Bidirectional Link–Modality Interaction for Link Prediction in Attribute-Based Multimodal Knowledge Graphs
In attribute-based multimodal knowledge graphs, images and text serve as auxiliary entity attributes, providing semantic evidence beyond graph topology for link prediction. However, bidirectional conditional dependencies between an entity’s multimodal representations and its local links—the one-hop factual triples formed by relations and neighboring entities—remain insufficiently modeled: different local links rely on structural, visual, and textual evidence to varying degrees, and conversely, the relevance of each modality differs across local links. Existing methods have progressed from modality alignment and fusion to relation-aware, structure-aware, and adaptive selection; yet they mainly let information flow from links to modalities, while conditioning on each modality to distinguish and weight individual surrounding links remains underexplored, leaving the two selection directions disconnected. We therefore propose BiMLI, a bidirectional link–modality interaction framework. Link→Modality selects relevant structural, visual, and textual evidence conditioned on each local link, whereas Modality→Link dynamically weights an entity’s surrounding links conditioned on each modality representation. Interaction-aware feature fusion and neighborhood aggregation integrate both representations, with cross-modal contrastive regularization as an auxiliary constraint. Under a controlled comparison using ten matched random seeds, BiMLI attains mean MRR scores of 41.39% and 44.28% on DB15K and MKG-W, exceeding ROAD by 1.79 and 6.18 percentage points, respectively. Ablation and fine-grained analyses show that the two directions are functionally asymmetric yet complementary, providing evidence for the value of bidirectional conditional modeling.
- 22 September 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (10) , 323
Open AccessBiMLI: Bidirectional Link–Modality Interaction for Link Prediction in Attribute-Based Multimodal Knowledge Graphs
In attribute-based multimodal knowledge graphs, images and text serve as auxiliary entity attributes, providing semantic evidence beyond graph topology for link prediction. However, bidirectional conditional dependencies between an entity’s multimodal representations and its local links—the one-hop factual triples formed by relations and neighboring entities—remain insufficiently modeled: different local links rely on structural, visual, and textual evidence to varying degrees, and conversely, the relevance of each modality differs across local links. Existing methods have progressed from modality alignment and fusion to relation-aware, structure-aware, and adaptive selection; yet they mainly let information flow from links to modalities, while conditioning on each modality to distinguish and weight individual surrounding links remains underexplored, leaving the two selection directions disconnected. We therefore propose BiMLI, a bidirectional link–modality interaction framework. Link→Modality selects relevant structural, visual, and textual evidence conditioned on each local link, whereas Modality→Link dynamically weights an entity’s surrounding links conditioned on each modality representation. Interaction-aware feature fusion and neighborhood aggregation integrate both representations, with cross-modal contrastive regularization as an auxiliary constraint. Under a controlled comparison using ten matched random seeds, BiMLI attains mean MRR scores of 41.39% and 44.28% on DB15K and MKG-W, exceeding ROAD by 1.79 and 6.18 percentage points, respectively. Ablation and fine-grained analyses show that the two directions are functionally asymmetric yet complementary, providing evidence for the value of bidirectional conditional modeling.
