C3-Bench supplies a multi-domain dataset and LLM-based evaluation protocol that exposes systematic failures in existing change captioning models outside their training regimes.
xBD: A Dataset for Assessing Building Damage from Satellite Imagery, November 2019
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
representative citing papers
Introduces Forged Calamity benchmark and shows that fine-tuned and zero-shot synthetic image detectors lose substantial accuracy on unseen generators and disaster types.
DORA is the first end-to-end agentic benchmark for LLM-based disaster response, covering perception, spatial analysis, evacuation planning, temporal reasoning, and report generation over heterogeneous geospatial data, with evaluations of 13 frontier models revealing tool-use and composition failures
The paper delivers the first comprehensive review and unified taxonomy of agentic AI in remote sensing, covering single-agent copilots, multi-agent systems, planning mechanisms, benchmarks, and a roadmap while noting limitations in grounding and safety.
FROST performs training-free few-shot segmentation on remote-sensing imagery by nonparametric density-ratio classification on frozen DINOv3 features and reports 5.6 mIoU gains from one example across 17 benchmarks.
GeoDisaster provides a new benchmark for operational disaster geo-intelligence and proposes an RCEA-trained multi-agent framework with 18 geospatial tools that improves tool use and decision consistency over existing RS-VLMs.
Damage-TriageFormer extends a DINOv3 ViT-L backbone with a feature pyramid and gated head to classify mono-temporal post-event imagery into five damage typologies on a new NOAA-derived benchmark, reporting macro F1 of 0.62.
UniReason-Med introduces a unified framework for 2D and 3D medical VQA with shared grounded reasoning, trained on a 220K dataset, claiming that joint 2D+3D supervision improves 3D performance over 3D-only training.
Position paper identifies structural challenges in applying generic agentic AI to Earth Observation and outlines design principles for EO-native agents focused on geospatial state and validity.
A hybrid AI system combines super-resolution, YOLO-based detection, and vision-language models to semantically classify building damage severity in pre- and post-disaster satellite images.
Supervised domain adaptation is required for any functional building damage detection across disasters, reaching Macro-F1 0.5552 on unseen Ida-BD data when combined with unsharp masking.
Dual-domain models achieve the highest accuracy (0.4688) while frequency-only models overfit and all approaches struggle with the minor damage class due to imbalance.
citing papers explorer
No citing papers match the current filters.