{"url":"/dataset/ssv2-spatio-temporal","name":"SSv2-Spatio-Temporal","full_name":"Something Someting v2-Spatio-Temporal","description_markdown":"We use Something-Something v2 dataset to obtain the generation prompts and ground truth masks from real action videos. We filter out a set of 295 prompts. The details for this filtering are in the \"Peekaboo: Interactive Video Generation via Masked-Diffusion\" paper. We then use an off-the-shelf OWL-ViT-large open-vocabulary object detector to obtain the bounding box (bbox) annotations of the object in the videos. This set represents bbox and prompt pairs of real-world videos, serving as a test bed for both the quality and control of methods for generating realistic videos with spatio-temporal control.","description_withheld":null,"homepage":"https://github.com/microsoft/Peekaboo/blob/main/eval/README.md","introduced_date":"2023-12-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/peekaboo-interactive-video-generation-via","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","first_author":"Yash Jain","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Interactive","url":"/datasets/modality/interactive"},{"name":"Tracking","url":"/datasets/modality/tracking"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SSv2-Spatio-Temporal"],"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."}