Conceptual-12M

Emerging

1papers using it

2025first seen

The 'Conceptual-12M' dataset is used to evaluate the performance of vision-language models in cross-modal retrieval tasks by providing a large collection of images and their corresponding textual descriptions.

🔎 Find this dataset

Papers using Conceptual-12M (1)

Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?2025