Minghong Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Minghong Xie has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Yafei Zhang
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
6 shared publications - Huafeng Li
Kunming University of Science and Technology
4 shared publications - Dapeng Tao
Yunnan University
2 shared publications - Mengzhao Wang
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
2 shared publications - Zhengtao Yu
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
2 shared publications Guangwen Peng
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
1 shared publication
Latest Publications
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 5879-5894
Dual-Task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding
Video Paragraph Grounding (VPG) aims to precisely locate the most appropriate moments within a video that are relevant to a given textual paragraph query. However, existing methods typically rely on large-scale annotated temporal labels and assume that the correspondence between videos and paragraphs is known. This is impractical in real-world applications, as constructing temporal labels requires significant labor costs, and the correspondence is often unknown. To address this issue, we propose a Dual-task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding method (DMR-JRG). In this method, retrieval and grounding tasks are mutually reinforced rather than being treated as separate issues. DMR-JRG mainly consists of two branches: a retrieval branch and a grounding branch. The retrieval branch uses inter-video contrastive learning to roughly align the global features of paragraphs and videos, reducing modality differences and constructing a coarse-grained feature space to break free from the need for correspondence between paragraphs and videos. Additionally, this coarse-grained feature space further facilitates the grounding branch in extracting fine-grained contextual representations. In the grounding branch, we achieve precise cross-modal matching and grounding by exploring the consistency between local, global, and temporal dimensions of video segments and textual paragraphs. By synergizing these dimensions, we construct a fine-grained feature space for video and textual features, greatly reducing the need for large-scale annotated temporal labels. Meanwhile, we design a grounding reinforcement retrieval module (GRRM) that brings the coarse-grained feature space of the retrieval branch closer to the fine-grained feature space of the grounding branch, thereby reinforcing retrieval branch through grounding branch, and finally achieving mutual reinforcement between tasks. Extensive experiments on three challenging datasets demonstrate the effectiveness of our proposed method. The code is available at https://github.com/X7J92/DMR-JRG.
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 5879-5894
Dual-Task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding
Video Paragraph Grounding (VPG) aims to precisely locate the most appropriate moments within a video that are relevant to a given textual paragraph query. However, existing methods typically rely on large-scale annotated temporal labels and assume that the correspondence between videos and paragraphs is known. This is impractical in real-world applications, as constructing temporal labels requires significant labor costs, and the correspondence is often unknown. To address this issue, we propose a Dual-task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding method (DMR-JRG). In this method, retrieval and grounding tasks are mutually reinforced rather than being treated as separate issues. DMR-JRG mainly consists of two branches: a retrieval branch and a grounding branch. The retrieval branch uses inter-video contrastive learning to roughly align the global features of paragraphs and videos, reducing modality differences and constructing a coarse-grained feature space to break free from the need for correspondence between paragraphs and videos. Additionally, this coarse-grained feature space further facilitates the grounding branch in extracting fine-grained contextual representations. In the grounding branch, we achieve precise cross-modal matching and grounding by exploring the consistency between local, global, and temporal dimensions of video segments and textual paragraphs. By synergizing these dimensions, we construct a fine-grained feature space for video and textual features, greatly reducing the need for large-scale annotated temporal labels. Meanwhile, we design a grounding reinforcement retrieval module (GRRM) that brings the coarse-grained feature space of the retrieval branch closer to the fine-grained feature space of the grounding branch, thereby reinforcing retrieval branch through grounding branch, and finally achieving mutual reinforcement between tasks. Extensive experiments on three challenging datasets demonstrate the effectiveness of our proposed method. The code is available at https://github.com/X7J92/DMR-JRG.
- 30 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 3979-3991
Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding
Visual grounding has attracted wide attention thanks to its broad application in various visual language tasks. Although visual grounding has made significant research progress, existing methods ignore the promotion effect of the association between text and image features at different hierarchies on cross-modal matching. This paper proposes a Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction Visual Grounding method. It first generates a mask through decoupled sentence phrases, and a text and image hierarchical matching mechanism is constructed, highlighting the role of association between different hierarchies in cross-modal matching. In addition, a corresponding target object position progressive correction strategy is defined based on the hierarchical matching mechanism to achieve accurate positioning for the target object described in the text. This method can continuously optimize and adjust the bounding box position of the target object as the certainty of the text description of the target object improves. This design explores the association between features at different hierarchies and highlights the role of features related to the target object and its position in target positioning. The proposed method is validated on different datasets through experiments, and its superiority is verified by the performance comparison with the state-of-the-art methods. The source code of the proposed method is available at .
- 30 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 3979-3991
Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding
Visual grounding has attracted wide attention thanks to its broad application in various visual language tasks. Although visual grounding has made significant research progress, existing methods ignore the promotion effect of the association between text and image features at different hierarchies on cross-modal matching. This paper proposes a Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction Visual Grounding method. It first generates a mask through decoupled sentence phrases, and a text and image hierarchical matching mechanism is constructed, highlighting the role of association between different hierarchies in cross-modal matching. In addition, a corresponding target object position progressive correction strategy is defined based on the hierarchical matching mechanism to achieve accurate positioning for the target object described in the text. This method can continuously optimize and adjust the bounding box position of the target object as the certainty of the text description of the target object improves. This design explores the association between features at different hierarchies and highlights the role of features related to the target object and its position in target positioning. The proposed method is validated on different datasets through experiments, and its superiority is verified by the performance comparison with the state-of-the-art methods. The source code of the proposed method is available at .
