CM50, a 33k-meme dataset with GPT-4o-generated annotations, and mtrCLIP, a fine-tuned CLIP model, together improve meme-text retrieval on MemeCap over the original CLIP.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes
CM50, a 33k-meme dataset with GPT-4o-generated annotations, and mtrCLIP, a fine-tuned CLIP model, together improve meme-text retrieval on MemeCap over the original CLIP.