{"url":"/dataset/revos","name":"ReVOS","full_name":null,"description_markdown":"We create a benchmark dataset named ReVOS. This dataset comprises 35,074 pairs of instruction-mask sequences derived from 1,042 diverse videos. In contrast to traditional referring video segmentation datasets, such as Ref-YouTube-VOS and MeViS, which primarily contain explicit short phrases, ReVOS includes text instructions that necessitates a sophisticated understanding of both video content and general world knowledge","description_withheld":null,"homepage":"https://github.com/cilinyan/revos-api","introduced_date":"2024-07-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","first_author":"Cilin Yan","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Referring Video Object Segmentation","url":"/task/referring-video-object-segmentation","datasets_with_task":"/datasets/task/referring-video-object-segmentation"}],"languages":[],"variants":["ReVOS"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/referring-video-object-segmentation-on-revos","task":"Referring Video Object Segmentation","dataset_variant":"ReVOS","rows":9,"metrics":["J&F","J","F","R"],"first_row_in_archive_order":{"model":"VRS-HQ (Chat-UniVi-13B)","paper":"/paper/the-devil-is-in-temporal-token-high-quality","metrics":{"F":"62.5","J":"57.6","J&F":"60","R":"18.9"},"code_links":[{"title":"sitonggong/vrs-hq","url":"https://github.com/sitonggong/vrs-hq"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-devil-is-in-temporal-token-high-quality","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","date":"2025-01-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tracking-with-human-intent-reasoning","title":"Tracking with Human-Intent Reasoning","date":"2023-12-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","date":"2023-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":6,"samples_unverified":5,"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":4,"samples_harvested":26,"samples_ran":15,"samples_unverified":11,"pointer_only_for_licence":10,"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."}