Query：
学者姓名：魏丽芳
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
Correspondence pruning aims to identify inliers from an initial set of correspondences with a low inlier ratio. Current Graph Neural Networks (GNNs) based correspondence pruning approaches suffer from feature over-smoothing during information propagation, making it difficult to distinguish inliers from outliers. In addition, Transformer-based methods can model long-range dependencies, but their quadratic complexity limits computational efficiency. To address these issues, we propose MatchMamba, a dual-view correspondence pruning network based on a selective state space model, Mamba. MatchMamba combines the strengths of GNNs and Mamba, enhancing local feature extraction while modeling global context with appropriate complexity. Specifically, to overcome Mamba's limitations in correspondence pruning, such as the lack of local context and unidirectional modeling, we introduce the Cluster Sampling Spatial Mamba (CSSM) block and Correspondence Flip Bidirectional Mamba (CFBM) block. CSSM captures fine-grained local context through the implicit soft assignment and mitigates GNN's over-smoothing using Mamba's selective mechanism. CFBM block leverages Mamba's efficient long-sequence modeling by constructing a pseudo-sequential structure through clustering. It applies forward and backward scanning to enable each correspondence to fully capture contextual information from others, achieving global context modeling with appropriate computational cost. Extensive experiments demonstrate that MatchMamba outperforms current state-of-the-art methods on several challenging tasks. The code is available at https://github.com/Mrwyb/MatchMamba
Keyword ：
Complexity theory Complexity theory Computational efficiency Computational efficiency Computational modeling Computational modeling Context modeling Context modeling Correspondence pruning Correspondence pruning Data models Data models Deep learning Deep learning Feature extraction Feature extraction Forestry Forestry graph neural networks (GNNs) graph neural networks (GNNs) image matching image matching Mathematical models Mathematical models selective state space model selective state space model Transformer Transformer Transformers Transformers
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Yubin , Li, Xiaojie , Chen, Hao et al. MatchMamba: Correspondence Pruning via Selective State Space Model [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2026 , 36 (1) : 161-174 . |
| MLA | Wu, Yubin et al. "MatchMamba: Correspondence Pruning via Selective State Space Model" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 36 . 1 (2026) : 161-174 . |
| APA | Wu, Yubin , Li, Xiaojie , Chen, Hao , Yang, Changcai , Wei, Lifang , Chen, Riqing . MatchMamba: Correspondence Pruning via Selective State Space Model . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2026 , 36 (1) , 161-174 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Two-view correspondence learning is a fundamental task in computer vision for locating the same object across two different images, and its essence lies in capturing the context from the images. Recent studies employ the standard Convolutional Neural Network (CNN) as the core architecture to capture the context. However, the inherent nature of the CNN's local receptive field and pooling operations can result in the loss of certain semantic context. This can result in the CNN-based correspondence learning methods having an insufficient understanding of the global context, especially on image pairs including challenges like significant viewpoint changes, repetitive structures and weak textures. To address this issue and these challenges, we propose a novel correspondence learning method called Parallel Reinforcement Network (PRNet). Firstly, we design a reinforcement injection block, not only to dynamically refine feature weights by using channel attention mechanism, but also to preserve important details for alleviating over-smoothing issue by strengthening the network's capacity. Secondly, to alleviate the potential issue of overlooking the weak local context by CNN, we propose a parallel fusion block to integrate both shallow and deep features, preserving local details and enhancing global context. We evaluate the performance of the proposed PRNet on an outlier rejection task and a relative pose estimation task. The experimental results demonstrate the proposed PRNet exceeds several existing state-of-the-art methods in various challenging scenarios.
