Search Results (51)

Mangroves play a crucial role in ecosystems, and the accurate classification and real-time monitoring of mangrove species are essential for their protection and restoration. To improve the segmentation performance of mangrove UAV remote sensing images, this study performs species segmentation after the super-resolution (SR) reconstruction of images. Therefore, we propose SwinNET, an SR reconstruction network. We design a convolutional enhanced channel attention (CEA) module within a network to enhance feature reconstruction through channel attention. Additionally, the Neighborhood Attention Transformer (NAT) is introduced to help the model better focus on domain features, aiming to improve the reconstruction of leaf details. These two attention mechanisms are symmetrically integrated within the network to jointly capture complementary information from spatial and channel dimensions. The experimental results demonstrate that SwinNET not only achieves superior performance in SR tasks but also significantly enhances the segmentation accuracy of mangrove species. Full article

Heterogeneous information network (HIN) embedding transforms multi-type nodes into low-dimensional vectors to preserve structural and semantic information for downstream tasks. However, it struggles with multiplex networks where nodes connect via diverse semantic paths (metapaths). Information fusion mainly improves the quality of node embedding by fully exploiting the structure and hidden information within the network. Current metapath-based methods ignore information from intermediate nodes along paths, depend on manually defined metapaths, and overlook implicit relationships between nodes sharing similar attributes. Our objective is to develop an adaptive framework that overcomes limitations in existing metapath-based embedding (incomplete information aggregation, manual path dependency, and ignorance of latent semantics) to learn more discriminative embeddings. We propose an adaptive multi-hop neighbor information fusion model for heterogeneous network embedding (ANHNE), which: (1) autonomously extracts composite metapaths (weighted combinations of relations) via a multipath aggregation matrix to mine hierarchical semantics of varying lengths for task-specific scenarios; (2) projects heterogeneous nodes into a unified space and employs hierarchical attention to selectively fuse neighborhood features across metapath hierarchies; and (3) enhances semantics by identifying potential node correlations via cosine similarity to construct implicit connections, enriching network structure with latent information. Extensive experimental results on multiple datasets show that ANHNE achieves more precise embeddings than comparable baseline models. Full article

Hyperspectral sparse unmixing (SU) networks have recently received considerable attention due to their model hyperspectral images (HSIs) with a priori spectral libraries and to capture nonlinear features through deep networks. This method effectively avoids errors associated with endmember extraction, and enhances the unmixing performance via nonlinear modeling. However, two major challenges remain: the use of large spectral libraries with high coherence leads to computational redundancy and performance degradation; moreover, certain feature extraction models, such as Transformer, while exhibiting strong representational capabilities, suffer from high computational complexity. To address these limitations, this paper proposes a hyperspectral unmixing dual-branch network integrating an adaptive hop-aware GCN and neighborhood offset Mamba that is termed DGMNet. Specifically, DGMNet consists of two parallel branches. The first branch employs the adaptive hop-neighborhood-aware GCN (AHNAGC) module to model global spatial features. The second branch utilizes the neighborhood spatial offset Mamba (NSOM) module to capture fine-grained local spatial structures. Subsequently, the designed Mamba-enhanced dual-stream feature fusion (MEDFF) module fuses the global and local spatial features extracted from the two branches and performs spectral feature learning through a spectral attention mechanism. Moreover, DGMNet innovatively incorporates a spectral-library-pruning mechanism into the SU network and designs a new pruning strategy that accounts for the contribution of small-target endmembers, thereby enabling the dynamic selection of valid endmembers and reducing the computational redundancy. Finally, an improved ESS-Loss is proposed, which combines an enhanced total variation (ETV) with an $l_{1/2}$ sparsity constraint to effectively refine the model performance. The experimental results on two synthetic and five real datasets demonstrate the effectiveness and superiority of the proposed method compared with the state-of-the-art methods. Notably, experiments on the Shahu dataset from the Gaofen-5 satellite further demonstrated DGMNet’s robustness and generalization. Full article

