Flickr30k
Emerging2papers using it
2023first seen
The 'Flickr-30K' dataset contains 30,000 images, each paired with five corresponding descriptive captions, and is used to evaluate vision-language tasks such as image captioning and retrieval.
The 'Flickr-30K' dataset contains 30,000 images, each paired with five corresponding descriptive captions, and is used to evaluate vision-language tasks such as image captioning and retrieval.