- Open Access
- 11 August 2026
- Published by MDPI AG in Preprints.org
BiMLI: Bidirectional Link–Modality Interaction for Link Prediction in Attribute-Based Multimodal Knowledge Graphs
In attribute-based multimodal knowledge graphs, images and text serve as auxiliary entity attributes, providing semantic evidence beyond graph topology for link prediction. However, bidirectional conditional dependencies between an entity's multimodal representations and its local links—the one-hop factual triples formed by relations and neighboring entities—remain insufficiently modeled: different local links rely on structural, visual, and textual evidence to varying degrees, and conversely, the relevance of each modality differs across local links. Existing methods have progressed from modality alignment and fusion to relation-aware, structure-aware, and adaptive selection; yet they mainly let information flow from links to modalities, while conditioning on each modality to distinguish and weight individual surrounding links remains underexplored, leaving the two selection directions disconnected. We therefore propose BiMLI, a Bidirectional Link–Modality Interaction framework. Link→Modality selects relevant structural, visual, and textual evidence conditioned on each local link, whereas Modality→Link dynamically weights an entity's surrounding links conditioned on each modality representation. Interaction-aware feature fusion and neighborhood aggregation integrate both representations, with cross-modal contrastive regularization as an auxiliary constraint. On DB15K and MKG-W, BiMLI achieves MRR scores of 42.35% and 43.55%, corresponding to relative improvements of 6.43% and 11.98% over the strongest respective baselines. Ablation and fine-grained analyses show that the two directions are functionally asymmetric yet complementary, validating the necessity of bidirectional conditional modeling.
- 11 August 2026
- Published by MDPI AG in Preprints.org
Open AccessBiMLI: Bidirectional Link–Modality Interaction for Link Prediction in Attribute-Based Multimodal Knowledge Graphs
In attribute-based multimodal knowledge graphs, images and text serve as auxiliary entity attributes, providing semantic evidence beyond graph topology for link prediction. However, bidirectional conditional dependencies between an entity's multimodal representations and its local links—the one-hop factual triples formed by relations and neighboring entities—remain insufficiently modeled: different local links rely on structural, visual, and textual evidence to varying degrees, and conversely, the relevance of each modality differs across local links. Existing methods have progressed from modality alignment and fusion to relation-aware, structure-aware, and adaptive selection; yet they mainly let information flow from links to modalities, while conditioning on each modality to distinguish and weight individual surrounding links remains underexplored, leaving the two selection directions disconnected. We therefore propose BiMLI, a Bidirectional Link–Modality Interaction framework. Link→Modality selects relevant structural, visual, and textual evidence conditioned on each local link, whereas Modality→Link dynamically weights an entity's surrounding links conditioned on each modality representation. Interaction-aware feature fusion and neighborhood aggregation integrate both representations, with cross-modal contrastive regularization as an auxiliary constraint. On DB15K and MKG-W, BiMLI achieves MRR scores of 42.35% and 43.55%, corresponding to relative improvements of 6.43% and 11.98% over the strongest respective baselines. Ablation and fine-grained analyses show that the two directions are functionally asymmetric yet complementary, validating the necessity of bidirectional conditional modeling.
- 30 December 2025
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 68 (1) , 32
Label-enhanced contrastive knowledge distillation
- 30 December 2025
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 68 (1) , 32
Label-enhanced contrastive knowledge distillation
- Open Access
- 4 January 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (1) , 168
Ship Infrared Automatic Target Recognition Based on Bipartite Graph Recommendation: A Model-Matching Method
Deep learning technology has greatly propelled the development of intelligent and information-driven research on ship infrared automatic target recognition (SIATR). In future scenarios, there will be various recognition models with different mechanisms to choose from. However, in complex and dynamic environments, ship infrared (IR) data exhibit rich feature space distribution, resulting in performance variations among SIATR models, thus preventing the existence of a universally superior model for all recognition scenarios. In light of this, this study proposes a model-matching method for SIATR tasks based on bipartite graph theory. This method establishes evaluation criteria based on recognition accuracy and feature learning credibility, uncovering the underlying connections between IR attributes of ships and candidate models. The objective is to selectively recommend the optimal candidate model for a given sample, enhancing the overall recognition performance and applicability of the model. We separately conducted tests for the optimization of accuracy and credibility on high-fidelity simulation data, achieving Accuracy and EDMS (our credibility metric) of 95.86% and 0.7781. Our method improves by 1.06% and 0.0274 for each metric compared to the best candidate models (six in total). Subsequently, we created a recommendation system that balances two tasks, resulting in improvements of 0.43% (accuracy) and 0.0071 (EDMS). Additionally, considering the relationship between model resources and performance, we achieved a 28.35% reduction in memory usage while realizing enhancements of 0.33% (accuracy) and 0.0045 (EDMS).
