{"url":"/dataset/long-rvos","name":"Long-RVOS","full_name":null,"description_markdown":"This work proposes Long-RVOS, a large-scale benchmark for long-term video object segmentation. Long-RVOS is the first minute-level dataset in the RVOS field, designed to tackle various realistic long-video challenges such as frequent occlusion, disappearance-reappearance, and shot changing. Notably, Long-RVOS offers significantly longer video duration than existing datasets. In addition, it contains the largest number of object classes and mask annotations. The large scale of Long-RVOS supports comprehensive training and evaluation of RVOS models. Finally, we gather 24,689 high-quality descriptions for building Long-RVOS.","description_withheld":null,"homepage":"https://isee-laboratory.github.io/Long-RVOS","introduced_date":"2025-05-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/long-rvos-a-comprehensive-benchmark-for-long","title":"Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation","first_author":"Tianming Liang","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Referring Video Object Segmentation","url":"/task/referring-video-object-segmentation","datasets_with_task":"/datasets/task/referring-video-object-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Long-RVOS"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/referring-video-object-segmentation-on-long","task":"Referring Video Object Segmentation","dataset_variant":"Long-RVOS","rows":7,"metrics":["J&F","tIoU","vIoU"],"first_row_in_archive_order":{"model":"ReferMo","paper":"/paper/long-rvos-a-comprehensive-benchmark-for-long","metrics":{"J&F":"51.3","tIoU":"71.2","vIoU":"42.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/long-rvos-a-comprehensive-benchmark-for-long","title":"Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation","date":"2025-05-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/glus-global-local-reasoning-unified-into-a","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","date":"2025-04-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":3,"samples_unverified":9,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/referdino-referring-video-object-segmentation","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","date":"2025-01-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/samwise-infusing-wisdom-in-sam2-for-text","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","date":"2024-11-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/one-token-to-seg-them-all-language-instructed","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","date":"2024-09-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":7,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/soc-semantic-assisted-object-cluster-for","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","date":"2023-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/referred-by-multi-modality-a-unified-temporal","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","date":"2023-05-25","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":28,"samples_ran":10,"samples_unverified":18,"pointer_only_for_licence":12,"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."}