{"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":"/task/video-object-segmentation","name":"Video Object Segmentation","slug":"video-object-segmentation","description_markdown":"Video object segmentation is a binary labeling problem aiming to separate foreground object(s) from the background region of a video.\r\n\r\nFor leaderboards please refer to the different subtasks.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":551,"papers_with_code":294,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":19,"subtasks":7,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-object-segmentation-on-davis-2016","slug":"video-object-segmentation-on-davis-2016","dataset":"DAVIS 2016","dataset_url":"/dataset/davis-2016","rows_in_archive":24,"metrics":["J&F","F-Score","Jaccard (Mean)","mIoU","Contour Accuracy"],"first_row_in_archive_order":{"model":"ISVOS (BL30K, MS)","paper_title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","paper_url":"/paper/look-before-you-match-instance-understanding","paper_date":"2022-12-13","arxiv_id":"2212.06826","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017-val","slug":"video-object-segmentation-on-davis-2017-val","dataset":"DAVIS 2017 (val)","dataset_url":"/dataset/davis-2017","rows_in_archive":17,"metrics":["Mean Jaccard & F-Measure","F-measure","Jaccard"],"first_row_in_archive_order":{"model":"XMem (BLK30K, MS)","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_url":"/paper/xmem-long-term-video-object-segmentation-with","paper_date":"2022-07-14","arxiv_id":"2207.07115","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos-1","slug":"video-object-segmentation-on-youtube-vos-1","dataset":"YouTube-VOS 2018","dataset_url":"/dataset/youtube-vos","rows_in_archive":17,"metrics":["Mean Jaccard & F-Measure","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)"],"first_row_in_archive_order":{"model":"XMem (BL30K, MS)","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_url":"/paper/xmem-long-term-video-object-segmentation-with","paper_date":"2022-07-14","arxiv_id":"2207.07115","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017-test-1","slug":"video-object-segmentation-on-davis-2017-test-1","dataset":"DAVIS 2017 (test-dev)","dataset_url":"/dataset/davis-2017","rows_in_archive":10,"metrics":["Jaccard","F-measure","Mean Jaccard & F-Measure"],"first_row_in_archive_order":{"model":"BATMAN","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","paper_url":"/paper/batman-bilateral-attention-transformer-in","paper_date":"2022-08-01","arxiv_id":"2208.01159","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos-2019-2","slug":"video-object-segmentation-on-youtube-vos-2019-2","dataset":"YouTube-VOS 2019","dataset_url":"/dataset/youtube-vos","rows_in_archive":10,"metrics":["Mean Jaccard & F-Measure","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)"],"first_row_in_archive_order":{"model":"XMem (BL30K,MS)","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_url":"/paper/xmem-long-term-video-object-segmentation-with","paper_date":"2022-07-14","arxiv_id":"2207.07115","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017","slug":"video-object-segmentation-on-davis-2017","dataset":"DAVIS 2017","dataset_url":"/dataset/davis-2017","rows_in_archive":5,"metrics":["Jaccard (Mean)","mIoU","J&F","F-Score"],"first_row_in_archive_order":{"model":"AOC-MF (val)","paper_title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","paper_url":"/paper/towards-robust-video-object-segmentation-with","paper_date":"2022-07-02","arxiv_id":"2207.00887","code_links":[{"title":"jerryx1110/robust-video-object-segmentation","url":"https://github.com/jerryx1110/robust-video-object-segmentation"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-robust-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2207.00887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00887"}},"official":{"repos":["jerryx1110/robust-video-object-segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-object-segmentation-on-m-3-vos","slug":"video-object-segmentation-on-m-3-vos","dataset":"M$^3$-VOS","dataset_url":"/dataset/m-3-vos","rows_in_archive":4,"metrics":["Average IOU"],"first_row_in_archive_order":{"model":"ReVOS","paper_title":"M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","paper_url":"/paper/m-3-vos-multi-phase-multi-transition-and-1","paper_date":"2025-06-15","arxiv_id":null,"code_links":[{"title":"zixuan-chen/M3VOS_Experiment","url":"https://github.com/zixuan-chen/M3VOS_Experiment"}],"syntology":null}},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017-test","slug":"video-object-segmentation-on-davis-2017-test","dataset":"DAVIS-2017 (test-dev)","dataset_url":null,"rows_in_archive":2,"metrics":["Mean Jaccard & F-Measure","Jaccard","F-measure"],"first_row_in_archive_order":{"model":"XMem (BL30K, MS)","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","paper_url":"/paper/xmem-long-term-video-object-segmentation-with","paper_date":"2022-07-14","arxiv_id":"2207.07115","code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}],"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/video-object-segmentation-on-fbms","slug":"video-object-segmentation-on-fbms","dataset":"FBMS","dataset_url":"/dataset/fbms","rows_in_archive":2,"metrics":["F-Score","Jaccard (Mean)"],"first_row_in_archive_order":{"model":"DFNet","paper_title":"Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation","paper_url":"/paper/learning-discriminative-feature-with-crf-for","paper_date":"2020-08-04","arxiv_id":"2008.01270","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-object-segmentation-on-youtube-1","slug":"video-object-segmentation-on-youtube-1","dataset":"YouTube","dataset_url":null,"rows_in_archive":2,"metrics":["Average","mIoU"],"first_row_in_archive_order":{"model":"Ours","paper_title":"Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation","paper_url":"/paper/multi-source-fusion-and-automatic-predictor","paper_date":"2021-08-11","arxiv_id":"2108.05076","code_links":[{"title":"xiaoqi-zhao-dlut/multi-source-aps-zvos","url":"https://github.com/xiaoqi-zhao-dlut/multi-source-aps-zvos"}],"syntology":null}},{"leaderboard":"/sota/video-object-segmentation-on-fbms-59","slug":"video-object-segmentation-on-fbms-59","dataset":"FBMS-59","dataset_url":"/dataset/fbms-59","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"LOCATE","paper_title":"LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training","paper_url":"/paper/locate-self-supervised-object-discovery-via","paper_date":"2023-08-22","arxiv_id":"2308.11239","code_links":[{"title":"silky1708/locate","url":"https://github.com/silky1708/locate"}],"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/locate-self-supervised-object-discovery-via#ran","syntology_url":"https://syntology.ai/paper/2308.11239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11239"}},"official":{"repos":["silky1708/locate"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-object-segmentation-on-mose","slug":"video-object-segmentation-on-mose","dataset":"MOSE","dataset_url":"/dataset/mose","rows_in_archive":1,"metrics":["J&F"],"first_row_in_archive_order":{"model":"Cutie","paper_title":"Putting the Object Back into Video Object Segmentation","paper_url":"/paper/putting-the-object-back-into-video-object","paper_date":"2023-10-19","arxiv_id":"2310.12982","code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}],"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/video-object-segmentation-on-segtrack-v2-1","slug":"video-object-segmentation-on-segtrack-v2-1","dataset":"SegTrack-v2","dataset_url":"/dataset/segtrack-v2-1","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"LOCATE","paper_title":"LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training","paper_url":"/paper/locate-self-supervised-object-discovery-via","paper_date":"2023-08-22","arxiv_id":"2308.11239","code_links":[{"title":"silky1708/locate","url":"https://github.com/silky1708/locate"}],"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/locate-self-supervised-object-discovery-via#ran","syntology_url":"https://syntology.ai/paper/2308.11239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11239"}},"official":{"repos":["silky1708/locate"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/davis","name":"DAVIS","full_name":"Densely Annotated VIdeo Segmentation","num_papers_in_archive":734},{"url":"/dataset/davis-2017","name":"DAVIS 2017","full_name":"DAVIS 2017","num_papers_in_archive":308},{"url":"/dataset/davis-2016","name":"DAVIS 2016","full_name":"DAVIS 2016","num_papers_in_archive":231},{"url":"/dataset/youtube-vos","name":"YouTube-VOS 2018","full_name":"Youtube Video Object Segmentation","num_papers_in_archive":203},{"url":"/dataset/fbms","name":"FBMS","full_name":"Freiburg-Berkeley Motion Segmentation","num_papers_in_archive":126},{"url":"/dataset/segtrack-v2-1","name":"SegTrack-v2","full_name":"","num_papers_in_archive":107},{"url":"/dataset/referring-expressions-for-davis-2016-2017","name":"Referring Expressions for DAVIS 2016 & 2017","full_name":"","num_papers_in_archive":82},{"url":"/dataset/mose","name":"MOSE","full_name":"Complex Video Object Segmentation","num_papers_in_archive":49},{"url":"/dataset/avsbench","name":"AVSBench","full_name":"Audio −Visual Segmentation","num_papers_in_archive":20},{"url":"/dataset/fbms-59","name":"FBMS-59","full_name":"Freiburg-Berkeley Motion Segmentation","num_papers_in_archive":19},{"url":"/dataset/lvos","name":"LVOS","full_name":"","num_papers_in_archive":19},{"url":"/dataset/bl30k","name":"BL30K","full_name":"","num_papers_in_archive":11},{"url":"/dataset/vost","name":"VOST","full_name":"","num_papers_in_archive":11},{"url":"/dataset/armbench","name":"ARMBench","full_name":"","num_papers_in_archive":4},{"url":"/dataset/m-3-vos","name":"M$^3$-VOS","full_name":"M$^3$-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","num_papers_in_archive":4},{"url":"/dataset/odms","name":"ODMS","full_name":"Object Depth via Motion and Segmentation","num_papers_in_archive":2},{"url":"/dataset/pumavos","name":"PUMaVOS","full_name":"Partial and Unusual Masks for Video Object Segmentation","num_papers_in_archive":2},{"url":"/dataset/visor","name":"VISOR - Semi supervised video object segmentation","full_name":"val","num_papers_in_archive":1},{"url":"/dataset/infinity-spills-basic-dataset","name":"Infinity Spills Basic Dataset","full_name":"Infinity Spills Basic Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/interactive-video-object-segmentation","name":"Interactive