A new reference-free metric, SPECS, fine-tunes LongCLIP with a specificity objective and reaches LLM-level human correlation on long captions at a fraction of the computational cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
A new reference-free metric, SPECS, fine-tunes LongCLIP with a specificity objective and reaches LLM-level human correlation on long captions at a fraction of the computational cost.