GR-CoT improves remote sensing open-vocabulary segmentation by building category interpretation standards offline and using macro-scenario anchoring plus knowledge-driven synthesis online to create image-adaptive vocabularies.
Learning transferable visual models from natural language supervision,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geospatial-Reasoning-Driven Vocabulary-Agnostic Remote Sensing Semantic Segmentation
GR-CoT improves remote sensing open-vocabulary segmentation by building category interpretation standards offline and using macro-scenario anchoring plus knowledge-driven synthesis online to create image-adaptive vocabularies.