{"url":"/dataset/vipseg","name":"VIPSeg","full_name":null,"description_markdown":"A large-scale VIdeo Panoptic Segmentation dataset","description_withheld":null,"homepage":"https://github.com/vipseg-dataset/vipseg-dataset","introduced_date":"2022-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/large-scale-video-panoptic-segmentation-in","title":"Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark","first_author":"Jiaxu Miao","url":null},"license":null,"modalities":[],"tasks":[{"name":"Video Panoptic Segmentation","url":"/task/video-panoptic-segmentation","datasets_with_task":"/datasets/task/video-panoptic-segmentation"}],"languages":[],"variants":["VIPSeg"],"data_loaders":[],"num_papers_in_archive":32,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-panoptic-segmentation-on-vipseg","task":"Video Panoptic Segmentation","dataset_variant":"VIPSeg","rows":12,"metrics":["VPQ","STQ"],"first_row_in_archive_order":{"model":"CAVIS(VIT-L)","paper":"/paper/context-aware-video-instance-segmentation","metrics":{"STQ":"56.1","VPQ":"58.5"},"code_links":[{"title":"Seung-Hun-Lee/CAVIS","url":"https://github.com/Seung-Hun-Lee/CAVIS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/context-aware-video-instance-segmentation","title":"Context-Aware Video Instance Segmentation","date":"2024-07-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/maxtron-mask-transformer-with-trajectory","title":"A Simple Video Segmenter by Tracking Objects Along Axial Trajectories","date":"2023-11-30","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dvis-decoupled-video-instance-segmentation","title":"DVIS: Decoupled Video Instance Segmentation Framework","date":"2023-06-06","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/tarvis-a-unified-approach-for-target-based","title":"TarViS: A Unified Approach for Target-based Video Segmentation","date":"2023-01-06","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"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":3,"samples_harvested":30,"samples_ran":19,"samples_unverified":11,"pointer_only_for_licence":24,"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."}