{"url":"/dataset/muses","name":"MUSES","full_name":"MUlti-Shot EventS","description_markdown":"MUSES is a large-scale dataset for temporal event (action) localization. It focuses on the temporal localization of multi-shot events, which are captured with multiple shots. Such events often appear in edited videos, such as TV shows and movies. \r\n\r\nWhat’s included in MUSES:\r\n\r\n* 3,697 videos of TV and movie dramas\r\n* 716 hours of duration\r\n* 25 event categories\r\n* 652k shots\r\n* 31,477 annotated event instances","description_withheld":null,"homepage":"http://songbai.site/muses/","introduced_date":"2020-12-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/multi-shot-temporal-event-localization-a","title":"Multi-shot Temporal Event Localization: a Benchmark","first_author":"Xiaolong Liu","url":null},"license":null,"modalities":[],"tasks":[{"name":"Temporal Action Localization","url":"/task/action-recognition","datasets_with_task":"/datasets/task/action-recognition"}],"languages":[],"variants":["MUSES"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/temporal-action-localization-on-muses","task":"Temporal Action Localization","dataset_variant":"MUSES","rows":2,"metrics":["mAP","mAP@0.3","mAP@0.4","mAP@0.5","mAP@0.6","mAP@0.7"],"first_row_in_archive_order":{"model":"TemporalMaxer","paper":"/paper/temporalmaxer-maximize-temporal-context-with","metrics":{"mAP":"27.2","mAP@0.3":"36.7","mAP@0.4":"33.2","mAP@0.5":"27.8 ","mAP@0.6":"21.9","mAP@0.7":"16.2"},"code_links":[{"title":"tuantng/temporalmaxer","url":"https://github.com/tuantng/temporalmaxer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/temporalmaxer-maximize-temporal-context-with","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","date":"2023-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-shot-temporal-event-localization-a","title":"Multi-shot Temporal Event Localization: a Benchmark","date":"2020-12-17","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."}