# FSAR-Cap: A Fine-Grained Two-Stage Annotated Dataset for SAR Image Captioning

arXiv: https://arxiv.org/abs/2510.16394 · HTML: https://mlsanity.com/paper/2510.16394/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2025.

## Built on by (most cited first, 2 of 2)

- [RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation](https://mlsanity.com/paper/2607.24810/) (2026)
- [OmniRSI: Taming Latent Diffusion for Unified Multimodal Remote Sensing Image Generation](https://mlsanity.com/paper/2610.15414/) (2026)

## Abstract (arXiv)

Synthetic Aperture Radar (SAR) image captioning enables scene-level semantic understanding and plays a crucial role in applications such as military intelligence and urban planning, but its development is limited by the scarcity of high-quality datasets. To address this, we present FSAR-Cap, a large-scale SAR captioning dataset with 14,480 images and 72,400 image-text pairs. FSAR-Cap is built on the FAIR-CSAR detection dataset and constructed through a two-stage annotation strategy that combines hierarchical template-based representation, manual verification and supplementation, prompt standardization. Compared with existing resources, FSAR-Cap provides richer fine-grained annotations, broader category coverage, and higher annotation quality. Benchmarking with multiple encoder-decoder architectures verifies its effectiveness, establishing a foundation for future research in SAR captioning and intelligent image interpretation.