{"url":"/dataset/pumavos","name":"PUMaVOS","full_name":"Partial and Unusual Masks for Video Object Segmentation","description_markdown":"PUMaVOS is a dataset of challenging and practical use cases inspired by the movie production industry.\r\n\r\n**Partial and Unusual Masks for Video Object Segmentation (PUMaVOS)** dataset has the following properties:\r\n- **24** videos, **21187** densely-annotated frames;\r\n- Covers complex practical use cases such as object parts, frequent occlusions, fast motion, deformable objects and more;\r\n- Average length of the video is **883 frames** or **29s**, with the longer ones spanning **1min**;\r\n- Fully densely annotated at 30FPS;\r\n- Benchmark-oriented: no separation into training/test, designed to be as diverse as possible to test your models;\r\n- 100% open and free to download.","description_withheld":null,"homepage":"https://max810.github.io/xmem2-project-page/#pumavos-dataset","introduced_date":"2023-07-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/xmem-production-level-video-segmentation-from","title":"XMem++: Production-level Video Segmentation From Few Annotated Frames","first_author":"Maksym Bekuzarov","url":null},"license":{"name":"CC BY 4.0","url":"https://max810.github.io/xmem2-project-page/#license"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"Video Object Segmentation","url":"/task/video-object-segmentation","datasets_with_task":"/datasets/task/video-object-segmentation"},{"name":"Semi-Supervised Video Object Segmentation","url":"/task/semi-supervised-video-object-segmentation","datasets_with_task":"/datasets/task/semi-supervised-video-object-segmentation"},{"name":"Interactive Segmentation","url":"/task/interactive-segmentation","datasets_with_task":"/datasets/task/interactive-segmentation"},{"name":"Interactive Video Object Segmentation","url":"/task/interactive-video-object-segmentation","datasets_with_task":"/datasets/task/interactive-video-object-segmentation"}],"languages":[],"variants":["PUMaVOS"],"data_loaders":[],"num_papers_in_archive":2,"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."}