Crack detection in complex pavement scenarios remains challenging due to the sparse small-target features and computational inefficiency of existing methods. To address these limitations, this study proposes an enhanced architecture based on Mask2Former. The framework integrates two key innovations. A Local Perception Module (LPM) reconstructs geometric topological relationships through a Sequence-Space Dynamic Transformation Mechanism (DS2M), enhancing neighborhood feature extraction via depthwise separable convolutions. Simultaneously, an Auxiliary Convolutional Layer (ACL) combines lightweight residual convolutions with shallow high-resolution features, preserving critical edge details through channel attention weighting. Experimental evaluations demonstrate the model’s superior performance, achieving improvements of 3.2% in mIoU and 2.7% in mAcc compared to baseline methods, while maintaining computational efficiency with only 12.8 GFLOPs. These results validate the effectiveness of geometric relationship modeling and hierarchical feature fusion for pavement crack detection, suggesting practical potential for infrastructure maintenance systems. The proposed approach balances precision and efficiency, offering a viable solution for real-world applications with complex crack patterns and hardware constraints. Full article

Rural public cultural spaces serve as vital venues for information exchange, interpersonal interaction, and cultural and leisure activities in rural communities. Since the Rural Revitalization Strategy was proposed in 2017, the planning and provision of rural public cultural spaces have attracted increasing attention in China. However, many such spaces remain underutilized, accompanied by low levels of user satisfaction among villagers. A key reason for this is the mismatch between standardized spatial configurations and villagers’ dynamic functional needs. Drawing on Hertzberger’s theory of spatial polyvalence, this study proposes a framework to evaluate spatial flexibility in rural public cultural spaces. The framework introduces quantitative indicators and computational methods across two dimensions: “competence”, referring to a space’s potential to accommodate multiple functions, and “performance”, reflecting the efficiency of functional transformation during actual use. Employing the proposed method, this study conducts a case analysis of the Xiangyang Village Neighborhood Center in Shanghai to evaluate its spatial characteristics and actual usage. The evaluation reveals two key issues at the overall level: (1) many residual spaces remain undesigned and lack strategies to support spontaneous use; (2) the spatial layout shows rigid public–private divisions, with little adaptability. At the room level, spaces such as the elevator, hairdressing room, party secretary’s office, and health center are functionally rigid and underutilized. Drawing on exemplary cases, this study proposes several key strategies such as (1) optimizing and innovatively activating residual spaces, (2) integrating multifunctional programs, and (3) improving spatial inclusiveness. Full article

Next point-of-interest (POI) recommendation aims to predict users’ future visitation intentions based on historical check-in trajectories. However, this task faces significant challenges, including coarse-grained user interest representation, insufficient social modeling, sparse check-in data, and the insufficient learning of contextual patterns. To address this, we propose a model that combines check-in trajectory information with user friendship relationships and uses a Transformer architecture for prediction (TraFriendFormer). Our approach begins with the construction of trajectory flow graphs using graph convolutional networks (GCNs) to globally capture POI correlations across both spatial and temporal dimensions. In parallel, we design an integrated social graph that combines explicit friendships with implicit interaction patterns, in which GraphSAGE aggregates neighborhood information to generate enriched user embeddings. Finally, we fuse the POI embeddings, user embeddings, timestamp embeddings, and category embeddings and input them into the Transformer architecture. Through the self-attention mechanism, the model captures the complex temporal relationships in the check-in sequence. We validate the effectiveness of TraFriendFormer on two real-world datasets (FourSquare and Gowalla). The experimental results show that TraFriendFormer achieves an average improvement of 10.3% to 37.2% in metrics such as Acc@k and MRR compared to the selected state-of-the-art baselines. Full article

