RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events

2025/09/02 by Chen, Zhenyuan, Wang, Chenxi, Zhang, Ningyu +1 · 2 citations
#Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2509.01907

Abstract

Remote sensing is critical for disaster monitoring, yet existing datasets lack temporal image pairs and detailed textual annotations. While single-snapshot imagery dominates current resources, it fails to capture dynamic disaster impacts over time. To address this gap, we introduce the Remote Sensing Change Caption (RSCC) dataset, a large-scale benchmark comprising 62,351 pre-/post-disaster image pairs (spanning earthquakes, floods, wildfires, and more) paired with rich, human-like change captions. By bridging the temporal and semantic divide in remote sensing data, RSCC enables robust training and evaluation of vision-language models for disaster-aware bi-temporal understanding. Our results highlight RSCC's ability to facilitate detailed disaster-related analysis, paving the way for more accurate, interpretable, and scalable vision-language applications in remote sensing. Code and dataset are available at https://github.com/Bili-Sakura/RSCC.

Citations

• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
• XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?
• VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity
• Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
• Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
• Qwen2.5 Technical Report
• G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey
• CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset
• HourVideo: 1-Hour Video-Language Understanding
• MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
• TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
• E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
• MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
• MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
• FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model
• Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
• Segment Any Change
• Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
• Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
• Improved Baselines with Visual Instruction Tuning
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• RSGPT: A Remote Sensing Vision Language Model and Benchmark
• What does CLIP know about a red circle? Visual prompt engineering for VLMs
• A Contrastive Framework for Neural Text Generation
• Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
• Learning Transferable Visual Models From Natural Language Supervision
• The Multi-Temporal Urban Development SpaceNet Dataset
• FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding
• BLEURT: Learning Robust Metrics for Text Generation
• xBD: A Dataset for Assessing Building Damage from Satellite Imagery
• Neural Text Generation with Unlikelihood Training
• Functional Map of the World

Cited by

• SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images
• Think First, Assign Next (ThiFAN-VQA): A Two-stage Chain-of-Thought Framework for Post-Disaster Damage Assessment

Related

• DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
• Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance
• Towards a multimodal framework for remote sensing image change retrieval and captioning
• CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset
• Change Captioning in Remote Sensing: Evolution to SAT-Cap -- A Single-Stage Transformer Approach