{"url":"/dataset/query-focused-video-summarization-dataset","name":"Query-Focused Video Summarization Dataset","full_name":null,"description_markdown":"Collects dense per-video-shot concept annotations.\r\n\r\nSource: [Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach](https://arxiv.org/pdf/1707.04960v1.pdf)","description_withheld":null,"homepage":"https://www.aidean-sharghi.com/cvpr2017","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/query-focused-video-summarization-dataset","title":"Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach","first_author":"Aidean Sharghi","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Video Summarization","url":"/task/video-summarization","datasets_with_task":"/datasets/task/video-summarization"},{"name":"Supervised Video Summarization","url":"/task/supervised-video-summarization","datasets_with_task":"/datasets/task/supervised-video-summarization"}],"languages":[],"variants":["Query-Focused Video Summarization Dataset"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-summarization-on-query-focused-video","task":"Video Summarization","dataset_variant":"Query-Focused Video Summarization Dataset","rows":2,"metrics":["F1 (avg)"],"first_row_in_archive_order":{"model":"EgoVLPv2","paper":"/paper/egovlpv2-egocentric-video-language-pre","metrics":{"F1 (avg)":"52.08"},"code_links":[{"title":"facebookresearch/EgoVLPv2","url":"https://github.com/facebookresearch/EgoVLPv2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/egovlpv2-egocentric-video-language-pre","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","date":"2023-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/egocentric-video-language-pretraining","title":"Egocentric Video-Language Pretraining","date":"2022-06-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":2,"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."}