Due to access to the source data during the transfer phase, conventional domain adaptation works have recently raised safety and privacy concerns. More research attention thus shifts to a more practical setting known as source-data-free domain adaptation (SFDA). The new challenge is how to obtain reliable semantic supervision in the absence of source domain training data and the labels on the target domain. To that end, in this work, we introduce a novel Gradual Geometry-Guided Knowledge Distillation (G2KD) approach for SFDA. Specifically, to address the lack of supervision, we used local geometry of data to construct a more credible probability distribution over the potential categories, termed geometry-guided knowledge. Then, knowledge distillation was adopted to integrate this extra information for boosting the adaptation. More specifically, first, we constructed a neighborhood geometry for any target data using a similarity comparison on the whole target dataset. Second, based on pre-obtained semantic estimation by clustering, we mined soft semantic representations expressing the geometry-guided knowledge by semantic fusion. Third, using the soften labels, we performed knowledge distillation regulated by the new objective. Considering the unsupervised setting of SFDA, in addition to the distillation loss and student loss, we introduced a mixed entropy regulator that minimized the entropy of individual data as well as maximized the mutual entropy with augmentation data to utilize neighbor relation. Our contribution is that, through local geometry discovery with semantic representation and self-knowledge distillation, the semantic information hidden in the local structures is transformed to effective semantic self-supervision. Also, our knowledge distillation works in a gradual way that is helpful to capture the dynamic variations in the local geometry, mitigating the previous guidance degradation and deviation at the same time. Extensive experiments on five challenging benchmarks confirmed the state-of-the-art performance of our method. Full article

Carbonate reservoirs are widely distributed and have great exploration potential. As a key indicator for reservoir characterization and evaluation, accurate and efficient porosity prediction is crucial for the exploration and development of oil and gas in carbonate reservoirs. To address the issues of low prediction accuracy and weak generalization ability in carbonate reservoir porosity prediction, a porosity prediction model (CNN-BiLSTM-Transformer) combining a convolutional neural network (CNN), bidirectional long short-term memory network (BiLSTM), and Transformer network is proposed. This model is applied to the Moxi gas field in the Sichuan Basin, using conventional logging curves as input feature variables for porosity prediction. Root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R²) are used as evaluation metrics for comprehensive analysis and comparison. The model extracts curve features through the CNN layer, captures both short- and long-term neighborhood information via the BiLSTM layer, and utilizes the Transformer layer with a self-attention mechanism to focus on temporal information and input features, effectively capturing global dependencies. The Adam optimization algorithm is employed to update the network’s weights, and hyperparameters are adjusted based on feedback from network accuracy to achieve precise porosity prediction in highly heterogeneous carbonate reservoirs. Compared with traditional machine learning and deep learning models, the improved model better captures domain-specific information, resulting in an R² increase of 0.23 and reductions in RMSE and MAE by 0.016 and 0.014, respectively. Experimental results show that the porosity prediction model based on the CNN-BiLSTM-Transformer algorithm achieves lower average relative error and better prediction performance. Therefore, the CNN-BiLSTM-Transformer model can effectively predict the porosity of carbonate reservoirs and offers valuable insights for carbonate reservoir parameter prediction. Full article

Point cloud completion reconstructs incomplete, sparse inputs into complete 3D shapes. However, in the current 3D completion task, it is difficult to effectively extract the local details of an incomplete one, resulting in poor restoration of local details and low accuracy of the completed point clouds. To address this problem, this paper proposes a multi-scale point cloud completion method based on local neighborhood dynamic fusion (LNDF: adaptive aggregation of multi-scale local features through dynamic range and weight adjustment). Firstly, the farthest point sampling (FPS) strategy is applied to the original incomplete and defective point clouds for down-sampling to obtain three types of point clouds at different scales. When extracting features from point clouds of different scales, the local neighborhood aggregation of key points is dynamically adjusted, and the Transformer architecture is integrated to further enhance the correlation of local feature extraction information. Secondly, by combining the method of generating point clouds layer by layer in a pyramid-like manner, the local details of the point clouds are gradually enriched from coarse to fine to achieve point cloud completion. Finally, when designing the decoder, inspired by the concept of generative adversarial networks (GANs), an attention discriminator designed in series with a feature extraction layer and an attention layer is added to further optimize the completion performance of the network. Experimental results show that LNDM-Net reduces the average Chamfer Distance (CD) by 5.78% on PCN and 4.54% on ShapeNet compared to SOTA. The visualization of completion results demonstrates the superior performance of our method in both point cloud completion accuracy and local detail preservation. When handling diverse samples and incomplete point clouds in real-world 3D scenarios from the KITTI dataset, the approach exhibits enhanced generalization capability and completion fidelity. Full article

