A vision-language model is finetuned on 114k anonymized relational captions to embed images by their underlying structural correspondences instead of visible attributes.
Multimodal datasets: misogyny, pornography, and ma- lignant stereotypes.arXiv, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Relational Visual Similarity
A vision-language model is finetuned on 114k anonymized relational captions to embed images by their underlying structural correspondences instead of visible attributes.