Static spatial grids over CLIP image embeddings improve text-to-image retrieval on homogeneous underwater keyframes, while text-only position suffixes do not.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Experimental Evaluation of Static Image Sub-Region-Based Search Models Using CLIP
Static spatial grids over CLIP image embeddings improve text-to-image retrieval on homogeneous underwater keyframes, while text-only position suffixes do not.