{"url":"/dataset/video-localized-narratives","name":"Video Localized Narratives","full_name":null,"description_markdown":"**Video Localized Narratives** is a new form of multimodal video annotations connecting vision and language. The annotations are created from videos with Localized Narratives, capturing even complex events involving multiple actors interacting with each other and with several passive objects. It contains annotations of 20k videos of the OVIS, UVO, and Oops datasets, totalling 1.7M words.\r\n\r\nSource: [Connecting Vision and Language with Video Localized Narratives](https://arxiv.org/pdf/2302.11217v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2302.11217v1.pdf](https://arxiv.org/pdf/2302.11217v1.pdf)","description_withheld":null,"homepage":"https://google.github.io/video-localized-narratives/","introduced_date":"2023-02-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/connecting-vision-and-language-with-video","title":"Connecting Vision and Language with Video Localized Narratives","first_author":"Paul Voigtlaender","url":null},"license":{"name":"CC BY 4.0 License","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Video Narrative Grounding","url":"/task/video-narrative-grounding","datasets_with_task":"/datasets/task/video-narrative-grounding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Video Localized Narratives"],"data_loaders":[],"num_papers_in_archive":3,"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."}