Yi Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yi Xie has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Yadi Wang
Henan University
6 shared publications Baojun Qiao
4 shared publications- Xianyu Zuo
Henan University, Kaifeng, China
4 shared publications - Lanxue Dang
School of Computer and Information Engineering, Henan University, Kaifeng, Henan, China
3 shared publications - Hongyu Han
School of Computer and Information Engineering, Henan University, Kaifeng, China
2 shared publications - Huiyu Mu
Henan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng, China
2 shared publications
Latest Publications
- 24 October 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 204
A multi-path attention residual and perception progressive refinement network for infrared small target detection
- 24 October 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 204
A multi-path attention residual and perception progressive refinement network for infrared small target detection
- 28 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 4411216
Cross-Domain Remote Sensing Scene Classification for Balancing Transferability and Discriminability in Partial Domain Adaptation
Due to the high cost of annotating remote sensing images, unsupervised partial domain adaptation (PDA) that do not require manual annotation have been widely studied for application in remote sensing scene classification (RSSC) tasks. PDA is based on the assumption that the class space of target domain is a subset of the source domain. Therefore, the model trained on the large-scale and full-labeled source domain is transferred to small-scale and unlabeled target domain effectively. However, most existing PDA methods for RSSC focus only on improving the transferability of features in the domain alignment process, neglecting the discriminative information that is equally important for cross-domain classification tasks. In this article, we proposed a Synergistic Contrastive-Adversarial Learning Partial Domain Adaptation (SCAPDA) method for adaptive cross-domain RSSC. The SCAPDA is built upon domain adversarial network, incorporating a discrimination constraint module (DCM) tailored for the target domain and a supervised contrastive learning module (SCLM) operating on both the source and target domains. The DCM learns a target-specific classifier under the constraint of enhancing discriminability in the target domain, thereby providing high-confidence supervision signals for supervised contrastive learning. The SCLM leverages supervised contrastive learning to explore both domain-invariant and class-specific information across source and target samples, aiming to promote transferable representations while preserving discriminability. The effectiveness of the proposed method is validated through experiments on three publicly available remote sensing datasets.
- 28 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 4411216
Cross-Domain Remote Sensing Scene Classification for Balancing Transferability and Discriminability in Partial Domain Adaptation
Due to the high cost of annotating remote sensing images, unsupervised partial domain adaptation (PDA) that do not require manual annotation have been widely studied for application in remote sensing scene classification (RSSC) tasks. PDA is based on the assumption that the class space of target domain is a subset of the source domain. Therefore, the model trained on the large-scale and full-labeled source domain is transferred to small-scale and unlabeled target domain effectively. However, most existing PDA methods for RSSC focus only on improving the transferability of features in the domain alignment process, neglecting the discriminative information that is equally important for cross-domain classification tasks. In this article, we proposed a Synergistic Contrastive-Adversarial Learning Partial Domain Adaptation (SCAPDA) method for adaptive cross-domain RSSC. The SCAPDA is built upon domain adversarial network, incorporating a discrimination constraint module (DCM) tailored for the target domain and a supervised contrastive learning module (SCLM) operating on both the source and target domains. The DCM learns a target-specific classifier under the constraint of enhancing discriminability in the target domain, thereby providing high-confidence supervision signals for supervised contrastive learning. The SCLM leverages supervised contrastive learning to explore both domain-invariant and class-specific information across source and target samples, aiming to promote transferable representations while preserving discriminability. The effectiveness of the proposed method is validated through experiments on three publicly available remote sensing datasets.
- 22 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 324
DFDNet: Differential fusion detection network for RGB-IR objects
- 22 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 324
DFDNet: Differential fusion detection network for RGB-IR objects
- Open Access
- 18 April 2026
- Published by Elsevier in SSRN Electronic Journal
A Lightweight YOLOv8-Based Method for Infrared Target Recognition
Infrared target recognition remains challenging due to weak signal intensity, low contrast, and complex background interference. To improve detection efficiency without increasing computational burden, a compact detection framework is developed based on an optimized YOLOv8n architecture. A lightweight backbone is designed to reduce redundant feature generation while maintaining discriminative capability. In addition, a multi-branch attention mechanism is introduced to enhance target-related responses and suppress background noise. A shared detection head is further employed to improve feature interaction across scales and stabilize prediction results. Experimental results on the HIT-UAV dataset and a curated Russia–Ukraine dataset indicate that the proposed method achieves competitive detection accuracy with significantly reduced parameters (1.62 M) and computational cost (4.10 GFLOPs), demonstrating its effectiveness for efficient infrared target recognition.
