{"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/mose","name":"MOSE","full_name":"Complex Video Object Segmentation","description_markdown":"**CoMplex video Object SEgmentation (MOSE)** is a dataset to study the tracking and segmenting objects in complex environments. MOSE contains 2,149 video clips and 5,200 objects from 36 categories, with 431,725 high-quality object segmentation masks. The most notable feature of MOSE dataset is complex scenes with crowded and occluded objects.\r\n\r\nSource: [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://arxiv.org/pdf/2302.01872.pdf)","description_withheld":null,"homepage":"https://henghuiding.github.io/MOSE","introduced_date":"2023-02-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/mose-a-new-dataset-for-video-object","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","first_author":"Henghui Ding","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Object Segmentation","url":"/task/video-object-segmentation","datasets_with_task":"/datasets/task/video-object-segmentation"},{"name":"Semi-Supervised Video Object Segmentation","url":"/task/semi-supervised-video-object-segmentation","datasets_with_task":"/datasets/task/semi-supervised-video-object-segmentation"},{"name":"Unsupervised Video Object Segmentation","url":"/task/unsupervised-video-object-segmentation","datasets_with_task":"/datasets/task/unsupervised-video-object-segmentation"},{"name":"Video Semantic Segmentation","url":"/task/video-semantic-segmentation","datasets_with_task":"/datasets/task/video-semantic-segmentation"},{"name":"Interactive Video Object Segmentation","url":"/task/interactive-video-object-segmentation","datasets_with_task":"/datasets/task/interactive-video-object-segmentation"}],"languages":[],"variants":["MOSE"],"data_loaders":[{"repo":"https://github.com/henghuiding/MOSE-api","url":"https://github.com/henghuiding/MOSE-api","frameworks":["pytorch"]}],"num_papers_in_archive":49,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-21","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"MOSE","rows":17,"metrics":["J&F","J","F","FPS"],"first_row_in_archive_order":{"model":"SAM2","paper":"/paper/2408-00714","metrics":{"J&F":"77.9"},"code_links":[{"title":"facebookresearch/segment-anything","url":"https://github.com/facebookresearch/segment-anything"},{"title":"facebookresearch/sam2","url":"https://github.com/facebookresearch/sam2"},{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"ibaiGorordo/ONNX-SAM2-Segment-Anything","url":"https://github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything"},{"title":"bowang-lab/medsam2","url":"https://github.com/bowang-lab/medsam2"},{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"},{"title":"louisfinner/him2sam","url":"https://github.com/louisfinner/him2sam"},{"title":"MindCode-4/code-4","url":"https://github.com/MindCode-4/code-4/tree/main/sam"},{"title":"dcnieho/segment-anything-2","url":"https://github.com/dcnieho/segment-anything-2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/SAM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-object-segmentation-on-mose","task":"Video Object Segmentation","dataset_variant":"MOSE","rows":1,"metrics":["J&F"],"first_row_in_archive_order":{"model":"Cutie","paper":"/paper/putting-the-object-back-into-video-object","metrics":{"J&F":"68.3"},"code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}]},"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":9,"of":9,"counts":{"papers_with_a_benchmark_row":9,"with_a_code_link":9,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/2408-00714","slug":"2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":49,"samples_ran":40,"samples_constructed":9,"samples_ran_checked":29,"samples_ran_instrument_failed":11,"samples_unverified":9,"pointer_only_for_licence":8,"official":{"repos":["facebookresearch/sam2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2408-00714#ran","syntology_url":"https://syntology.ai/paper/2408.00714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00714"}}}},{"paper":"/paper/putting-the-object-back-into-video-object","slug":"putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","arxiv_id":"2310.12982","rows_on_this_dataset":9,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/Cutie"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/putting-the-object-back-into-video-object#ran","syntology_url":"https://syntology.ai/paper/2310.12982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12982"}}}},{"paper":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":10,"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}}}},{"paper":"/paper/decoupling-features-in-hierarchical","slug":"decoupling-features-in-hierarchical","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","date":"2022-10-18","arxiv_id":"2210.09782","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/swem-towards-real-time-video-object-1","slug":"swem-towards-real-time-video-object-1","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","date":"2022-08-22","arxiv_id":"2208.10128","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/xmem-long-term-video-object-segmentation-with","slug":"xmem-long-term-video-object-segmentation-with","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","date":"2022-07-14","arxiv_id":"2207.07115","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/XMem"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xmem-long-term-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2207.07115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07115"}}}},{"paper":"/paper/recurrent-dynamic-embedding-for-video-object","slug":"recurrent-dynamic-embedding-for-video-object","title":"Recurrent Dynamic Embedding for Video Object Segmentation","date":"2022-05-08","arxiv_id":"2205.03761","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-space-time-networks-with-improved","slug":"rethinking-space-time-networks-with-improved","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","date":"2021-06-09","arxiv_id":"2106.05210","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":6,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/STCN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-space-time-networks-with-improved#ran","syntology_url":"https://syntology.ai/paper/2106.05210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05210"}}}},{"paper":"/paper/associating-objects-with-transformers-for","slug":"associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","date":"2021-06-04","arxiv_id":"2106.02638","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/2408-00714","slug":"2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":49,"samples_ran":40,"samples_constructed":9,"samples_ran_checked":29,"samples_ran_instrument_failed":11,"samples_unverified":9,"pointer_only_for_licence":8,"official":{"repos":["facebookresearch/sam2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2408-00714#ran","syntology_url":"https://syntology.ai/paper/2408.00714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00714"}}}},{"paper":"/paper/putting-the-object-back-into-video-object","slug":"putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","arxiv_id":"2310.12982","rows_on_this_dataset":9,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/Cutie"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/putting-the-object-back-into-video-object#ran","syntology_url":"https://syntology.ai/paper/2310.12982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12982"}}}},{"paper":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":10,"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}}}},{"paper":"/paper/decoupling-features-in-hierarchical","slug":"decoupling-features-in-hierarchical","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","date":"2022-10-18","arxiv_id":"2210.09782","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/swem-towards-real-time-video-object-1","slug":"swem-towards-real-time-video-object-1","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","date":"2022-08-22","arxiv_id":"2208.10128","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/xmem-long-term-video-object-segmentation-with","slug":"xmem-long-term-video-object-segmentation-with","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","date":"2022-07-14","arxiv_id":"2207.07115","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/XMem"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xmem-long-term-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2207.07115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07115"}}}},{"paper":"/paper/recurrent-dynamic-embedding-for-video-object","slug":"recurrent-dynamic-embedding-for-video-object","title":"Recurrent Dynamic Embedding for Video Object Segmentation","date":"2022-05-08","arxiv_id":"2205.03761","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-space-time-networks-with-improved","slug":"rethinking-space-time-networks-with-improved","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","date":"2021-06-09","arxiv_id":"2106.05210","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":6,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/STCN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-space-time-networks-with-improved#ran","syntology_url":"https://syntology.ai/paper/2106.05210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05210"}}}},{"paper":"/paper/associating-objects-with-transformers-for","slug":"associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","date":"2021-06-04","arxiv_id":"2106.02638","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/mose/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/mose/papers/ran/1","json":"/dataset/mose/papers/ran/1.json","rows":5}],"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":5,"samples_harvested":77,"samples_ran":57,"samples_constructed":15,"samples_ran_checked":45,"samples_ran_instrument_failed":12,"samples_unverified":20,"pointer_only_for_licence":22,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":1,"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":"ff6fd39f077d7b3bded9f03d6102ed2d24220f9a5cf536136343a1d14ea88b23","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}