Video Object Segmentation"},{"url":"/task/long-tail-video-object-segmentation","name":"Long-tail Video Object Segmentation"},{"url":"/task/referring-video-object-segmentation","name":"Referring Video Object Segmentation"},{"url":"/task/semi-supervised-video-object-segmentation","name":"Semi-Supervised Video Object Segmentation"},{"url":"/task/unsupervised-video-object-segmentation","name":"Unsupervised Video Object Segmentation"},{"url":"/task/video-salient-object-detection","name":"Video Salient Object Detection"},{"url":"/task/video-shadow-detection","name":"Video Shadow Detection"}],"parent_tasks":[{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":6,"rows_per_page":100,"shown":100,"of":551,"of_with_code":294,"tagged_in_all":551,"counts":{"archive_papers_tagged":551,"with_a_code_link":294,"where_syntology_ran_a_sample":95,"not_listed_spam_title":0,"listed":551,"listed_where_code_ran":95,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":81,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":81,"listed_every_run_a_failure_of_syntologys_instrument":14,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/emerging-properties-in-self-supervised-vision","slug":"emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","arxiv_id":"2104.14294","repositories_listed":32,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/emerging-properties-in-self-supervised-vision#ran","syntology_url":"https://syntology.ai/paper/2104.14294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14294"}},"official":{"repos":["facebookresearch/dino"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/2408-00714","slug":"2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","repositories_listed":11,"syntology":{"n":49,"n_ran":40,"n_constructed":9,"n_ran_checked":29,"n_instrument":11,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":27,"n_pointer_only":8,"phrase":"40 ran (of which 9 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 0 violated, 27 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/2408-00714#ran","syntology_url":"https://syntology.ai/paper/2408.00714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00714"}},"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"]}}},{"url":"/paper/one-shot-video-object-segmentation","slug":"one-shot-video-object-segmentation","title":"One-Shot Video Object Segmentation","date":"2016-11-16","arxiv_id":"1611.05198","repositories_listed":8,"syntology":null},{"url":"/paper/rethinking-self-supervised-correspondence","slug":"rethinking-self-supervised-correspondence","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective","date":"2021-03-31","arxiv_id":"2103.17263","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-self-supervised-correspondence#ran","syntology_url":"https://syntology.ai/paper/2103.17263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.17263"}},"official":{"repos":["xvjiarui/VFS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modular-interactive-video-object-segmentation","slug":"modular-interactive-video-object-segmentation","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","date":"2021-03-14","arxiv_id":"2103.07941","repositories_listed":5,"syntology":{"n":18,"n_ran":10,"n_constructed":3,"n_ran_checked":5,"n_instrument":5,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/modular-interactive-video-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.07941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07941"}},"official":{"repos":["hkchengrex/MiVOS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/premvos-proposal-generation-refinement-and","slug":"premvos-proposal-generation-refinement-and","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","date":"2018-07-24","arxiv_id":"1807.09190","repositories_listed":5,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/premvos-proposal-generation-refinement-and#ran","syntology_url":"https://syntology.ai/paper/1807.09190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09190"}},"official":null}},{"url":"/paper/video-polyp-segmentation-a-deep-learning","slug":"video-polyp-segmentation-a-deep-learning","title":"Video Polyp Segmentation: A Deep Learning Perspective","date":"2022-03-27","arxiv_id":"2203.14291","repositories_listed":4,"syntology":{"n":8,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/video-polyp-segmentation-a-deep-learning#ran","syntology_url":"https://syntology.ai/paper/2203.14291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14291"}},"official":{"repos":["DengPingFan/PraNet","GewelsJI/PNS-Net","gewelsji/vps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/make-one-shot-video-object-segmentation-1","slug":"make-one-shot-video-object-segmentation-1","title":"Make One-Shot Video Object Segmentation Efficient