# SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning

arXiv: https://arxiv.org/abs/2006.08432 · HTML: https://mlsanity.com/paper/2006.08432/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 19 of 19)

- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information](https://mlsanity.com/paper/2204.09860/) (2022)
- [Large Language Models for Captioning and Retrieving Remote Sensing Images](https://mlsanity.com/paper/2402.06475/) (2024)
- [Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward](https://mlsanity.com/paper/2305.08413/) (2023)
- [Towards a Collective Agenda on AI for Earth Science Data Analysis](https://mlsanity.com/paper/2104.05107/) (2021)
- [Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning](https://mlsanity.com/paper/2312.01191/) (2023)
- [RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering](https://mlsanity.com/paper/2411.01595/) (2024)
- [LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery](https://mlsanity.com/paper/2505.02829/) (2025)
- [Multilingual Augmentation for Robust Visual Question Answering in Remote Sensing Images](https://mlsanity.com/paper/2304.03844/) (2023)
- [Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning](https://mlsanity.com/paper/2212.01261/) (2022)
- [GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing](https://mlsanity.com/paper/2507.05887/) (2025)
- [Good Representation, Better Explanation: Role of Convolutional Neural Networks in Transformer-Based Remote Sensing Image Captioning](https://mlsanity.com/paper/2502.16095/) (2025)
- [BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation](https://mlsanity.com/paper/2603.29630/) (2026)
- [Offline Evaluation of Set-Based Text-to-Image Generation](https://mlsanity.com/paper/2410.17331/) (2024)
- [Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges](https://mlsanity.com/paper/2508.06832/) (2025)
- [Multimodal Analysis Of Google Bard And GPT-Vision: Experiments In Visual Reasoning](https://mlsanity.com/paper/2309.16705/) (2023)
- [MsEdF: A Multi-stream Encoder-decoder Framework for Remote Sensing Image Captioning](https://mlsanity.com/paper/2502.09282/) (2025)
- [A Novel Lightweight Transformer with Edge-Aware Fusion for Remote Sensing Image Captioning](https://mlsanity.com/paper/2506.09429/) (2025)

## Abstract (arXiv)

Deep neural networks (DNNs) have been recently found popular for image captioning problems in remote sensing (RS). Existing DNN based approaches rely on the availability of a training set made up of a high number of RS images with their captions. However, captions of training images may contain redundant information (they can be repetitive or semantically similar to each other), resulting in information deficiency while learning a mapping from the image domain to the language domain. To overcome this limitation, in this paper, we present a novel Summarization Driven Remote Sensing Image Captioning (SD-RSIC) approach. The proposed approach consists of three main steps. The first step obtains the standard image captions by jointly exploiting convolutional neural networks (CNNs) with long short-term memory (LSTM) networks. The second step, unlike the existing RS image captioning methods, summarizes the ground-truth captions of each training image into a single caption by exploiting sequence to sequence neural networks and eliminates the redundancy present in the training set. The third step automatically defines the adaptive weights associated to each RS image to combine the standard captions with the summarized captions based on the semantic content of the image. This is achieved by a novel adaptive weighting strategy defined in the context of LSTM networks. Experimental results obtained on the RSCID, UCM-Captions and Sydney-Captions datasets show the effectiveness of the proposed approach compared to the state-of-the-art RS image captioning approaches. The code of the proposed approach is publicly available at https://gitlab.tubit.tu-berlin.de/rsim/SD-RSIC.