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
DCPNet: A Dual-Task Collaborative Promotion Network for Pansharpening
Pansharpening, a type of image fusion, combines a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral output. Recent advancements in deep learning have led to the development of data-driven pansharpening methods, which have shown superior performance over traditional non-data-driven approaches. Nevertheless, current data-driven methods primarily focus on the design of single-task-driven networks. They tend to ignore the positive impact that incorporating auxiliary tasks could have on pansharpening. This oversight restricts further improvements in their performance. To break the constraints of single-task methods, we propose a dual-task collaborative promotion network (DCPNet) for pansharpening. DCPNet incorporates an LRMS image super-resolution (SR) reconstruction network into the pansharpening network, establishing a dual-task parallel collaborative framework that achieves joint collaborative optimization for both pansharpening and SR reconstruction. Additionally, we devise a feature fusion scheme that jointly reinforces spectral and spatial details, establishing a bridge for information interaction between the two task branches. This enables the two branches to extract higher quality features in a collaborative way, thus facilitating the realization of the interaction and fusion of dual-task features, as well as the exploration of potential information within the fused features. Experimental results demonstrate that our approach not only effectively transfers spectral information from the LRMS images to the fusion result but also preserves spatial details from the PAN images. The code is available at https://github.com/lhf12278/DCPNet.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
DCPNet: A Dual-Task Collaborative Promotion Network for Pansharpening
Pansharpening, a type of image fusion, combines a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral output. Recent advancements in deep learning have led to the development of data-driven pansharpening methods, which have shown superior performance over traditional non-data-driven approaches. Nevertheless, current data-driven methods primarily focus on the design of single-task-driven networks. They tend to ignore the positive impact that incorporating auxiliary tasks could have on pansharpening. This oversight restricts further improvements in their performance. To break the constraints of single-task methods, we propose a dual-task collaborative promotion network (DCPNet) for pansharpening. DCPNet incorporates an LRMS image super-resolution (SR) reconstruction network into the pansharpening network, establishing a dual-task parallel collaborative framework that achieves joint collaborative optimization for both pansharpening and SR reconstruction. Additionally, we devise a feature fusion scheme that jointly reinforces spectral and spatial details, establishing a bridge for information interaction between the two task branches. This enables the two branches to extract higher quality features in a collaborative way, thus facilitating the realization of the interaction and fusion of dual-task features, as well as the exploration of potential information within the fused features. Experimental results demonstrate that our approach not only effectively transfers spectral information from the LRMS images to the fusion result but also preserves spatial details from the PAN images. The code is available at https://github.com/lhf12278/DCPNet.
- 1 October 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 98
A unified framework for damaged image fusion and completion based on low-rank and sparse decomposition
- 1 October 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 98
A unified framework for damaged image fusion and completion based on low-rank and sparse decomposition
- Open Access
- 2 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 174092-174107
Joint Framework for Image Fusion and Super-Resolution via Multicomponent Analysis and Residual Compensation
To solve the problems in two-step processing of image fusion and Super-Resolution Reconstruction (SRR), we propose a joint framework of image Fusion and Super-Resolution (FSR) based on multicomponent analysis and residual compensation. Inspired by the idea of multicomponent analysis, we design a new structure-texture decomposition model to realize multicomponent dictionary learning for the above task. To depict the relationship between low-resolution image and its corresponding high-resolution image, the correlation of their sparse coding coefficients is introduced in the model. To compensate the information loss during the SRR, we propose a reconstruction residue compensation mechanism, in which the reconstruction residual error is compensated into the initial result of FSR to improve the quality of the final processing result. In addition, we propose different fusion algorithms for structure and texture components. For structure components, the fusion rule with the maximum absolute value is adopted, and for texture components, we design a new saliency measure to construct fusion results. Experiment results show that the proposed method can well retain the brightness and detail information in the original image, and is superior to other methods in subjective and objective evaluation.
- 2 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 174092-174107
Open AccessJoint Framework for Image Fusion and Super-Resolution via Multicomponent Analysis and Residual Compensation
To solve the problems in two-step processing of image fusion and Super-Resolution Reconstruction (SRR), we propose a joint framework of image Fusion and Super-Resolution (FSR) based on multicomponent analysis and residual compensation. Inspired by the idea of multicomponent analysis, we design a new structure-texture decomposition model to realize multicomponent dictionary learning for the above task. To depict the relationship between low-resolution image and its corresponding high-resolution image, the correlation of their sparse coding coefficients is introduced in the model. To compensate the information loss during the SRR, we propose a reconstruction residue compensation mechanism, in which the reconstruction residual error is compensated into the initial result of FSR to improve the quality of the final processing result. In addition, we propose different fusion algorithms for structure and texture components. For structure components, the fusion rule with the maximum absolute value is adopted, and for texture components, we design a new saliency measure to construct fusion results. Experiment results show that the proposed method can well retain the brightness and detail information in the original image, and is superior to other methods in subjective and objective evaluation.