- 18 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Lightweight YOLOv8-Based Method for Infrared Target Recognition
Infrared target recognition remains challenging due to weak signal intensity, low contrast, and complex background interference. To improve detection efficiency without increasing computational burden, a compact detection framework is developed based on an optimized YOLOv8n architecture. A lightweight backbone is designed to reduce redundant feature generation while maintaining discriminative capability. In addition, a multi-branch attention mechanism is introduced to enhance target-related responses and suppress background noise. A shared detection head is further employed to improve feature interaction across scales and stabilize prediction results. Experimental results on the HIT-UAV dataset and a curated Russia–Ukraine dataset indicate that the proposed method achieves competitive detection accuracy with significantly reduced parameters (1.62 M) and computational cost (4.10 GFLOPs), demonstrating its effectiveness for efficient infrared target recognition.
- Open Access
- 27 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 927-934
Optimization of Electric Vehicle Routing for Urban Logistics Using an Improved Discrete Grey Wolf Optimizer
- 27 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 927-934
Open AccessOptimization of Electric Vehicle Routing for Urban Logistics Using an Improved Discrete Grey Wolf Optimizer
- Open Access
- 23 March 2026
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 149
MAFNet: A multi-modal adaptive fusion network-based approach for individual building extraction from oblique photogrammetry
- 23 March 2026
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 149
Open AccessMAFNet: A multi-modal adaptive fusion network-based approach for individual building extraction from oblique photogrammetry
- 13 March 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 195
TRSADepth: Self-supervised monocular depth estimation with texture-robust sparse attention in natural environments
- 13 March 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 195
TRSADepth: Self-supervised monocular depth estimation with texture-robust sparse attention in natural environments
- 11 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 314
DAGG-Net: Dual adaptive graph and gating network for multimodal aspect-based sentiment analysis
- 11 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 314
DAGG-Net: Dual adaptive graph and gating network for multimodal aspect-based sentiment analysis
- 26 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 6319-6330
Myocardial Infarction Detection With Incomplete Multi-View Data via Dual-Branch Gating Completion and Dirichlet Weighting
Multi-view myocardial infarction (MI) detection often relies on electrocardiogram (ECG) data, which suffers from noise sensitivity and limited early diagnostic value. Echocardiography provides richer temporal-spatial information but frequently encounters missing views due to clinical acquisition constraints. Existing fusion methods typically adopt static or overly complex dynamic weighting, limiting their adaptability to varying view quality and hindering real-time applicability. To this end, this paper proposes a view completion method based on a dual-branch gating structure, combining Transformer and Graph Neural Network (GNN) to complete incomplete multi-view information. Specifically, the model uses the Transformer encoder to model global temporal dependencies, introduces GNN to strengthen the local structural relationship between views, and uses the gating mechanism to achieve collaborative completion of the aforementioned two core components. Furthermore, this paper designs an uncertainty-driven dynamic weighted fusion strategy based on Dirichlet distribution, which can adaptively adjust the fusion weights according to the prediction confidence of each view, overcoming the limitations of traditional static weighting. Experiments on the HMC-QU dataset show that the proposed method achieves 92.31% accuracy, 90.00% precision, and 100.00% specificity, outperforming state-of-the-art models and demonstrating strong potential for clinical deployment.
- 26 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 6319-6330
Myocardial Infarction Detection With Incomplete Multi-View Data via Dual-Branch Gating Completion and Dirichlet Weighting
Multi-view myocardial infarction (MI) detection often relies on electrocardiogram (ECG) data, which suffers from noise sensitivity and limited early diagnostic value. Echocardiography provides richer temporal-spatial information but frequently encounters missing views due to clinical acquisition constraints. Existing fusion methods typically adopt static or overly complex dynamic weighting, limiting their adaptability to varying view quality and hindering real-time applicability. To this end, this paper proposes a view completion method based on a dual-branch gating structure, combining Transformer and Graph Neural Network (GNN) to complete incomplete multi-view information. Specifically, the model uses the Transformer encoder to model global temporal dependencies, introduces GNN to strengthen the local structural relationship between views, and uses the gating mechanism to achieve collaborative completion of the aforementioned two core components. Furthermore, this paper designs an uncertainty-driven dynamic weighted fusion strategy based on Dirichlet distribution, which can adaptively adjust the fusion weights according to the prediction confidence of each view, overcoming the limitations of traditional static weighting. Experiments on the HMC-QU dataset show that the proposed method achieves 92.31% accuracy, 90.00% precision, and 100.00% specificity, outperforming state-of-the-art models and demonstrating strong potential for clinical deployment.