Scene-graph-guided multimodal RAG improves aerial VQA by feeding query-relevant structured visual knowledge to a text LLM instead of dense visual tokens.
AUG: A new dataset and an efficient model for aerial image urban scene graph generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
Scene-graph-guided multimodal RAG improves aerial VQA by feeding query-relevant structured visual knowledge to a text LLM instead of dense visual tokens.
- PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments