{"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/uvo","name":"UVO","full_name":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","description_markdown":"UVO is a new benchmark for open-world class-agnostic object segmentation in videos. Besides shifting the problem focus to the open-world setup, UVO is significantly larger, providing approximately 8 times more videos compared with [DAVIS](/dataset/davis), and 7 times more mask (instance) annotations per video compared with [YouTube-VOS](/dataset/youtube-vos) and [YouTube-VIS](/dataset/youtubevis). UVO is also more challenging as it includes many videos with crowded scenes and complex background motions. Some highlights of the dataset include:\r\n\r\n- High quality instance masks densely annotated at 30 fps on 1024 YouTube videos and 1fps on 10337 videos from Kinetics dataset\r\n\r\n- Open-world: annotating all objects in each video, 13.5 objects per video on average\r\n\r\n- Diverse object categories: 57% of objects are not covered by COCO categories","description_withheld":null,"homepage":"https://sites.google.com/view/unidentified-video-object/home?authuser=0","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/unidentified-video-objects-a-benchmark-for","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","first_author":"Weiyao Wang","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"Object Localization","url":"/task/object-localization","datasets_with_task":"/datasets/task/object-localization"},{"name":"Unsupervised Object Detection","url":"/task/unsupervised-object-detection","datasets_with_task":"/datasets/task/unsupervised-object-detection"},{"name":"Video Instance Segmentation","url":"/task/video-instance-segmentation","datasets_with_task":"/datasets/task/video-instance-segmentation"},{"name":"Open World Object Detection","url":"/task/open-world-object-detection","datasets_with_task":"/datasets/task/open-world-object-detection"},{"name":"Unsupervised Instance Segmentation","url":"/task/unsupervised-instance-segmentation","datasets_with_task":"/datasets/task/unsupervised-instance-segmentation"},{"name":"Open-World Instance Segmentation","url":"/task/open-world-instance-segmentation","datasets_with_task":"/datasets/task/open-world-instance-segmentation"},{"name":"Object Discovery","url":"/task/object-discovery","datasets_with_task":"/datasets/task/object-discovery"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["UVO"],"data_loaders":[{"repo":"https://github.com/dulucas/uvo_challenge","url":"https://github.com/dulucas/uvo_challenge","frameworks":["pytorch"]}],"num_papers_in_archive":27,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-world-instance-segmentation-on-uvo","task":"Open-World Instance Segmentation","dataset_variant":"UVO","rows":2,"metrics":["ARmask"],"first_row_in_archive_order":{"model":"GLEE-Pro","paper":"/paper/general-object-foundation-model-for-images","metrics":{"ARmask":"72.6"},"code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-instance-segmentation-on-uvo","task":"Unsupervised Instance Segmentation","dataset_variant":"UVO","rows":1,"metrics":["AP","AP50","AP75"],"first_row_in_archive_order":{"model":"CutLER (Cascade+DINO)","paper":"/paper/cut-and-learn-for-unsupervised-object","metrics":{"AP":"10.1","AP50":"22.8","AP75":"8"},"code_links":[{"title":"facebookresearch/cutler","url":"https://github.com/facebookresearch/cutler"},{"title":"u2seg/u2seg","url":"https://github.com/u2seg/u2seg"}]},"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":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}}}},{"paper":"/paper/open-vocabulary-panoptic-segmentation-with-1","slug":"open-vocabulary-panoptic-segmentation-with-1","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","date":"2023-03-08","arxiv_id":"2303.04803","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cut-and-learn-for-unsupervised-object","slug":"cut-and-learn-for-unsupervised-object","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","date":"2023-01-26","arxiv_id":"2301.11320","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}}}},{"paper":"/paper/open-vocabulary-panoptic-segmentation-with-1","slug":"open-vocabulary-panoptic-segmentation-with-1","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","date":"2023-03-08","arxiv_id":"2303.04803","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cut-and-learn-for-unsupervised-object","slug":"cut-and-learn-for-unsupervised-object","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","date":"2023-01-26","arxiv_id":"2301.11320","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/uvo/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/uvo/papers/ran/1","json":"/dataset/uvo/papers/ran/1.json","rows":1}],"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":1,"samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"ac8aecd16919b99960ba73e0f194487b1c66db83efa26aef9d32f68da5e79c88","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}