Richer text prompts from LLM synonyms and cleaner image regions from activation maps improve zero-shot vision-language classification.
St-adapter: Parameter-efficient image-to-video transfer learning
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
-
Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
Richer text prompts from LLM synonyms and cleaner image regions from activation maps improve zero-shot vision-language classification.