{"url":"/dataset/cc12m","name":"CC12M","full_name":"Conceptual 12M","description_markdown":"Conceptual 12M (CC12M) is a dataset with 12 million image-text pairs specifically meant to be used for vision-and-language pre-training.\r\n\r\nSource: [Changpinyo et al.](https://arxiv.org/pdf/2102.08981v1.pdf)\r\n\r\nImage source: [Changpinyo et al.](https://arxiv.org/pdf/2102.08981v1.pdf)","description_withheld":null,"homepage":"https://arxiv.org/pdf/2102.08981v1.pdf","introduced_date":"2021-02-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/conceptual-12m-pushing-web-scale-image-text","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","first_author":"Soravit Changpinyo","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CC12M"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/conceptual_12m","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/conceptual_12m","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":153,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}