{"url":"/dataset/sfd","name":"SF20K","full_name":"Short-Films 20K","description_markdown":"Short-Films 20K (SF20K) is the largest publicly available movie dataset. SF20K is composed of 20,143 amateur films and offers long-term video tasks in the form of multiple-choice and open-ended question answering.","description_withheld":null,"homepage":"https://ridouaneg.github.io/sf20k.html","introduced_date":"2024-06-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/short-film-dataset-sfd-a-benchmark-for-story","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","first_author":"Ridouane Ghermi","url":null},"license":{"name":"cc-by-nc-sa-4.0","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Multiple Choice Question Answering (MCQA)","url":"/task/multiple-choice-qa","datasets_with_task":"/datasets/task/multiple-choice-qa"},{"name":"Open-Ended Question Answering","url":"/task/open-question","datasets_with_task":"/datasets/task/open-question"},{"name":"zero-shot long video question answering","url":"/task/zero-shot-long-video-question-answering","datasets_with_task":"/datasets/task/zero-shot-long-video-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SF20K"],"data_loaders":[],"num_papers_in_archive":1,"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."}