Keyword ：
Channel attention mechanism Channel attention mechanism Outlier rejection Outlier rejection Parallel fusion Parallel fusion Pose estimation Pose estimation Two-view correspondence Two-view correspondence
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Kang, Zheng , Lai, Taotao , Li, Zuoyong et al. PRNet: Parallel Reinforcement Network for two-view correspondence learning [J]. | KNOWLEDGE-BASED SYSTEMS , 2025 , 310 . |
| MLA | Kang, Zheng et al. "PRNet: Parallel Reinforcement Network for two-view correspondence learning" . | KNOWLEDGE-BASED SYSTEMS 310 (2025) . |
| APA | Kang, Zheng , Lai, Taotao , Li, Zuoyong , Wei, Lifang , Chen, Riqing . PRNet: Parallel Reinforcement Network for two-view correspondence learning . | KNOWLEDGE-BASED SYSTEMS , 2025 , 310 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In digital pathology, nuclei segmentation is a critical task for pathological image analysis, holding significant importance for diagnosis and research. However, challenges such as blurred boundaries between nuclei and background regions, domain shifts between pathological images, and uneven distribution of nuclei pose significant obstacles to segmentation tasks. To address these issues, we propose an innovative Causal inference inspired Diversified aggregation convolution Network named CDNet, which integrates a Diversified Aggregation Convolution (DAC), a Causal Inference Module (CIM) based on causal discovery principles, and a comprehensive loss function. DAC improves the issue of unclear boundaries between nuclei and background regions, and CIM enhances the model's cross-domain generalization ability. A novel Stable-Weighted Combined loss function was designed that combined the chunk-computed Dice Loss with the Focal Loss and the Causal Inference Loss to address the issue of uneven nuclei distribution. Experimental evaluations on the MoNuSeg, GLySAC, and MoNuSAC datasets demonstrate that CDNet significantly outperforms other models and exhibits strong generalization capabilities. Specifically, CDNet outperforms the second-best model by 0.79% (mIoU) and 1.32% (DSC) on the MoNuSeg dataset, by 2.65% (mIoU) and 2.13% (DSC) on the GLySAC dataset, and by 1.54% (mIoU) and 1.10% (DSC) on the MoNuSAC dataset. Code is publicly available at https://github.com/7FFDW/CDNet.
Keyword ：
Causal inference Causal inference Digital pathology Digital pathology Feature fusion Feature fusion Nuclei segmentation Nuclei segmentation Spurious correlation Spurious correlation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fan, Dawei , Chen, Zhuo , Gao, Yifan et al. Multiplex aggregation combining sample reweight composite network for pathology image segmentation [J]. | ARTIFICIAL INTELLIGENCE IN MEDICINE , 2025 , 169 . |
| MLA | Fan, Dawei et al. "Multiplex aggregation combining sample reweight composite network for pathology image segmentation" . | ARTIFICIAL INTELLIGENCE IN MEDICINE 169 (2025) . |
| APA | Fan, Dawei , Chen, Zhuo , Gao, Yifan , Yu, Jiaming , Li, Kaibin , Wei, Yi et al. Multiplex aggregation combining sample reweight composite network for pathology image segmentation . | ARTIFICIAL INTELLIGENCE IN MEDICINE , 2025 , 169 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Removing outliers is of paramount importance in the process of feature-based point cloud registration. However, it is still extremely challenging due to the high proportion of outliers, and the estimation of the accurate transmission matrix depends on the distribution of the inliers. The effective extraction of contextual information (local view) and the acquisition of full structural information (global view) influence the identification of inliers. Inspired by Gestalt principles in handling local and global relationships, we propose a Gestalt-inspired Graph Transformer Network (G-GTNet) for robust point cloud registration. G-GTNet extracts broader and more reliable contextual information while effectively aggregating both local and global features. Specifically, adhering to Gestalt principles, we design a multi-granularity aggregation (MGA) block that refines feature maps through a cascaded expanding path to acquire contextual details and promote information exchange among correspondences. In addition, to establish a consensus mechanism between local and global information, we introduce a global consensus attention (GCA) block. Similarly, the GCA follows Gestalt principles to optimally integrate local details and information about global structure, which allows it to gather information on a larger scale. Furthermore, a dependable seed selection (DSS) block is designed to filter out reliable and evenly distributed correspondences by distinguishing outliers and inliers more efficiently. Extensive experiments demonstrate that G-GTNet achieves better performance than state-of-the-art methods. It exhibits competitive performance and robustness in both outlier removal and pose estimation tasks across various public datasets with diverse feature descriptors. Notably, our proposed G-GTNet achieves an RR of 84.36% on the 3DMatch using FPFH descriptor, surpassing SC2-PCR by 1.33%. Our code will be released at https://github.com/gwk429/G-GTNet.
