GRASP combines region-focused alignment with semantic prototype based hard-negative synthesis to improve drone-view fine-grained image-text retrieval.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views
GRASP combines region-focused alignment with semantic prototype based hard-negative synthesis to improve drone-view fine-grained image-text retrieval.