{"url":"/dataset/vspw","name":"VSPW","full_name":"Video Scene Parsing in the Wild","description_markdown":"A Large-scale Dataset for Video Scene Parsing in the Wild","description_withheld":null,"homepage":"https://www.vspwdataset.com/","introduced_date":"2021-06-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/vspw-a-large-scale-dataset-for-video-scene","title":"VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild","first_author":"Jiaxu Miao","url":null},"license":null,"modalities":[],"tasks":[{"name":"Video Semantic Segmentation","url":"/task/video-semantic-segmentation","datasets_with_task":"/datasets/task/video-semantic-segmentation"}],"languages":[],"variants":["VSPW"],"data_loaders":[],"num_papers_in_archive":35,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-semantic-segmentation-on-vspw","task":"Video Semantic Segmentation","dataset_variant":"VSPW","rows":5,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DVIS++(VIT-L)","paper":"/paper/dvis-improved-decoupled-framework-for","metrics":{"mIoU":"63.8"},"code_links":[{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":12,"samples_unverified":2,"pointer_only_for_licence":14,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dvis-improved-decoupled-framework-for","title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","date":"2023-12-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tube-link-a-flexible-cross-tube-baseline-for","title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","date":"2023-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mining-relations-among-cross-frame-affinities","title":"Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation","date":"2022-07-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/coarse-to-fine-feature-mining-for-video","title":"Learning Local and Global Temporal Contexts for Video Semantic Segmentation","date":"2022-04-07","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":15,"samples_ran":12,"samples_unverified":3,"pointer_only_for_licence":14,"papers_with_no_sample_that_ran":1,"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."}