With the emergence of large-scale vision-language pre-training (VLP) models, remote sensing (RS) image–text retrieval is shifting from global representation learning to fine-grained semantic alignment. This review systematically examines two mainstream representation paradigms—real-valued embedding and deep hashing—and analyzes how the evolution of RS datasets influences model capability, including multi-scale robustness, small object discriminability, and temporal semantic understanding. We further dissect three core challenges specific to RS scenarios: multi-scale semantic modeling, small object feature preservation, and multi-temporal reasoning. Representative architectures and technical solutions are reviewed in depth, followed by a critical discussion of their limitations in terms of generalization, evaluation consistency, and reproducibility. We also highlight the growing role of VLP-based models and the dependence of their performance on large-scale, high-quality image–text corpora. Finally, we outline future research directions, including RS-oriented VLP adaptation and unified multi-granularity evaluation frameworks. These insights aim to provide a coherent reference for advancing practical deployment and promoting cross-domain applications of RS image–text retrieval.

In recent years, autonomous driving technology has made remarkable progress in urban transportation and logistics, while its application in complex off-road environments has gradually become a research hotspot. Compared to traditional manned vehicles, unmanned vehicles demonstrate higher safety and flexibility in scenarios such as rapid transportation, emergency rescue, and environmental reconnaissance. However, current research on path planning is predominantly focused on structured environments, with limited attention given to unstructured off-road conditions. This paper proposes an improved A* algorithm tailored to address the challenges of path planning in complex off-road environments. First, a grid map incorporating multi-dimensional information is constructed by integrating elevation data, risk zones, and surface attributes, significantly enhancing environmental perception accuracy. At the algorithm level, the heuristic function and search strategy of the A* algorithm are optimized to improve its efficiency and path smoothness in complex terrains. Furthermore, the method supports the flexible planning of three types of paths—minimizing time, minimizing risk, or optimizing smoothness—based on specific task requirements. Simulation results demonstrate that the improved A* algorithm effectively adapts to dynamic off-road environments, providing intelligent and efficient path planning solutions for unmanned vehicles. The proposed method holds significant value for advancing the application of autonomous driving technology in complex environments.

Post-disaster emergency communication recovery is not merely a link-repair task but a high-level planning problem constrained by service priorities, inter-object dependencies, resource budgets, and time windows. Existing restoration optimization methods generally rely on fully structured inputs, whereas direct large language model (LLM) planning may produce fluent candidates that violate encoded prerequisites, stage-order relations, budget limits, or temporal constraints. To address this challenge, we propose ICG-Restore, an intent-constrained, graph-enhanced LLM planning framework with rule-consistent minimal-edit repair. ICG-Restore transforms mixed restoration requests and structured network observations into task packages that can be checked for validator-level feasibility under an encoded high-level constraint model and evaluated by downstream abstract executors or schedulers. The framework compiles natural-language requests, structured observations, and operational rules into a task-intent object; retrieves task-relevant context from a heterogeneous scenario graph and a restoration knowledge graph; generates stage-wise restoration candidates; and applies bounded local corrections to candidates that violate encoded constraints. In this paper, “minimal-edit” is a descriptive label for a bounded local repair principle that prioritizes less disruptive corrections. Candidates accepted by the validators are evaluated and ranked by a safety-aware agent executor operating in an abstract restoration action space. Experiments on controlled abstract topologies covering three scales, four restoration tasks, and five environmental evolution modes show that ICG-Restore improves validator-level constraint satisfaction and benchmark-estimated recovery utility. Compared with Direct-LLM, it improves CSR and CRS by 1.99% and 24.56%, respectively; benchmark-specific WCTC@5 structural-alignment diagnostic increases by 38.87%.

Post-disaster emergency communication recovery is not merely a link-repair task but a high-level planning problem constrained by service priorities, inter-object dependencies, resource budgets, and time windows. Existing restoration optimization methods generally rely on fully structured inputs, whereas direct large language model (LLM) planning often produces fluent yet operationally infeasible plans due to missing prerequisites, stage-order conflicts, and budget violations. To address this challenge, we propose ICG-Restore, an intent-constrained, graph-enhanced LLM planning framework with rule-consistent minimal-edit repair. The framework compiles natural-language requests, structured network observations, and operational rules into a task-intent object, retrieves task-relevant local context from a heterogeneous scenario graph and a restoration knowledge graph, generates stage-wise restoration candidates, and repairs infeasible plans through bounded edits that preserve the original planning backbone. Feasible candidates are then evaluated and ranked by a safety-aware agent executor in an abstract restoration action space. Experiments on three topology scales, four restoration tasks, and five environmental evolution modes demonstrate that ICG-Restore consistently improves executability, critical-target coverage, and overall recovery quality. Compared with Direct-LLM, it improves CSR, WCTC@5, and CRS by 1.99%, 38.87%, and 24.56%, respectively.

Accurate road graph extraction from satellite imagery is essential for large-scale mapping and geospatial analysis. Recent one-shot graph extraction frameworks based on foundation models have achieved promising performance, but their effectiveness decreases in complex environments where road structures are partially obscured by vegetation, buildings, shadows, and other surface conditions. These occlusion-induced disturbances lead to incomplete connectivity and degraded topology reconstruction, particularly under out-of-domain scenarios. This study proposes an occlusion-aware refinement framework to improve the robustness of satellite image road graph extraction while maintaining the original backbone architecture. The proposed framework introduces three complementary strategies: Synthetic Occlusion Augmentation for explicit occlusion-aware representation learning, an Occlusion-Adaptive Extended-Line strategy with Hard-Mining Topology Optimization for improved connectivity reasoning, and an Occlusion-Adaptive Node-Guided Resampling mechanism for reliable graph node localization. Experiments conducted on the Global-Scale road graph extraction benchmark demonstrate that the proposed method consistently improves topology reconstruction performance. Compared with the reproduced SAM-Road++ baseline, the proposed framework improves TOPO F1 from 61.81 to 62.56 on the in-domain split and from 46.93 to 51.51 on the out-of-domain split. Furthermore, the ID-OOD performance gap is reduced from 14.88 to 11.05, indicating enhanced robustness under unseen geographic conditions. The results demonstrate that explicitly modeling occlusion as a structured factor can effectively improve the generalization capability of satellite road graph extraction systems.

Remote sensing captions typically interleave domain-specific terminology, object attributes, spatial relations, and scene context within a single sentence, while the corresponding imagery contains targets spanning markedly different spatial extents—from individual vehicles to entire airport layouts. A single global text vector and fixed-scale visual pooling therefore tend to discard the local and hierarchical evidence needed for reliable image–text alignment. Moreover, standard contrastive objectives treat all unmatched pairs as equally unrelated, ignoring the fact that semantically adjacent scenes (e.g., airports and industrial zones) share substantial visual content. To address these issues, we develop a CLIP-style dual encoder with three targeted additions: a text encoder that preserves word-level, phrase-level, and sentence-level representations before fusing them through cross-granularity attention; a visual encoder that associates four hierarchical feature levels with scale-aware receptive-field configurations and incorporates SAM-guided local views during training; and a semantic membership-aware contrastive loss that applies detached, bounded discount weights to semantically close negatives without inverting their penalty sign. On the cleaned RSICD benchmark, the model achieves 87.5% mAP for in-domain prompt-based scene recognition and 34.37% mean recall for scene-constrained retrieval, outperforming the quoted RemoteCLIP and fully fine-tuned CLIP results in the scene-constrained retrieval comparison. Ablation confirms that each of the three components contributes meaningfully to the final performance. The deployable dual encoder contains approximately 59.7 million trainable parameters, and SAM is not required at inference.