Graphs are an effective data structure for characterizing ubiquitous connections as well as evolving behaviors that emerge in inter-wined systems. Limited by the stereotype of node-to-node connections, learning node representations is often confined in a graph diffusion process where local information has been excessively aggregated, as the random walk of graph neural networks (GNN) explores far-reaching neighborhoods layer-by-layer. In this regard, tremendous efforts have been made to alleviate feature over-smoothing issues such that current backbones can lend themselves to be used in a deep network architecture. However, compared to designing a new GNN, less attention has been paid to underlying topology by graph re-wiring, which mitigates not only flaws of the random walk but also the over-smoothing risk incurred by reducing unnecessary diffusion in deep layers. Inspired by the notion of non-local mean techniques in the area of image processing, we propose a non-local information exchange mechanism by establishing an express connection to the distant node, instead of propagating information along the (possibly very long) original pathway node-after-node. Since the process of seeking express connections throughout a graph can be computationally expensive in real-world applications, we propose a re-wiring framework (coined the express messenger wrapper) to progressively incorporate express links in a non-local manner, which allows us to capture multi-scale features without using a very deep model; our approach is thus free of the over-smoothing challenge. We integrate our express messenger wrapper with existing GNN backbones (either using graph convolution or tokenized transformer) and achieve a new record on the Roman-empire dataset as well as in terms of SOTA performance on both homophilous and heterophilous datasets. Full article

Aiming to address the fundamental limitation of fixed activation functions that constrain network expressiveness in existing deep deblurring models, in this pioneering study, we introduced Kolmogorov–Arnold Networks (KANs) into the field of full-color/RGB image deblurring, proposing the Kolmogorov–Arnold and Transformer Network (KT-Deblur) framework based on dynamically learnable activation functions. This framework overcomes the constraints of traditional networks’ fixed nonlinear transformations by employing adaptive activation regulation for different blur types through KANs’ differentiable basis functions. Integrated with a U-Net architecture within a generative adversarial network framework, it significantly enhances detail restoration capabilities in complex scenarios. The innovatively designed Unified Attention Feature Extraction (UAFE) module combines neighborhood self-attention with linear self-attention mechanisms, achieving synergistic optimization of noise suppression and detail enhancement through adaptive feature space weighting. Supported by the Fast Spatial Feature Module (FSFM), it effectively improves the model’s ability to handle complex blur patterns. Our experimental results demonstrate that the proposed method outperforms existing algorithms in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics across multiple standard datasets, achieving an average PSNR of 41.25 dB on the RealBlur-R dataset, surpassing the latest state-of-the-art (SOTA) algorithms. This model exhibits strong robustness, providing a new paradigm for image-deblurring network design. Full article

Entity Alignment (EA) in Knowledge Graphs (KGs) is a crucial task for the integration of multiple KGs, facilitating the amalgamation of multi-source knowledge and enhancing support for downstream applications. In recent years, unsupervised EA methods have demonstrated remarkable efficacy in leveraging graph structures or utilizing auxiliary information. However, the increasing complexity of many modeling methods limits their applicability to large KGs in real-world scenarios. Given that most EA encoders primarily focus on modeling one-hop neighborhoods within the KG’s graph structure while neglecting similarities among multi-hop neighborhoods, we propose an efficient and effective unsupervised EA method, MPGT-Align, based on a multi-hop pruning graph transformer. The core innovation of MPGT-Align lies in mining multi-hop neighborhood features of entities through two components: Pruning-hop2Token and Attention-based Transformer encoder. The former aggregates only those multi-hop neighborhoods that contribute to alignment targets, inspired by search pruning algorithms. The latter empowers MPGT-Align to adaptively extract more effective alignment information from both entity itself and its multi-hop neighbors. Furthermore, Pruning-hop2Token serves as a non-parametric method that not only reduces model parameters, but also allows MPGT-Align to be trained with small batch sizes, thereby enabling efficient handling of large KGs. Extensive experiments conducted across various benchmark datasets demonstrate that our method consistently outperforms most existing supervised and unsupervised EA techniques. Full article

