Training on automatically generated hard negative captions improves vision-language models' zero-shot detection of fine-grained image-text mismatches and robustness to noisy inputs.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
Training on automatically generated hard negative captions improves vision-language models' zero-shot detection of fine-grained image-text mismatches and robustness to noisy inputs.