VRAP claims state-of-the-art vision-language results by prepending image-derived object tags to LLM prompts, but the evidence is incomplete and internally inconsistent.
In: Findings of the Association for Comput ational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11- 16, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes
VRAP claims state-of-the-art vision-language results by prepending image-derived object tags to LLM prompts, but the evidence is incomplete and internally inconsistent.