{"url":"/dataset/mtvr","name":"mTVR","full_name":null,"description_markdown":"mTVR is a large-scale multilingual video moment retrieval dataset, containing 218K English and Chinese queries from 21.8K TV show video clips. The dataset is collected by extending the popular TVR dataset (in English) with paired Chinese queries and subtitles. Compared to existing moment retrieval datasets, mTVR is multilingual, larger, and comes with diverse annotations.\r\n\r\nSource: [MTVR: Multilingual Moment Retrieval in Videos](https://arxiv.org/pdf/2108.00061v1.pdf)\r\n\r\nImage source: [MTVR: Multilingual Moment Retrieval in Videos](https://arxiv.org/pdf/2108.00061v1.pdf)","description_withheld":null,"homepage":"https://github.com/jayleicn/mTVRetrieval","introduced_date":"2021-07-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/mtvr-multilingual-moment-retrieval-in-videos","title":"MTVR: Multilingual Moment Retrieval in Videos","first_author":"Jie Lei","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["mTVR"],"data_loaders":[],"num_papers_in_archive":5,"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."}