{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":7,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/the-devil-is-in-temporal-token-high-quality","slug":"the-devil-is-in-temporal-token-high-quality","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","date":"2025-01-15","arxiv_id":"2501.08549","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/visa-reasoning-video-object-segmentation-via","slug":"visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["cilinyan/VISA","cilinyan/revos-api"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visa-reasoning-video-object-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2407.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11325"}}}},{"paper":"/paper/tracking-with-human-intent-reasoning","slug":"tracking-with-human-intent-reasoning","title":"Tracking with Human-Intent Reasoning","date":"2023-12-29","arxiv_id":"2312.17448","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mevis-a-large-scale-benchmark-for-video","slug":"mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","date":"2023-08-16","arxiv_id":"2308.08544","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["henghuiding/MeViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mevis-a-large-scale-benchmark-for-video#ran","syntology_url":"https://syntology.ai/paper/2308.08544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08544"}}}},{"paper":"/paper/lisa-reasoning-segmentation-via-large","slug":"lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","arxiv_id":"2308.00692","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":8,"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-as-queries-for-referring-video#ran","syntology_url":"https://syntology.ai/paper/2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}}}},{"paper":"/paper/end-to-end-referring-video-object","slug":"end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","arxiv_id":"2111.14821","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["mttr2021/MTTR"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-referring-video-object#ran","syntology_url":"https://syntology.ai/paper/2111.14821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14821"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/the-devil-is-in-temporal-token-high-quality","slug":"the-devil-is-in-temporal-token-high-quality","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","date":"2025-01-15","arxiv_id":"2501.08549","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/visa-reasoning-video-object-segmentation-via","slug":"visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["cilinyan/VISA","cilinyan/revos-api"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visa-reasoning-video-object-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2407.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11325"}}}},{"paper":"/paper/tracking-with-human-intent-reasoning","slug":"tracking-with-human-intent-reasoning","title":"Tracking with Human-Intent Reasoning","date":"2023-12-29","arxiv_id":"2312.17448","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mevis-a-large-scale-benchmark-for-video","slug":"mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","date":"2023-08-16","arxiv_id":"2308.08544","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["henghuiding/MeViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mevis-a-large-scale-benchmark-for-video#ran","syntology_url":"https://syntology.ai/paper/2308.08544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08544"}}}},{"paper":"/paper/lisa-reasoning-segmentation-via-large","slug":"lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","arxiv_id":"2308.00692","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":8,"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-as-queries-for-referring-video#ran","syntology_url":"https://syntology.ai/paper/2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}}}},{"paper":"/paper/end-to-end-referring-video-object","slug":"end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","arxiv_id":"2111.14821","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["mttr2021/MTTR"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-referring-video-object#ran","syntology_url":"https://syntology.ai/paper/2111.14821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14821"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/revos/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/revos/papers/ran/1","json":"/dataset/revos/papers/ran/1.json","rows":4}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":26,"samples_ran":22,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":15,"samples_unverified":4,"pointer_only_for_licence":16,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":2,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/referring-video-object-segmentation-on-revos","since_archive":"/sota/referring-video-object-segmentation-on-revos#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"47b42e8e53566afc76ee61bdfa0c914445049b58d9fbd726e2af95e6f2825efb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}