Again","date":"2020-12-03","arxiv_id":"2012.01866","repositories_listed":4,"syntology":null},{"url":"/paper/interactive-video-object-segmentation-using","slug":"interactive-video-object-segmentation-using","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","date":"2020-07-16","arxiv_id":"2007.08139","repositories_listed":4,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/interactive-video-object-segmentation-using#ran","syntology_url":"https://syntology.ai/paper/2007.08139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08139"}},"official":{"repos":["yuk6heo/IVOS-ATNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/youtube-vos-sequence-to-sequence-video-object","slug":"youtube-vos-sequence-to-sequence-video-object","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","date":"2018-09-03","arxiv_id":"1809.00461","repositories_listed":4,"syntology":null},{"url":"/paper/lucid-data-dreaming-for-video-object","slug":"lucid-data-dreaming-for-video-object","title":"Lucid Data Dreaming for Video Object Segmentation","date":"2017-03-28","arxiv_id":"1703.09554","repositories_listed":4,"syntology":null},{"url":"/paper/segment-everything-everywhere-all-at-once","slug":"segment-everything-everywhere-all-at-once","title":"Segment Everything Everywhere All at Once","date":"2023-04-13","arxiv_id":"2304.06718","repositories_listed":3,"syntology":null},{"url":"/paper/seggpt-segmenting-everything-in-context","slug":"seggpt-segmenting-everything-in-context","title":"SegGPT: Segmenting Everything In Context","date":"2023-04-06","arxiv_id":"2304.03284","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seggpt-segmenting-everything-in-context#ran","syntology_url":"https://syntology.ai/paper/2304.03284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03284"}},"official":{"repos":["baaivision/painter"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/epic-kitchens-visor-benchmark-video","slug":"epic-kitchens-visor-benchmark-video","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","date":"2022-09-26","arxiv_id":"2209.13064","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/epic-kitchens-visor-benchmark-video#ran","syntology_url":"https://syntology.ai/paper/2209.13064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.13064"}},"official":{"repos":["epic-kitchens/visor-hos","epic-kitchens/visor-vos","epic-kitchens/visor-wdtcf"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","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"}},"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"]}}},{"url":"/paper/physarum-powered-differentiable-linear","slug":"physarum-powered-differentiable-linear","title":"Physarum Powered Differentiable Linear Programming Layers and Applications","date":"2020-04-30","arxiv_id":"2004.14539","repositories_listed":3,"syntology":null},{"url":"/paper/exploiting-geometric-constraints-on-dense","slug":"exploiting-geometric-constraints-on-dense","title":"EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency","date":"2019-09-29","arxiv_id":"1909.13258","repositories_listed":3,"syntology":null},{"url":"/paper/video-object-segmentation-using-space-time","slug":"video-object-segmentation-using-space-time","title":"Video Object Segmentation using Space-Time Memory Networks","date":"2019-04-01","arxiv_id":"1904.00607","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-object-segmentation-using-space-time#ran","syntology_url":"https://syntology.ai/paper/1904.00607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00607"}},"official":null}},{"url":"/paper/feelvos-fast-end-to-end-embedding-learning","slug":"feelvos-fast-end-to-end-embedding-learning","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","date":"2019-02-25","arxiv_id":"1902.09513","repositories_listed":3,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/feelvos-fast-end-to-end-embedding-learning#ran","syntology_url":"https://syntology.ai/paper/1902.09513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09513"}},"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fast-online-object-tracking-and-segmentation","slug":"fast-online-object-tracking-and-segmentation","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","date":"2018-12-12","arxiv_id":"1812.05050","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fast-online-object-tracking-and-segmentation#ran","syntology_url":"https://syntology.ai/paper/1812.05050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05050"}},"official":null}},{"url":"/paper/video-object-segmentation-with-re","slug":"video-object-segmentation-with-re","title":"Video Object Segmentation with Re-identification","date":"2017-08-01","arxiv_id":"1708.00197","repositories_listed":3,"syntology":null},{"url":"/paper/accelerating-volumetric-medical-image","slug":"accelerating-volumetric-medical-image","title":"Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2","date":"2025-05-03","arxiv_id":"2505.01854","repositories_listed":2,"syntology":null},{"url":"/paper/stable-mean-teacher-for-semi-supervised-video","slug":"stable-mean-teacher-for-semi-supervised-video","title":"Stable Mean Teacher for Semi-supervised Video Action Detection","date":"2024-12-10","arxiv_id":"2412.07072","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/stable-mean-teacher-for-semi-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2412.07072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07072"}},"official":{"repos":["AKASH2907/stable-mean-teacher","akash2907/stable_mean_teacher"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/pvuw-2024-challenge-on-complex-video","slug":"pvuw-2024-challenge-on-complex-video","title":"PVUW 2024 