A scalable pipeline generates 1.7 million increasingly abstract MSCOCO captions, and fine-tuning CLIP on them improves zero-shot retrieval in poetry and metaphor tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mining Contextualized Visual Associations from Images for Creativity Understanding
A scalable pipeline generates 1.7 million increasingly abstract MSCOCO captions, and fine-tuning CLIP on them improves zero-shot retrieval in poetry and metaphor tasks.