Yimin Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yimin Shen has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Bo Zhou
Department of Computer Science and Engineering, Chengdu Technological University, Chengdu 611730, China
2 shared publications - Xiang Chen
School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China
2 shared publications - Xianju Zheng
Department of Computer Science and Engineering, Chengdu Technological University, Chengdu 611730, China
2 shared publications Di Zhou
Sichuan University of Arts and Science
1 shared publicationFei Du
Chengdu Technological University
1 shared publicationFeilong Qin
School of Big Data and Artificial Intelligence, Chengdu Technological University
1 shared publication
Latest Publications
- Open Access
- 15 May 2026
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 20, 1774633
A context-aware transformer with weighted residual for efficient remote sensing target detection
Remote sensing image target detection has important applications in disaster prevention and mitigation. However, current detection models still have shortcomings in multi-scale feature fusion and in representing contextual information, and are prone to class imbalance during training. To address these issues, this paper proposes a target detection model that combines a context transformer and a weighted residual pyramid. Specifically, a weighted residual pyramid module is designed to fuse deep and shallow target-instance features effectively, and a learnable balancing factor is introduced to alleviate the imbalance in contributions across network layers. Simultaneously, a context transformer module is introduced into the feature extraction and fusion networks to enhance the model’s multi-scale feature representation capability. Furthermore, a rotated bounding box is introduced to locate target instances, reducing the influence of redundant background information, and a CIoU-based multi-task loss function is designed to reduce the contribution of different instance targets to the regression task. Experimental results show that, while ensuring real-time performance, the proposed model achieves mAP@0.5 scores of 0.754 and 0.714 on the DOTAv1.0 and DOTAv1.5 datasets, respectively, demonstrating consistent improvements across both datasets. Meanwhile, visualization of detection results across various disaster scenarios shows that the model proposed in this paper has strong practical value.
- 15 May 2026
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 20, 1774633
Open AccessA context-aware transformer with weighted residual for efficient remote sensing target detection
Remote sensing image target detection has important applications in disaster prevention and mitigation. However, current detection models still have shortcomings in multi-scale feature fusion and in representing contextual information, and are prone to class imbalance during training. To address these issues, this paper proposes a target detection model that combines a context transformer and a weighted residual pyramid. Specifically, a weighted residual pyramid module is designed to fuse deep and shallow target-instance features effectively, and a learnable balancing factor is introduced to alleviate the imbalance in contributions across network layers. Simultaneously, a context transformer module is introduced into the feature extraction and fusion networks to enhance the model’s multi-scale feature representation capability. Furthermore, a rotated bounding box is introduced to locate target instances, reducing the influence of redundant background information, and a CIoU-based multi-task loss function is designed to reduce the contribution of different instance targets to the regression task. Experimental results show that, while ensuring real-time performance, the proposed model achieves mAP@0.5 scores of 0.754 and 0.714 on the DOTAv1.0 and DOTAv1.5 datasets, respectively, demonstrating consistent improvements across both datasets. Meanwhile, visualization of detection results across various disaster scenarios shows that the model proposed in this paper has strong practical value.
- Open Access
- 10 May 2026
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Electronics Express
- Vol. 23 (9) , 20240565
Investigation of the partially recoverable gate leakage on normally-OFF Schottky-type p-GaN gate AlGaN/GaN HEMTs
In this work, gate leakage behavior on Schottky-type p-GaN gate AlGaN/GaN HEMT is investigated, especially when the Schottky junction is damaged. A controllable degradation of the Schottky junction is achieved, then the previous semi-floated p-GaN is electrically connected to the gate electrode. Therefore, the pre-stressed GaN device exhibits an improved gate stability, as well as a normal gate control and large gate swing. Furthermore, the associated trap level is extracted by Arrhenius plot based on the exponential relationship between the recovery speed versus temperature.
- 10 May 2026
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Electronics Express
- Vol. 23 (9) , 20240565
Open AccessInvestigation of the partially recoverable gate leakage on normally-OFF Schottky-type p-GaN gate AlGaN/GaN HEMTs
In this work, gate leakage behavior on Schottky-type p-GaN gate AlGaN/GaN HEMT is investigated, especially when the Schottky junction is damaged. A controllable degradation of the Schottky junction is achieved, then the previous semi-floated p-GaN is electrically connected to the gate electrode. Therefore, the pre-stressed GaN device exhibits an improved gate stability, as well as a normal gate control and large gate swing. Furthermore, the associated trap level is extracted by Arrhenius plot based on the exponential relationship between the recovery speed versus temperature.
