March 28, 2023
fireshot capture 1393 google ai blog crossmodal 3600 multilingual reference captions fo

Google releases crossmodal-3600 dataset of geographic diversity image captions

Google has released the Crossmodal-3600 image captioning evaluation dataset, which serves as a benchmark for linguistic image captioning, allowing researchers to study the field more reliably. Crossmodal-3600 in 36 languages, with 3,600 different photos from around the world, plus 261,375 human-generated reference captions, the researchers mentioned that the captions from Crossmodal-3600 are of good quality and maintain a consistent style across languages .

Ewen Eagle

I am the founder of Urbantechstory, a Technology based blog. where you find all kinds of trending technology, gaming news, and much more.

View all posts by Ewen Eagle →

Leave a Reply

Your email address will not be published.