{"url":"/dataset/dialogcc","name":"DialogCC","full_name":null,"description_markdown":"**DialogCC** is a large-scale multi-modal dialogue dataset, which covers diverse real-world topics and various images per dialogue. It contains 651k unique images and is designed for image and text retrieval tasks.\r\n\r\nSource: [DialogCC: Large-Scale Multi-Modal Dialogue Dataset](https://arxiv.org/pdf/2212.04119v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2212.04119v1.pdf](https://arxiv.org/pdf/2212.04119v1.pdf)","description_withheld":null,"homepage":"https://github.com/passing2961/DialogCC","introduced_date":"2022-12-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/dialogcc-large-scale-multi-modal-dialogue","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","first_author":"Young-Jun Lee","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Dialog","url":"/datasets/modality/dialog"}],"tasks":[{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DialogCC"],"data_loaders":[],"num_papers_in_archive":1,"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."}