Population aging and urbanization are two of the most significant social transformations of the 21st century. Against the backdrop of rapid aging in China, developing age-friendly community environments, particularly through the renovation of legacy residential communities, not only supports active and healthy aging but also promotes equity and sustainable development. This study focuses on residential communities built in the 1980s in Hangzhou, exploring strategies for the age-friendly renovation of outdoor public spaces. The residential communities that flourished during the construction boom of the 1980s are now confronting a dual challenge: aging populations and deteriorating facilities. However, existing renovation efforts often pay insufficient attention to the comprehensive age-friendly transformation of outdoor public spaces within these neighborhoods. Following a structured research framework encompassing investigation, evaluation, design, and discussion, this study first analyzes linear grid layouts and usage patterns of these communities. Then, the research team uses post-occupancy evaluation (POE) to assess the age-friendliness of outdoor public spaces. Semi-structured interviews with elderly residents identify key concerns and establish a preliminary evaluation framework, while a Likert-scale questionnaire quantifies the satisfaction with age-friendly features across four communities. The assessment reveals that key age-friendliness issues, including poor traffic safety, dispersed activity spaces, and insufficiently adapted facilities, are closely linked to the linear usage patterns within the spatial framework of the grid layouts. Based on the findings, the study develops tiered renovation goals, renovation principles and implemented an age-friendly design in the Hemu Community. The strengths, weaknesses, and feasibility of the renovation plan are discussed, while three recommendations are made to ensure successful implementation. The study is intended to provide a valuable reference for advancing age-friendly residential renewal efforts in Hangzhou and contributing to the broader objective of sustainable, inclusive city development. Full article

The fusion of infrared and visible light images is a crucial technology for enhancing visual perception in complex environments. It plays a pivotal role in improving visual perception and subsequent performance in advanced visual tasks. However, due to the significant degradation of visible light image quality in low-light or nighttime scenes, most existing fusion methods often struggle to obtain sufficient texture details and salient features when processing such scenes. This can lead to a decrease in fusion quality. To address this issue, this article proposes a new image fusion method called BMFusion. Its aim is to significantly improve the quality of fused images in low-light or nighttime scenes and generate high-quality fused images around the clock. This article first designs a brightness attention module composed of brightness attention units. It extracts multimodal features by combining the SimAm attention mechanism with a Transformer architecture. Effective enhancement of brightness and features has been achieved, with gradual brightness attention performed during feature extraction. Secondly, a complementary fusion module was designed. This module deeply fuses infrared and visible light features to ensure the complementarity and enhancement of each modal feature during the fusion process, minimizing information loss to the greatest extent possible. In addition, a feature reconstruction network combining CLIP-guided semantic vectors and neighborhood attention enhancement was proposed in the feature reconstruction stage. It uses the KAN module to perform channel adaptive optimization on the reconstruction process, ensuring semantic consistency and detail integrity of the fused image during the reconstruction phase. The experimental results on a large number of public datasets demonstrate that the BMFusion method can generate fusion images with higher visual quality and richer details in night and low-light environments compared with various existing state-of-the-art (SOTA) algorithms. At the same time, the fusion image can significantly improve the performance of advanced visual tasks. This shows the great potential and application prospect of this method in the field of multimodal image fusion. Full article

Vehicle-to-vehicle communication enables capturing sensor information from diverse perspectives, greatly aiding in semantic scene completion in autonomous driving. However, the misalignment of features between ego vehicle and cooperative vehicles leads to ambiguity problems, affecting accuracy and semantic information. In this paper, we propose a Two-Stream Multi-Vehicle collaboration approach (TSMV), which divides the features of collaborative vehicles into two streams and regresses interactively. To overcome the problems caused by feature misalignment, the Neighborhood Self-Cross Attention Transformer (NSCAT) module is designed to enable the ego vehicle to query the most similar local features from collaborative vehicles through cross-attention, rather than assuming spatial-temporal synchronization. A 3D occupancy map is finally generated from the features of collaborative vehicle aggregation. Experimental results on both V2VSSC and SemanticOPV2V datasets demonstrate TSMV outpace state-of-the-art collaborative semantic scene completion techniques. Full article