VCRScore, a gradient-boosting regressor on ViLT, CLIP, and lexical precision/recall features, achieves the highest Spearman correlation with human caption-quality scores among the metrics tested.
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
-
VCRScore: Image captioning metric based on V\&L Transformers, CLIP, and precision-recall
VCRScore, a gradient-boosting regressor on ViLT, CLIP, and lexical precision/recall features, achieves the highest Spearman correlation with human caption-quality scores among the metrics tested.