Challenge on Complex Video Understanding: Methods and Results","date":"2024-06-24","arxiv_id":"2406.17005","repositories_listed":2,"syntology":null},{"url":"/paper/uniref-segment-every-reference-object-in","slug":"uniref-segment-every-reference-object-in","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","date":"2023-12-25","arxiv_id":"2312.15715","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniref-segment-every-reference-object-in#ran","syntology_url":"https://syntology.ai/paper/2312.15715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15715"}},"official":{"repos":["foundationvision/uniref"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/xmem-production-level-video-segmentation-from","slug":"xmem-production-level-video-segmentation-from","title":"XMem++: Production-level Video Segmentation From Few Annotated Frames","date":"2023-07-29","arxiv_id":"2307.15958","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/xmem-production-level-video-segmentation-from#ran","syntology_url":"https://syntology.ai/paper/2307.15958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15958"}},"official":{"repos":["max810/XMem2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/online-unsupervised-video-object-segmentation","slug":"online-unsupervised-video-object-segmentation","title":"Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering","date":"2023-06-21","arxiv_id":"2306.12048","repositories_listed":2,"syntology":null},{"url":"/paper/video-object-segmentation-in-panoptic-wild","slug":"video-object-segmentation-in-panoptic-wild","title":"Video Object Segmentation in Panoptic Wild Scenes","date":"2023-05-08","arxiv_id":"2305.04470","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-object-segmentation-in-panoptic-wild#ran","syntology_url":"https://syntology.ai/paper/2305.04470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04470"}},"official":{"repos":["yoxu515/viposeg-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dsec-mos-segment-any-moving-object-with","slug":"dsec-mos-segment-any-moving-object-with","title":"Event-Free Moving Object Segmentation from Moving Ego Vehicle","date":"2023-04-28","arxiv_id":"2305.00126","repositories_listed":2,"syntology":null},{"url":"/paper/croc-cross-view-online-clustering-for-dense","slug":"croc-cross-view-online-clustering-for-dense","title":"CrOC: Cross-View Online Clustering for Dense Visual Representation Learning","date":"2023-03-23","arxiv_id":"2303.13245","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/croc-cross-view-online-clustering-for-dense#ran","syntology_url":"https://syntology.ai/paper/2303.13245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13245"}},"official":{"repos":["stegmuel/croc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/treating-motion-as-option-to-reduce-motion","slug":"treating-motion-as-option-to-reduce-motion","title":"Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation","date":"2022-09-04","arxiv_id":"2209.03138","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/treating-motion-as-option-to-reduce-motion#ran","syntology_url":"https://syntology.ai/paper/2209.03138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03138"}},"official":{"repos":["suhwan-cho/tmo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/in-defense-of-online-models-for-video","slug":"in-defense-of-online-models-for-video","title":"In Defense of Online Models for Video Instance Segmentation","date":"2022-07-21","arxiv_id":"2207.10661","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in-defense-of-online-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2207.10661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10661"}},"official":{"repos":["wjf5203/vnext"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/associating-objects-with-scalable","slug":"associating-objects-with-scalable","title":"Scalable Video Object Segmentation with Identification Mechanism","date":"2022-03-22","arxiv_id":"2203.11442","repositories_listed":2,"syntology":null},{"url":"/paper/robust-visual-tracking-by-segmentation","slug":"robust-visual-tracking-by-segmentation","title":"Robust Visual Tracking by Segmentation","date":"2022-03-21","arxiv_id":"2203.11191","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/d2conv3d-dynamic-dilated-convolutions-for","slug":"d2conv3d-dynamic-dilated-convolutions-for","title":"D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos","date":"2021-11-15","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/efficient-video-object-segmentation-with","slug":"efficient-video-object-segmentation-with","title":"Accelerating Video Object Segmentation with Compressed