{"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/mevis","name":"MeViS","full_name":"Motion expressions Video Segmentation","description_markdown":"MeViS is a large-scale dataset for motion expressions guided video segmentation, which focuses on segmenting objects in video content based on a sentence describing the motion of the objects. The dataset contains numerous motion expressions to indicate target objects in complex environments.","description_withheld":null,"homepage":"https://henghuiding.github.io/MeViS/","introduced_date":"2023-08-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","first_author":"Henghui Ding","url":null},"license":null,"modalities":[],"tasks":[{"name":"Referring Video Object Segmentation","url":"/task/referring-video-object-segmentation","datasets_with_task":"/datasets/task/referring-video-object-segmentation"}],"languages":[],"variants":["MeViS"],"data_loaders":[],"num_papers_in_archive":46,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/referring-video-object-segmentation-on-mevis","task":"Referring Video Object Segmentation","dataset_variant":"MeViS","rows":16,"metrics":["J&F","J","F"],"first_row_in_archive_order":{"model":"MPG-SAM 2","paper":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","metrics":{"F":"56.7","J":"50.7","J&F":"53.7"},"code_links":[{"title":"rongfu-dsb/MPG-SAM2","url":"https://github.com/rongfu-dsb/MPG-SAM2"}]},"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":16,"of":16,"counts":{"papers_with_a_benchmark_row":16,"with_a_code_link":15,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":16,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":8,"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/glus-global-local-reasoning-unified-into-a","slug":"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","arxiv_id":"2504.07962","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":12,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glus-global-local-reasoning-unified-into-a#ran","syntology_url":"https://syntology.ai/paper/2504.07962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07962"}}}},{"paper":"/paper/find-first-track-next-decoupling","slug":"find-first-track-next-decoupling","title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","date":"2025-03-05","arxiv_id":"2503.03492","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/referdino-referring-video-object-segmentation","slug":"referdino-referring-video-object-segmentation","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","date":"2025-01-24","arxiv_id":"2501.14607","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","slug":"mpg-sam-2-adapting-sam-2-with-mask-priors-and","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","date":"2025-01-23","arxiv_id":"2501.13667","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":1,"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}}}},{"paper":"/paper/internvideo2-5-empowering-video-mllms-with","slug":"internvideo2-5-empowering-video-mllms-with","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","date":"2025-01-21","arxiv_id":"2501.12386","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-context-temporal-consistent-modeling","slug":"multi-context-temporal-consistent-modeling","title":"Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation","date":"2025-01-09","arxiv_id":"2501.04939","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/samwise-infusing-wisdom-in-sam2-for-text","slug":"samwise-infusing-wisdom-in-sam2-for-text","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","date":"2024-11-26","arxiv_id":"2411.17646","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decoupling-static-and-hierarchical-motion","slug":"decoupling-static-and-hierarchical-motion","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","date":"2024-04-04","arxiv_id":"2404.03645","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["heshuting555/dshmp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/decoupling-static-and-hierarchical-motion#ran","syntology_url":"https://syntology.ai/paper/2404.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03645"}}}},{"paper":"/paper/towards-temporally-consistent-referring-video","slug":"towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","arxiv_id":"2403.19407","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":10,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-temporally-consistent-referring-video#ran","syntology_url":"https://syntology.ai/paper/2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}}}},{"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/vlt-vision-language-transformer-and-query","slug":"vlt-vision-language-transformer-and-query","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2022-10-28","arxiv_id":"2210.15871","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["henghuiding/Vision-Language-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlt-vision-language-transformer-and-query#ran","syntology_url":"https://syntology.ai/paper/2210.15871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15871"}}}},{"paper":"/paper/language-bridged-spatial-temporal-interaction-1","slug":"language-bridged-spatial-temporal-interaction-1","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","date":"2022-06-08","arxiv_id":"2206.03789","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["dzh19990407/lbdt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"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/language-bridged-spatial-temporal-interaction-1#ran","syntology_url":"https://syntology.ai/paper/2206.03789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03789"}}}},{"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"}}}},{"paper":"/paper/urvos-unified-referring-video-object","slug":"urvos-unified-referring-video-object","title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","date":"2020-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/glus-global-local-reasoning-unified-into-a","slug":"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","arxiv_id":"2504.07962","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":12,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glus-global-local-reasoning-unified-into-a#ran","syntology_url":"https://syntology.ai/paper/2504.07962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07962"}}}},{"paper":"/paper/find-first-track-next-decoupling","slug":"find-first-track-next-decoupling","title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","date":"2025-03-05","arxiv_id":"2503.03492","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/referdino-referring-video-object-segmentation","slug":"referdino-referring-video-object-segmentation","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","date":"2025-01-24","arxiv_id":"2501.14607","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","slug":"mpg-sam-2-adapting-sam-2-with-mask-priors-and","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","date":"2025-01-23","arxiv_id":"2501.13667","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":1,"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}}}},{"paper":"/paper/internvideo2-5-empowering-video-mllms-with","slug":"internvideo2-5-empowering-video-mllms-with","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","date":"2025-01-21","arxiv_id":"2501.12386","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-context-temporal-consistent-modeling","slug":"multi-context-temporal-consistent-modeling","title":"Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation","date":"2025-01-09","arxiv_id":"2501.04939","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/samwise-infusing-wisdom-in-sam2-for-text","slug":"samwise-infusing-wisdom-in-sam2-for-text","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","date":"2024-11-26","arxiv_id":"2411.17646","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decoupling-static-and-hierarchical-motion","slug":"decoupling-static-and-hierarchical-motion","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","date":"2024-04-04","arxiv_id":"2404.03645","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["heshuting555/dshmp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/decoupling-static-and-hierarchical-motion#ran","syntology_url":"https://syntology.ai/paper/2404.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03645"}}}},{"paper":"/paper/towards-temporally-consistent-referring-video","slug":"towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","arxiv_id":"2403.19407","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":10,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-temporally-consistent-referring-video#ran","syntology_url":"https://syntology.ai/paper/2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}}}},{"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/vlt-vision-language-transformer-and-query","slug":"vlt-vision-language-transformer-and-query","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2022-10-28","arxiv_id":"2210.15871","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["henghuiding/Vision-Language-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlt-vision-language-transformer-and-query#ran","syntology_url":"https://syntology.ai/paper/2210.15871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15871"}}}},{"paper":"/paper/language-bridged-spatial-temporal-interaction-1","slug":"language-bridged-spatial-temporal-interaction-1","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","date":"2022-06-08","arxiv_id":"2206.03789","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["dzh19990407/lbdt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"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/language-bridged-spatial-temporal-interaction-1#ran","syntology_url":"https://syntology.ai/paper/2206.03789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03789"}}}},{"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"}}}},{"paper":"/paper/urvos-unified-referring-video-object","slug":"urvos-unified-referring-video-object","title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","date":"2020-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/dataset/mevis/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/mevis/papers/ran/1","json":"/dataset/mevis/papers/ran/1.json","rows":9}],"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":9,"samples_harvested":88,"samples_ran":62,"samples_constructed":6,"samples_ran_checked":29,"samples_ran_instrument_failed":33,"samples_unverified":26,"pointer_only_for_licence":38,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":9,"papers_with_a_run_with_no_instrument_failure":8,"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":3,"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-mevis","since_archive":"/sota/referring-video-object-segmentation-on-mevis#since-judged","papers_judged":3,"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":"e2cb227747d03fb9f68c25c9ff2fd37f752a91683f7d3f4eb2d624e186db659b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}