Keyword ：
Gestalt principles Gestalt principles Global consensus attention Global consensus attention Graph transformer Graph transformer Multi-granularity aggregation Multi-granularity aggregation Outlier removal Outlier removal Point cloud registration Point cloud registration
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gu, Weikang , Han, Mingyue , Xue, Li et al. G-GTNet: Gestalt-inspired graph transformer network for robust point cloud registration [J]. | KNOWLEDGE-BASED SYSTEMS , 2025 , 329 . |
| MLA | Gu, Weikang et al. "G-GTNet: Gestalt-inspired graph transformer network for robust point cloud registration" . | KNOWLEDGE-BASED SYSTEMS 329 (2025) . |
| APA | Gu, Weikang , Han, Mingyue , Xue, Li , Yu, Jiaming , Dong, Heng , Yang, Changcai et al. G-GTNet: Gestalt-inspired graph transformer network for robust point cloud registration . | KNOWLEDGE-BASED SYSTEMS , 2025 , 329 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Nuclear segmentation and classification play a crucial role in pathological image analysis. However, it is frequently challenged by blurred nuclear boundaries and complex structures in digital pathology slides, due to factors such as staining techniques and imaging methods, posing a significant challenge for accurate segmentation and classification. To this end, we propose a novel and efficient approach for nuclear identification, termed Information Propagation with Multi-Granularity Morphology-Guided Network (IPMMG). Specifically, IPMMG progressively captures edge morphology information from different network layers while simultaneously incorporating structural morphology features at multiple granularities. By explicitly propagating features related to both the edge and the structure, our approach constrains semantic features to focus on contours of the region of interest in the nuclear segmentation task, thus mitigating the challenge of blurred morphology. Experiments on public datasets demonstrate that IPMMG achieves state-of-the-art (SOTA) performance in segmentation, as measured by Dice and IoU scores, while also attaining competitive results in classification with DQ, SQ, and PQ metrics. In particular, our proposal IPMMG excels in handling nuclei with blurred edges and complex structures.
Keyword ：
Information propagation Information propagation Morphology-guided Morphology-guided Multi-granularity Multi-granularity Nuclear classification Nuclear classification Nuclear segmentation Nuclear segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fan, Dawei , Li, Jun , Cai, Chengfei et al. IPMMG: Information propagation with multi-granularity morphology-guided for nuclear segmentation and classification [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 298 . |
| MLA | Fan, Dawei et al. "IPMMG: Information propagation with multi-granularity morphology-guided for nuclear segmentation and classification" . | EXPERT SYSTEMS WITH APPLICATIONS 298 (2025) . |
| APA | Fan, Dawei , Li, Jun , Cai, Chengfei , Lin, Lihui , Chen, Riqing , Chen, Yanping et al. IPMMG: Information propagation with multi-granularity morphology-guided for nuclear segmentation and classification . | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 298 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The accurate identification of high-quality correspondences is a prerequisite task in feature-based point cloud registration. However, it is extremely challenging to handle the fusion of local and global features due to feature redundancy and complex spatial relationships. Given that Gestalt principles provide key advantages in analyzing local and global relationships, we propose a novel Gestalt-guided Parallel Interaction Network via orthogonal geometric consistency (GPI-Net) in this paper. It utilizes Gestalt principles to facilitate complementary communication between local and global information. Specifically, we introduce an orthogonal integration strategy to optimally reduce redundant information and generate a more compact global structure for high-quality correspondences. To capture geometric features in correspondences, we leverage a Gestalt Feature Attention (GFA) block through a hybrid utilization of self-attention and cross-attention mechanisms. Furthermore, to facilitate the integration of local detail information into the global structure, we design an innovative Dual-path Multi-Granularity parallel interaction aggregation (DMG) block to promote information exchange across different granularities. Extensive experiments on various challenging tasks demonstrate the superior performance of our proposed GPI-Net in comparison to existing methods. The code will be released at https://github.com/gwk/GPI-Net. Copyright © 2025, The Authors. All rights reserved.
