MMAE: A universal image fusion method via mask attention mechanism

Pattern Recognition, Journal Year: 2024, Volume and Issue: unknown, P. 111041 - 111041

Published: Sept. 1, 2024

Language: Английский

---

IF-USOD: Multimodal information fusion interactive feature enhancement architecture for underwater salient object detection

Information Fusion, Journal Year: 2024, Volume and Issue: unknown, P. 102806 - 102806

Published: Nov. 1, 2024

Language: Английский

---

Conti-Fuse: A novel continuous decomposition-based fusion framework for infrared and visible images

Information Fusion, Journal Year: 2024, Volume and Issue: unknown, P. 102839 - 102839

Published: Dec. 1, 2024

Language: Английский

---

A Mamba-aware Spatial Spectral Cross-modal Network for Remote Sensing Classification

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2025, Volume and Issue: 63, P. 1 - 15

Published: Jan. 1, 2025

This study introduces a novel cross-modal spatial-spectral interaction Mamba (CMS ² I-Mamba) for remote sensing image fusion classification. Unlike convolution-based models focusing on local details and Transformer-based with high computational complexity, CMS I-Mamba efficiently global long-range dependencies in linear complexity manner. First, multispectral (MS) panchromatic (PAN) images each have unique advantages the spectral spatial attributes. Given this, this paper innovatively designs multi-path selective-scan mechanism (MPS M), which applies different path scanning strategies to deeply capture features from both dimensions, aiming enhance robustness complementarity of features. Secondly, overcome characterization differences between acquired by sensors, further channel alignment module (CIAM). employs efficient former-last oddeven achieve precise semantic deep modalities. Finally, leverage shared guide singular features, proposes semantic-aware calibration (SACM), accurately constraints calibrates same information not only enhances model's ability understand scene semantics, but also promotes utilization Through experimental verification multiple datasets, proposed shows excellent recognition performance efficiency (parameter quantity running speed) classification tasks. The code is available at: https://github.com/ru-willow/CMSI-Mamba.

Language: Английский

---

FMamba: Multimodal Image Fusion Driven by State Space Models

Digital Signal Processing, Journal Year: 2025, Volume and Issue: unknown, P. 105033 - 105033

Published: Jan. 1, 2025

Language: Английский

---

Low-illumination color imaging: Progress and challenges

Optics & Laser Technology, Journal Year: 2025, Volume and Issue: 184, P. 112553 - 112553

Published: Feb. 3, 2025

Language: Английский

---

LEFuse: Joint low-light enhancement and image fusion for nighttime infrared and visible images

Neurocomputing, Journal Year: 2025, Volume and Issue: unknown, P. 129592 - 129592

Published: Feb. 1, 2025

Language: Английский

---

TCTFusion: A Triple-Branch Cross-Modal Transformer for Adaptive Infrared and Visible Image Fusion

Electronics, Journal Year: 2025, Volume and Issue: 14(4), P. 731 - 731

Published: Feb. 13, 2025

Infrared-visible image fusion (IVIF) is an important part of multimodal (MMF). Our goal to combine useful information from infrared and visible sources produce strong, detailed, fused images that help people understand scenes better. However, most existing methods based on convolutional neural networks extract cross-modal local features without fully utilizing long-range contextual information. This limitation reduces performance, especially in complex scenarios. To address this issue, we propose TCTFusion, a three-branch transformer for visible–infrared fusion. The model includes shallow feature module (SFM), frequency decomposition (FDM), aggregation (IAM). three branches specifically receive input infrared, visible, concatenated images. SFM extracts using residual connections with shared weights. FDM then captures low-frequency global across modalities high-frequency within each modality. IAM aggregates complementary features, enabling the full interaction between different modalities. Finally, decoder generates image. Additionally, introduce pixel loss structural significantly improve model’s overall performance. Extensive experiments mainstream datasets demonstrate TCTFusion outperforms other state-of-the-art both qualitative quantitative evaluations.

Language: Английский

---

High-Throughput Prediction of Metal-Embedded Complex Properties with a New GNN-Based Metal Attention Framework

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 14, 2025

Metal-embedded complexes (MECs), including transition metal (TMCs) and metal-organic frameworks (MOFs), are important in catalysis, materials science, molecular devices due to their unique atom centrality complex coordination environments. However, modeling predicting properties accurately is challenging. A new attention (MA) framework for graph neural networks (GNNs) was proposed address the limitations of traditional methods, which fail differentiate core structures from ordinary covalent bonds. This MA converts heterogeneous graphs into homogeneous ones with distinct features by highlighting key metal-feature through hierarchical pooling a cross-attention. To assess its performance, 11 widely used GNN algorithms, three heterogeneous, were compared. Experimental results indicate significant improvements accuracy: an average 32.07% TMC up 23.01% MOF CO2 absorption. Moreover, tests on framework's robustness regarding data set size variation comparison larger non-MA model show that enhanced performance stems architecture, not merely increasing capacity. The potential offers potent statistical tool optimizing designing like catalysts gas storage systems.

Language: Английский

---

Multi-modal image fusion of visible and infrared for precise positioning of UAVs in agricultural fields

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 232, P. 110024 - 110024

Published: Feb. 16, 2025

Language: Английский

---