- Open Access
- 16 February 2026
- Published by MDPI AG in Journal of Sensor and Actuator Networks
- Vol. 15 (1) , 23
Temporal Attentive Graph Networks for Financial Surveillance: An Incremental Multi-Scale Framework
Systemic risk propagation in modern financial markets is characterized by non-linear contagion and rapid topological evolution, rendering traditional static monitoring methods ineffective. Existing Graph Neural Networks (GNNs) often struggle to capture “structural breaks” during crises due to their reliance on static adjacency assumptions and isotropic aggregation. To address these challenges, this study proposes the Temporal Attentive Graph Networks (TAGN), a dynamic framework designed for extreme volatility prediction and financial surveillance. TAGN constructs an incremental multi-scale graph by fusing high-frequency trading data, supply chain linkages, and institutional co-holdings to model heterogeneous risk transmission channels. Technically, it employs a deeply coupled GAT-GRU architecture, where the Graph Attention Network (GAT) dynamically assigns weights to contagion sources, and the Gated Recurrent Unit (GRU) memorizes the trajectory of structural evolution. Extensive experiments on the S&P 500 dataset (2018–2024) demonstrate that TAGN significantly outperforms state-of-the-art baselines, including WinGNN and PatchTST, achieving an AUC of 0.890 and a Precision at 50 of 61.5%. Notably, a risk early-warning index derived from TAGN exhibits a 1–2 week lead time over the VIX index during major market stress events, such as the Silicon Valley Bank collapse. This research facilitates a paradigm shift from historical statistical estimation to dynamic network-aware sensing, offering interpretable tools for RegTech applications.
- 16 February 2026
- Published by MDPI AG in Journal of Sensor and Actuator Networks
- Vol. 15 (1) , 23
Open AccessTemporal Attentive Graph Networks for Financial Surveillance: An Incremental Multi-Scale Framework
Systemic risk propagation in modern financial markets is characterized by non-linear contagion and rapid topological evolution, rendering traditional static monitoring methods ineffective. Existing Graph Neural Networks (GNNs) often struggle to capture “structural breaks” during crises due to their reliance on static adjacency assumptions and isotropic aggregation. To address these challenges, this study proposes the Temporal Attentive Graph Networks (TAGN), a dynamic framework designed for extreme volatility prediction and financial surveillance. TAGN constructs an incremental multi-scale graph by fusing high-frequency trading data, supply chain linkages, and institutional co-holdings to model heterogeneous risk transmission channels. Technically, it employs a deeply coupled GAT-GRU architecture, where the Graph Attention Network (GAT) dynamically assigns weights to contagion sources, and the Gated Recurrent Unit (GRU) memorizes the trajectory of structural evolution. Extensive experiments on the S&P 500 dataset (2018–2024) demonstrate that TAGN significantly outperforms state-of-the-art baselines, including WinGNN and PatchTST, achieving an AUC of 0.890 and a Precision at 50 of 61.5%. Notably, a risk early-warning index derived from TAGN exhibits a 1–2 week lead time over the VIX index during major market stress events, such as the Silicon Valley Bank collapse. This research facilitates a paradigm shift from historical statistical estimation to dynamic network-aware sensing, offering interpretable tools for RegTech applications.
- Open Access
- 11 November 2025
- Published by MDPI AG in Preprints.org
Temporal Attentive Graph Networks for Financial Surveillance: An Incremental Multi-Scale Framework
Addressing the limitations of conventional financial time series models in capturing modern market dynamics, this study introduces a novel financial monitoring framework based on Temporal Attentive Graph Networks (TAGN). The TAGN model integrates Graph Attention Networks (GAT) and Gated Recurrent Units (GRU) to simultaneously capture spatial dependencies among financial entities and the dynamic evolution of network structure. The framework uses a multi-relational dynamic graph of 50 NASDAQ stocks. Node features fuse multi-scale information (micro, meso, macro), and the graph structure integrates price correlation, supply chain, and institutional co-holdings. Compared to benchmarks (Logistic Regression, GCN, GCN-LSTM), TAGN demonstrates superior performance (AUC: 0.89) in predicting stocks likely to experience extreme volatility (>±15%) within three months. Empirical analysis (2018–2023) effectively quantifies network imprints of major events (e.g., 45% average edge weight surge during COVID-19; community stability Jaccard similarity drop to 0.34 following the SVB incident). An ablation study confirms the critical contribution of the attention and temporal components. Finally, by generating a risk early-warning index integrating network topology and model output, this research offers a new tool for systemic risk quantification and proactive anticipation.
- 11 November 2025
- Published by MDPI AG in Preprints.org
Open AccessTemporal Attentive Graph Networks for Financial Surveillance: An Incremental Multi-Scale Framework
Addressing the limitations of conventional financial time series models in capturing modern market dynamics, this study introduces a novel financial monitoring framework based on Temporal Attentive Graph Networks (TAGN). The TAGN model integrates Graph Attention Networks (GAT) and Gated Recurrent Units (GRU) to simultaneously capture spatial dependencies among financial entities and the dynamic evolution of network structure. The framework uses a multi-relational dynamic graph of 50 NASDAQ stocks. Node features fuse multi-scale information (micro, meso, macro), and the graph structure integrates price correlation, supply chain, and institutional co-holdings. Compared to benchmarks (Logistic Regression, GCN, GCN-LSTM), TAGN demonstrates superior performance (AUC: 0.89) in predicting stocks likely to experience extreme volatility (>±15%) within three months. Empirical analysis (2018–2023) effectively quantifies network imprints of major events (e.g., 45% average edge weight surge during COVID-19; community stability Jaccard similarity drop to 0.34 following the SVB incident). An ablation study confirms the critical contribution of the attention and temporal components. Finally, by generating a risk early-warning index integrating network topology and model output, this research offers a new tool for systemic risk quantification and proactive anticipation.