Keyword ：
Geometry Geometry
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gu, Weikang , Han, Mingyue , Xue, Li et al. GPI-Net: Gestalt-Guided Parallel Interaction Network via Orthogonal Geometric Consistency for Robust Point Cloud Registration [J]. | arXiv , 2025 . |
| MLA | Gu, Weikang et al. "GPI-Net: Gestalt-Guided Parallel Interaction Network via Orthogonal Geometric Consistency for Robust Point Cloud Registration" . | arXiv (2025) . |
| APA | Gu, Weikang , Han, Mingyue , Xue, Li , Dong, Heng , Yang, Changcai , Chen, Riqing et al. GPI-Net: Gestalt-Guided Parallel Interaction Network via Orthogonal Geometric Consistency for Robust Point Cloud Registration . | arXiv , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Correspondence pruning aims to remove false correspondences (outliers) from an initial putative correspondence set. This process holds significant importance and serves as a fundamental step in various applications within the fields of remote sensing and photogrammetry. The presence of noise, illumination changes, and small overlaps in remote sensing images frequently result in a substantial number of outliers within the initial set, thereby rendering the correspondence pruning notably challenging. Although the spatial consensus of correspondences has been widely used to determine the correctness of each correspondence, achieving uniform consensus can be challenging due to the uneven distribution of correspondences. Existing works have mainly focused on either local or global consensus, with a very small perspective or large perspective, respectively. They often ignore the moderate perspective between local and global consensus, called group consensus, which serves as a buffering organization from local to global consensus, hence leading to insufficient correspondence consensus aggregation. To address this issue, we propose a multi-granularity consensus network (MGCNet) to achieve consensus across regions of different scales, which leverages local, group, and global consensus to accomplish robust and accurate correspondence pruning. Specifically, we introduce a GroupGCN module that randomly divides the initial correspondences into several groups and then focuses on group consensus and acts as a buffer organization from local to global consensus. Additionally, we propose a Multi-level Local Feature Aggregation Module that adapts to the size of the local neighborhood to capture local consensus and a Multi-order Global Feature Module to enhance the richness of the global consensus. Experimental results demonstrate that MGCNet outperforms state-of-the-art methods on various tasks, highlighting the superiority and great generalization of our method. In particular, we achieve 3.95% and 8.5% mAP5 degrees improvement without RANSAC on the YFCC100M dataset in known and unknown scenes for pose estimation, compared to the second-best models (MSA-LFC and CLNet). Source code: https://github.com/1211193023/MGCNet.
Keyword ：
Correspondence pruning Correspondence pruning Group consensus Group consensus Image matching Image matching Image registration Image registration Multi-granularity consensus Multi-granularity consensus Remote sensing image Remote sensing image
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhuang, Fengyuan , Liu, Yizhang , Li, Xiaojie et al. MGCNet: Multi-granularity consensus network for remote sensing image correspondence pruning [J]. | ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING , 2025 , 219 : 38-51 . |
| MLA | Zhuang, Fengyuan et al. "MGCNet: Multi-granularity consensus network for remote sensing image correspondence pruning" . | ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 219 (2025) : 38-51 . |
| APA | Zhuang, Fengyuan , Liu, Yizhang , Li, Xiaojie , Zhou, Ji , Chen, Riqing , Wei, Lifang et al. MGCNet: Multi-granularity consensus network for remote sensing image correspondence pruning . | ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING , 2025 , 219 , 38-51 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Purpose: Deep learning-based classroom behavior analysis provides new avenues for monitoring teaching quality in higher education. However, it faces challenges such as low detection accuracy, difficulty in recognizing small objects and handling occlusions as well as the difficulty in balancing real-time performance with accuracy. Design/methodology/approach: This paper proposes an improved YOLOv11 method for classroom state recognition, achieving precise classification and behavior detection through the integration of AFGCAttention, SPDConv and RCSOSA modules. AFGCAttention optimizes feature weight allocation through an adaptive fine-grained channel attention mechanism, SPDConv enhances the processing capabilities for small objects and low-resolution images by converting spatial information into depth information and RCSOSA reduces channel redundancy while improving spatial object attention. Findings: Experiments demonstrate that the YOLO-ASR model excels in precision, recall and mAP50. Compared to other You Only Look Once versions, it shows significantly improved detection accuracy and robustness in complex classroom environments, achieving an mAP50 of 93.8% and an mAP50-95 of 73.1%. Time-series analysis reveals dynamic changes in student behavior across teaching phases, including attention fluctuations, mobile phone use and signs of fatigue. Research limitations/implications: By analyzing student behavior across different classroom phases, patterns in mobile phone use and signs of fatigue were identified. These insights help teachers adjust their strategies, highlighting the method’s significance in monitoring teaching quality. Originality/value: This study optimizes the YOLOv11 model for classroom behavior detection by integrating effective modules to enhance performance. It offers a novel approach for quantitatively assessing teaching effectiveness, providing data support for educational reform and advancing intelligent classroom management and innovative teaching models. © 2025, Emerald Publishing Limited.