- 4 January 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (1) , 168
Open AccessShip Infrared Automatic Target Recognition Based on Bipartite Graph Recommendation: A Model-Matching Method
Deep learning technology has greatly propelled the development of intelligent and information-driven research on ship infrared automatic target recognition (SIATR). In future scenarios, there will be various recognition models with different mechanisms to choose from. However, in complex and dynamic environments, ship infrared (IR) data exhibit rich feature space distribution, resulting in performance variations among SIATR models, thus preventing the existence of a universally superior model for all recognition scenarios. In light of this, this study proposes a model-matching method for SIATR tasks based on bipartite graph theory. This method establishes evaluation criteria based on recognition accuracy and feature learning credibility, uncovering the underlying connections between IR attributes of ships and candidate models. The objective is to selectively recommend the optimal candidate model for a given sample, enhancing the overall recognition performance and applicability of the model. We separately conducted tests for the optimization of accuracy and credibility on high-fidelity simulation data, achieving Accuracy and EDMS (our credibility metric) of 95.86% and 0.7781. Our method improves by 1.06% and 0.0274 for each metric compared to the best candidate models (six in total). Subsequently, we created a recommendation system that balances two tasks, resulting in improvements of 0.43% (accuracy) and 0.0071 (EDMS). Additionally, considering the relationship between model resources and performance, we achieved a 28.35% reduction in memory usage while realizing enhancements of 0.33% (accuracy) and 0.0045 (EDMS).
- Open Access
- 28 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (23) , 12162
A Wideband Microstrip-to-Waveguide Transition Using E-Plane Probe with Parasitic Patch for W-Band Application
The hollow metal waveguides are attractive components for millimeter-wave circuits owing to low loss. To integrate with the front-end circuit, a transition from microstrip line to waveguide is required. In this article, a microstrip-to-waveguide transition is presented in the W-band by using an E-plane probe with a parasitic patch. The probe is embedded into the waveguide along the center of the broad wall to excite the TE10 mode. A backshort-circuited waveguide with a quarter wavelength is used to obtain sufficient energy coupling and achieve good impedance matching. The additional parasitic patch can introduce a new resonance at a low frequency to enhance the working bandwidth. Hence, the proposed transition achieves wide working bandwidth and low insertion loss. For verification, a back-to-back transition is constructed and measured. The measured results indicate that the proposed transition has a wide working bandwidth covering the entire W-band. The measured reflection coefficient is below −13 dB from 70 to 110 GHz and the average insert loss is 1.1 dB. Attributed to wide working bandwidth and simple structure, the proposed transition is attractive for W-band circuit systems.
- 28 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (23) , 12162
Open AccessA Wideband Microstrip-to-Waveguide Transition Using E-Plane Probe with Parasitic Patch for W-Band Application
The hollow metal waveguides are attractive components for millimeter-wave circuits owing to low loss. To integrate with the front-end circuit, a transition from microstrip line to waveguide is required. In this article, a microstrip-to-waveguide transition is presented in the W-band by using an E-plane probe with a parasitic patch. The probe is embedded into the waveguide along the center of the broad wall to excite the TE10 mode. A backshort-circuited waveguide with a quarter wavelength is used to obtain sufficient energy coupling and achieve good impedance matching. The additional parasitic patch can introduce a new resonance at a low frequency to enhance the working bandwidth. Hence, the proposed transition achieves wide working bandwidth and low insertion loss. For verification, a back-to-back transition is constructed and measured. The measured results indicate that the proposed transition has a wide working bandwidth covering the entire W-band. The measured reflection coefficient is below −13 dB from 70 to 110 GHz and the average insert loss is 1.1 dB. Attributed to wide working bandwidth and simple structure, the proposed transition is attractive for W-band circuit systems.