{"url":"/dataset/mediapi-rgb","name":"Mediapi-RGB","full_name":"Mediapi-RGB","description_markdown":"Mediapi-RGB is a bilingual corpus of French Sign Language (LSF) and written French in the form of subtitled videos, accompanied by complementary data (various representations, segmentation, vocabulary, etc.). It can be used in academic research for a wide range of tasks, such as training or evaluating sign language (SL)  extraction, recognition or translation models.\r\n\r\nTo build this corpus, we used videos from   Média'Pi!, a bilingual online media with journalistic-type content in LSF with French subtitles. We collected 1230 videos dating from September 2017 to January 2022, representing a total of 86h. Based on the subtitles, we temporally segmented the videos into 50084 video segments (or extracts). We also automatically cropped the signer and harmonised the segments in terms of size (444x444) and frequency (25fps).","description_withheld":null,"homepage":"https://www.ortolang.fr/market/corpora/mediapi-rgb?lang=en","introduced_date":"2024-02-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/mediapi-rgb-enabling-technological","title":"Mediapi-RGB: Enabling Technological Breakthroughs in French Sign Language (LSF) Research through an Extensive Video-Text Corpus","first_author":"Yanis Ouakrim","url":null},"license":{"name":"Research Only","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sign Language Translation","url":"/task/sign-language-translation","datasets_with_task":"/datasets/task/sign-language-translation"},{"name":"Gloss-free Sign Language Translation","url":"/task/gloss-free-sign-language-translation","datasets_with_task":"/datasets/task/gloss-free-sign-language-translation"},{"name":"Sign Language Production","url":"/task/sign-language-production","datasets_with_task":"/datasets/task/sign-language-production"}],"languages":[{"name":"French","url":"/datasets/language/french"},{"name":"French Sign Language","url":"/datasets/language/french-sign-language"}],"variants":["Mediapi-RGB"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sign-language-translation-on-mediapi-rgb","task":"Sign Language Translation","dataset_variant":"Mediapi-RGB","rows":1,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"Transformer Baseline","paper":"/paper/mediapi-rgb-enabling-technological","metrics":{"BLEU-4":"4.14"},"code_links":[{"title":"youakrim/sign_language_translation_Mediapi-RGB","url":"https://github.com/youakrim/sign_language_translation_Mediapi-RGB"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mediapi-rgb-enabling-technological","title":"Mediapi-RGB: Enabling Technological Breakthroughs in French Sign Language (LSF) Research through an Extensive Video-Text Corpus","date":"2024-02-29","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}