Video","date":"2021-07-26","arxiv_id":"2107.12192","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/efficient-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2107.12192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12192"}},"official":{"repos":["kai422/covos"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/synthref-generation-of-synthetic-referring","slug":"synthref-generation-of-synthetic-referring","title":"SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation","date":"2021-06-08","arxiv_id":"2106.04403","repositories_listed":2,"syntology":null},{"url":"/paper/vitae-vision-transformer-advanced-by","slug":"vitae-vision-transformer-advanced-by","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","date":"2021-06-07","arxiv_id":"2106.03348","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vitae-vision-transformer-advanced-by#ran","syntology_url":"https://syntology.ai/paper/2106.03348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03348"}},"official":{"repos":["Annbless/ViTAE"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/refvos-a-closer-look-at-referring-expressions","slug":"refvos-a-closer-look-at-referring-expressions","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","date":"2020-10-01","arxiv_id":"2010.00263","repositories_listed":2,"syntology":null},{"url":"/paper/learning-object-depth-from-camera-motion-and","slug":"learning-object-depth-from-camera-motion-and","title":"Learning Object Depth from Camera Motion and Video Object Segmentation","date":"2020-07-11","arxiv_id":"2007.05676","repositories_listed":2,"syntology":null},{"url":"/paper/learning-what-to-learn-for-video-object","slug":"learning-what-to-learn-for-video-object","title":"Learning What to Learn for Video Object Segmentation","date":"2020-03-25","arxiv_id":"2003.11540","repositories_listed":2,"syntology":null},{"url":"/paper/collaborative-video-object-segmentation-by","slug":"collaborative-video-object-segmentation-by","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","date":"2020-03-18","arxiv_id":"2003.08333","repositories_listed":2,"syntology":null},{"url":"/paper/learning-fast-and-robust-target-models-for","slug":"learning-fast-and-robust-target-models-for","title":"Learning Fast and Robust Target Models for Video Object Segmentation","date":"2020-02-27","arxiv_id":"2003.00908","repositories_listed":2,"syntology":null},{"url":"/paper/mast-a-memory-augmented-self-supervised","slug":"mast-a-memory-augmented-self-supervised","title":"MAST: A Memory-Augmented Self-supervised Tracker","date":"2020-02-18","arxiv_id":"2002.07793","repositories_listed":2,"syntology":null},{"url":"/paper/ranet-ranking-attention-network-for-fast","slug":"ranet-ranking-attention-network-for-fast","title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","date":"2019-08-19","arxiv_id":"1908.06647","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ranet-ranking-attention-network-for-fast#ran","syntology_url":"https://syntology.ai/paper/1908.06647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06647"}},"official":{"repos":["Storife/RANet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/tukey-inspired-video-object-segmentation","slug":"tukey-inspired-video-object-segmentation","title":"Tukey-Inspired Video Object Segmentation","date":"2018-11-19","arxiv_id":"1811.07958","repositories_listed":2,"syntology":null},{"url":"/paper/fast-and-accurate-online-video-object","slug":"fast-and-accurate-online-video-object","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","date":"2018-06-06","arxiv_id":"1806.02323","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/fast-and-accurate-online-video-object#ran","syntology_url":"https://syntology.ai/paper/1806.02323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02323"}},"official":{"repos":["JingchunCheng/FAVOS"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/fast-video-object-segmentation-by-reference","slug":"fast-video-object-segmentation-by-reference","title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","date":"2018-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/deep-extreme-cut-from-extreme-points-to","slug":"deep-extreme-cut-from-extreme-points-to","title":"Deep Extreme Cut: From Extreme Points to Object Segmentation","date":"2017-11-24","arxiv_id":"1711.09081","repositories_listed":2,"syntology":null},{"url":"/paper/learning-video-object-segmentation-from","slug":"learning-video-object-segmentation-from","title":"Learning Video Object Segmentation from Static Images","date":"2016-12-08","arxiv_id":"1612.02646","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-video-object-segmentation-from#ran","syntology_url":"https://syntology.ai/paper/1612.02646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.02646"}},"official":null}},{"url":"/paper/m-3-vos-multi-phase-multi-transition-and-1","slug":"m-3-vos-multi-phase-multi-transition-and-1","title":"M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","date":"2025-06-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/videomolmo-spatio-temporal-grounding-meets","slug":"videomolmo-spatio-temporal-grounding-meets","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","date":"2025-06-05","arxiv_id":"2506.05336","repositories_listed":1,"syntology":null},{"url":"/paper/omni-r1-reinforcement-learning-for-omnimodal","slug":"omni-r1-reinforcement-learning-for-omnimodal","title":"Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration","date":"2025-05-26","arxiv_id":"2505.20256","repositories_listed":1,"syntology":null},{"url":"/paper/thinkvideo-high-quality-reasoning-video","slug":"thinkvideo-high-quality-reasoning-video","title":"ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts","date":"2025-05-24","arxiv_id":"2505.18561","repositories_listed":1,"syntology":null},{"url":"/paper/video-gpt-via-next-clip-diffusion","slug":"video-gpt-via-next-clip-diffusion","title":"Video-GPT