Keyword ：
Cellular telephones Cellular telephones Deep learning Deep learning Information management Information management Redundancy Redundancy Students Students Teaching Teaching
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Huang, Yikun , Xue, Xingsi , Chen, Hao et al. A method for classroom behavior state recognition and teaching quality monitoring [J]. | International Journal of Intelligent Computing and Cybernetics , 2025 , 18 (2) : 382-396 . |
| MLA | Huang, Yikun et al. "A method for classroom behavior state recognition and teaching quality monitoring" . | International Journal of Intelligent Computing and Cybernetics 18 . 2 (2025) : 382-396 . |
| APA | Huang, Yikun , Xue, Xingsi , Chen, Hao , Wei, Lifang , Zhang, Fuquan , Wang, Zhenyu et al. A method for classroom behavior state recognition and teaching quality monitoring . | International Journal of Intelligent Computing and Cybernetics , 2025 , 18 (2) , 382-396 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Nuclear segmentation and classification play a pivotal role in pathological image analysis. However, it is often hindered by blurred nuclear boundaries and complex structures in digital pathology slides, caused by factors such as staining techniques and imaging methods, presenting a significant challenge for accurate segmentation and classification. To address this issue, we propose a novel and efficient approach for nuclear identification, termed Information Propagation with Multi-Granularity Morphology-Guided Network (IPMMG). IPMMG progressively captures edge morphology information from different network layers while simultaneously incorporating structural morphology features at multiple granularities. By explicitly propagating features related to both the edge and structure, our approach constrains semantic features to focus on the region of interest's contour, thereby alleviating the challenge of blurred morphology. Experiments on public datasets demonstrate that IPMMG achieves state-of-the-art performance in segmentation, as measured by Dice and IoU scores, while also attaining competitive results in classification with DQ, SQ, and PQ metrics. In particular, it excels in handling nuclei with blurred edges and complex structures. © 2025, The Authors. All rights reserved.
Keyword ：
Semantic Segmentation Semantic Segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fan, Dawei , Li, Jun , Cai, Chengfei et al. Ipmmg: Information Propagation with Multi-Granularity Morphology-Guided for Nuclear Segmentation and Classification [J]. | SSRN , 2025 . |
| MLA | Fan, Dawei et al. "Ipmmg: Information Propagation with Multi-Granularity Morphology-Guided for Nuclear Segmentation and Classification" . | SSRN (2025) . |
| APA | Fan, Dawei , Li, Jun , Cai, Chengfei , Lin, Lihui , Chen, Riqing , Chen, Yanping et al. Ipmmg: Information Propagation with Multi-Granularity Morphology-Guided for Nuclear Segmentation and Classification . | SSRN , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Frame deletion detection is a challenging task in the field of digital video forensics. This paper proposes a deep-learning-based frame deletion detection method for single-shot videos. We capture traces of frame deletion forgery from both adjacent and long-range continuous frames. Specifically, we propose a novel multi-scale difference convolutional neural network (MSDCNN) structure, which models different levels of inter-frame variations. Then, we use the long-short-term memory network (LSTM) to capture the long-term variation pattern of multi-scale differential features. The proposed method is a simple and principled frame deletion detection framework with a small computational cost. According to the experiments, the proposed framework can achieve a more advanced performance of frame deletion detection than traditional methods and methods based on 3D convolutions.
Keyword ：
CNN CNN Frame deletion Frame deletion LSTM LSTM Multi-scale difference feature Multi-scale difference feature Video forensics Video forensics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Feng, Chunhui , Wu, Dawei , Wu, Tianle et al. An MSDCNN-LSTM framework for video frame deletion forensics [J]. | MULTIMEDIA TOOLS AND APPLICATIONS , 2024 . |
| MLA | Feng, Chunhui et al. "An MSDCNN-LSTM framework for video frame deletion forensics" . | MULTIMEDIA TOOLS AND APPLICATIONS (2024) . |
| APA | Feng, Chunhui , Wu, Dawei , Wu, Tianle , Wei, Lifang . An MSDCNN-LSTM framework for video frame deletion forensics . | MULTIMEDIA TOOLS AND APPLICATIONS , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
