Injecting LLM-generated action triplets and action state descriptions as learnable visual prompts improves CLIP's image-text retrieval performance on Flickr30K and COCO.
Sim- ilarity reasoning and filtration for image-text matching
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching
Injecting LLM-generated action triplets and action state descriptions as learnable visual prompts improves CLIP's image-text retrieval performance on Flickr30K and COCO.