{"url":"/dataset/sakuga-42m","name":"Sakuga-42M","full_name":null,"description_markdown":"Sakuga-42M is a large-scale hand-drawn cartoon video dataset for academic research purposes, it comprises 42 million cartoon keyframes covering various artistic styles, regions, and years, with comprehensive semantic annotations including video-text description pairs, anime tags, content taxonomies, etc. The dataset is intended to support researchers in their exploration of more effective and practical solutions for creating cartoons.","description_withheld":null,"homepage":"https://github.com/zhenglinpan/SakugaDataset","introduced_date":"2024-05-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/sakuga-42m-dataset-scaling-up-cartoon","title":"Sakuga-42M Dataset: Scaling Up Cartoon Research","first_author":"Zhenglin Pan","url":null},"license":{"name":"CC BY-NC-SA","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Text to Video Retrieval","url":"/task/text-to-video-retrieval","datasets_with_task":"/datasets/task/text-to-video-retrieval"},{"name":"Video to Text Retrieval","url":"/task/video-to-text-retrieval","datasets_with_task":"/datasets/task/video-to-text-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["Sakuga-42M"],"data_loaders":[],"num_papers_in_archive":2,"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."}