Shubao Pan

Infrared–visible image fusion must reconcile different sensor roles: infrared imagery provides illumination-robust thermal evidence, whereas visible imagery supplies richer but illumination-sensitive structures and textures. Existing vision–language fusion methods show that textual context can guide reconstruction, but they rarely examine where language should enter a modality-specific network. We propose VBT-Fusion, a branch-selective language-conditioning framework for infrared–visible fusion. A precomputed language sequence interacts only with the visible branch, while the infrared representation follows an independent text-free path. In three Restormer-CA stages, text tokens query projected visible tokens, and the attended response is pooled and normalized to generate a global language-conditioned weighting vector for visible-feature calibration. Stage-1 modality features form an early fusion representation that preserves local structure and fine detail, whereas Stage-3 features form a deep representation with stronger contextual and thermal responses. A fusion convolution combines the two representations before a four-level U-Net reconstructs the fused image. Experiments on MSRS, M3FD, and RoadScene demonstrate strong in-domain performance and competitive cross-dataset generalization. VBT-Fusion ranks first on all seven reported MSRS metrics and preserves information richness and high-frequency detail on RoadScene, although several source-fidelity measures reveal a complementary trade-off. Ablation results support visible-branch language conditioning, cross-depth aggregation, and hierarchical reconstruction.

Traditional methods of analyzing and processing computer networks have difficulty dealing with their rapidly increasing scalability, structure, and traffic complexity due to the rapid development of information technology. Graph neural networks (GNNs), an emerging deep learning technology, adapt to graph-structured data and relationships. They offer new mechanisms and solutions to real-world problems. This paper provides a structured, unified synthesis of current research in this interdisciplinary field. It reviews the basic concepts and models of GNNs, highlights their current state in major computer network management and optimization scenarios, and discusses typical applications, challenges, open issues, and future research directions.