{"url":"/dataset/youku-mplug","name":"Youku-mPLUG","full_name":null,"description_markdown":"**Youku-mPLUG** is a large Chinese high-quality video-language dataset which is collected from Youku.com, a well-known Chinese video-sharing website, with strict criteria of safety, diversity, and quality. It contains 10 million video-text pairs for pre-training and 0.3 millon videos for downstream benchmarks covering Video-Text Retrieval, Video Captioning and Video Category Classification. \r\n\r\nSource: [Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks](https://arxiv.org/pdf/2306.04362v1.pdf)\r\n\r\nImage Source: [Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks](https://arxiv.org/pdf/2306.04362v1.pdf)","description_withheld":null,"homepage":"https://github.com/X-PLUG/Youku-mPLUG","introduced_date":"2023-06-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","first_author":"Haiyang Xu","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/X-PLUG/Youku-mPLUG/blob/main/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Video-Text Retrieval","url":"/task/video-text-retrieval","datasets_with_task":"/datasets/task/video-text-retrieval"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Youku-mPLUG"],"data_loaders":[],"num_papers_in_archive":4,"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."}