{"url":"/dataset/wukong","name":"Wukong","full_name":null,"description_markdown":"**Wukong** is a large-scale Chinese cross-modal dataset for benchmarking different multi-modal pre-training methods to facilitate the Vision-Language Pre-training (VLP). This dataset contains 100 million Chinese image-text pairs from the web. This base query list is taken from and is filtered according to the frequency of Chinese words and phrases.","description_withheld":null,"homepage":"https://wukong-dataset.github.io/wukong-dataset/","introduced_date":"2022-02-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/wukong-100-million-large-scale-chinese-cross","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","first_author":"Jiaxi Gu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Wukong"],"data_loaders":[],"num_papers_in_archive":16,"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."}