{"url":"/dataset/hq-ytvis","name":"HQ-YTVIS","full_name":null,"description_markdown":"While Video Instance Segmentation (VIS) has seen rapid progress, current approaches struggle to predict high-quality masks with accurate boundary details. To tackle this issue, we identify that the coarse boundary annotations of the popular YouTube-VIS dataset constitute a major limiting factor. To benchmark high-quality mask predictions for VIS, we introduce the HQ-YTVIS dataset as well as Tube-Boundary AP in ECCV 2022. HQ-YTVIS consists of a manually re-annotated test set and our automatically refined training data, which provides training, validation and testing support to facilitate future development of VIS methods aiming at higher mask quality.","description_withheld":null,"homepage":"https://www.vis.xyz/data/hqvis/","introduced_date":"2022-07-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/video-mask-transfiner-for-high-quality-video","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","first_author":"Lei Ke","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[],"tasks":[{"name":"Video Instance Segmentation","url":"/task/video-instance-segmentation","datasets_with_task":"/datasets/task/video-instance-segmentation"}],"languages":[],"variants":["HQ-YTVIS"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-instance-segmentation-on-hq-ytvis","task":"Video Instance Segmentation","dataset_variant":"HQ-YTVIS","rows":4,"metrics":["Tube-Boundary AP"],"first_row_in_archive_order":{"model":"VMT (Swin-L)","paper":"/paper/video-mask-transfiner-for-high-quality-video","metrics":{"Tube-Boundary AP":"44.8"},"code_links":[{"title":"SysCV/vmt","url":"https://github.com/SysCV/vmt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/video-mask-transfiner-for-high-quality-video","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","date":"2022-07-28","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/seqformer-a-frustratingly-simple-model-for","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","date":"2021-12-15","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":7,"samples_ran":5,"samples_unverified":2,"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."}