via Next Clip Diffusion","date":"2025-05-18","arxiv_id":"2505.12489","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-referring-video-single-and-multi","slug":"few-shot-referring-video-single-and-multi","title":"Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching","date":"2025-04-18","arxiv_id":"2504.13710","repositories_listed":1,"syntology":null},{"url":"/paper/dc-sam-in-context-segment-anything-in-images","slug":"dc-sam-in-context-segment-anything-in-images","title":"DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency","date":"2025-04-16","arxiv_id":"2504.12080","repositories_listed":1,"syntology":null},{"url":"/paper/masseg-2nd-technical-report-for-4th-pvuw-mose","slug":"masseg-2nd-technical-report-for-4th-pvuw-mose","title":"MASSeg : 2nd Technical Report for 4th PVUW MOSE Track","date":"2025-04-14","arxiv_id":"2504.10254","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","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"}},"official":null}},{"url":"/paper/the-1st-solution-for-4th-pvuw-mevis-challenge","slug":"the-1st-solution-for-4th-pvuw-mevis-challenge","title":"The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation","date":"2025-04-07","arxiv_id":"2504.05178","repositories_listed":1,"syntology":null},{"url":"/paper/4th-pvuw-mevis-3rd-place-report-sa2va","slug":"4th-pvuw-mevis-3rd-place-report-sa2va","title":"4th PVUW MeViS 3rd Place Report: Sa2VA","date":"2025-04-01","arxiv_id":"2504.00476","repositories_listed":1,"syntology":null},{"url":"/paper/referdino-plus-2nd-solution-for-4th-pvuw","slug":"referdino-plus-2nd-solution-for-4th-pvuw","title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025","date":"2025-03-30","arxiv_id":"2503.23509","repositories_listed":1,"syntology":null},{"url":"/paper/one-shot-medical-video-object-segmentation","slug":"one-shot-medical-video-object-segmentation","title":"One-Shot Medical Video Object Segmentation via Temporal Contrastive Memory Networks","date":"2025-03-19","arxiv_id":"2503.14979","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-annotation-burden-exploiting-image","slug":"reducing-annotation-burden-exploiting-image","title":"Reducing Annotation Burden: Exploiting Image Knowledge for Few-Shot Medical Video Object Segmentation via Spatiotemporal Consistency Relearning","date":"2025-03-19","arxiv_id":"2503.14958","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/wandering-around-a-bioinspired-approach-to","slug":"wandering-around-a-bioinspired-approach-to","title":"Wandering around: A bioinspired approach to visual attention through object motion sensitivity","date":"2025-02-10","arxiv_id":"2502.06747","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","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"}},"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"]}}},{"url":"/paper/learning-motion-and-temporal-cues-for","slug":"learning-motion-and-temporal-cues-for","title":"Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation","date":"2025-01-14","arxiv_id":"2501.07806","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/sa2va-marrying-sam2-with-llava-for-dense","slug":"sa2va-marrying-sam2-with-llava-for-dense","title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","date":"2025-01-07","arxiv_id":"2501.04001","repositories_listed":1,"syntology":null},{"url":"/paper/dtos-dynamic-time-object-sensing-with-large","slug":"dtos-dynamic-time-object-sensing-with-large","title":"DTOS: Dynamic Time Object Sensing with Large Multimodal Model","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/m-3-vos-multi-phase-multi-transition-and","slug":"m-3-vos-multi-phase-multi-transition-and","title":"M$^3$-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","date":"2024-12-18","arxiv_id":"2412.13803","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-video-object-segmentation","slug":"multi-granularity-video-object-segmentation","title":"Multi-Granularity Video Object Segmentation","date":"2024-12-02","arxiv_id":"2412.01471","repositories_listed":1,"syntology":null},{"url":"/paper/referring-video-object-segmentation-via","slug":"referring-video-object-segmentation-via","title":"Referring Video Object Segmentation via Language-aligned Track Selection","date":"2024-12-02","arxiv_id":"2412.01136","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-track-anything","slug":"efficient-track-anything","title":"Efficient Track Anything","date":"2024-11-28","arxiv_id":"2411.18933","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-track-anything#ran","syntology_url":"https://syntology.ai/paper/2411.18933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18933"}},"official":null}},{"url":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/ikea-manuals-at-work-4d-grounding-of-assembly","slug":"ikea-manuals-at-work-4d-grounding-of-assembly","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","date":"2024-11-18","arxiv_id":"2411.11409","repositories_listed":1,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":2,"n_instrument":10,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":18,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/ikea-manuals-at-work-4d-grounding-of-assembly#ran","syntology_url":"https://syntology.ai/paper/2411.11409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11409"}},"official":{"repos":["yunongLiu1/IKEA-Manuals-at-Work"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/livos-light-video-object-segmentation-with","slug":"livos-light-video-object-segmentation-with","title":"LiVOS: Light Video Object Segmentation with Gated Linear Matching","date":"2024-11-05","arxiv_id":"2411.02818","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-spatio-temporal-memory-networks","slug":"continuous-spatio-temporal-memory-networks","title":"Continuous Spatio-Temporal Memory Networks for 4D Cardiac Cine MRI Segmentation","date":"2024-10-30","arxiv_id":"2410.23191","repositories_listed":1,"syntology":null},{"url":"/paper/smite-segment-me-in-time","slug":"smite-segment-me-in-time","title":"SMITE: Segment Me In TimE","date":"2024-10-24","arxiv_id":"2410.18538","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/smite-segment-me-in-time#ran","syntology_url":"https://syntology.ai/paper/2410.18538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18538"}},"official":{"repos":["alimohammadiamirhossein/smite"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/sam2long-enhancing-sam-2-for-long-video","slug":"sam2long-enhancing-sam-2-for-long-video","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","date":"2024-10-21","arxiv_id":"2410.16268","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sam2long-enhancing-sam-2-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2410.16268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16268"}},"official":{"repos":["mark12ding/sam2long"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/one-token-to-seg-them-all-language-instructed","slug":"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","arxiv_id":"2409.19603","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/one-token-to-seg-them-all-language-instructed#ran","syntology_url":"https://syntology.ai/paper/2409.19603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19603"}},"official":{"repos":["showlab/videolisa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/x-prompt-multi-modal-visual-prompt-for-video","slug":"x-prompt-multi-modal-visual-prompt-for-video","title":"X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation","date":"2024-09-28","arxiv_id":"2409.19342","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/x-prompt-multi-modal-visual-prompt-for-video#ran","syntology_url":"https://syntology.ai/paper/2409.19342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19342"}},"official":{"repos":["pinxueguo/x-prompt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unleashing-the-temporal-spatial-reasoning","slug":"unleashing-the-temporal-spatial-reasoning","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","date":"2024-08-28","arxiv_id":"2408.15876","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03286","slug":"2408-03286","title":"Biomedical SAM 2: Segment Anything in Biomedical Images and Videos","date":"2024-08-06","arxiv_id":"2408.03286","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-03286#ran","syntology_url":"https://syntology.ai/paper/2408.03286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03286"}},"official":{"repos":["ZhilingYan/Biomedical-SAM-2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-00169","slug":"2408-00169","title":"Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation","date":"2024-07-31","arxiv_id":"2408.00169","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-00169#ran","syntology_url":"https://syntology.ai/paper/2408.00169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00169"}},"official":{"repos":["vujas-eteph/lazyxmem"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/disentangling-spatio-temporal-knowledge-for","slug":"disentangling-spatio-temporal-knowledge-for","title":"Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video","date":"2024-07-22","arxiv_id":"2407.15794","repositories_listed":1,"syntology":null},{"url":"/paper/actionvos-actions-as-prompts-for-video-object","slug":"actionvos-actions-as-prompts-for-video-object","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","date":"2024-07-10","arxiv_id":"2407.07402","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/actionvos-actions-as-prompts-for-video-object#ran","syntology_url":"https://syntology.ai/paper/2407.07402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07402"}},"official":{"repos":["ut-vision/actionvos"],"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"]}}},{"url":"/paper/video-inpainting-localization-with","slug":"video-inpainting-localization-with","title":"Video Inpainting Localization with Contrastive Learning","date":"2024-06-25","arxiv_id":"2406.17628","repositories_listed":1,"syntology":null},{"url":"/paper/trusted-video-inpainting-localization-via","slug":"trusted-video-inpainting-localization-via","title":"Trusted Video Inpainting Localization via Deep Attentive Noise Learning","date":"2024-06-19","arxiv_id":"2406.13576","repositories_listed":1,"syntology":null},{"url":"/paper/vidsod-100-a-new-dataset-and-a-baseline-model","slug":"vidsod-100-a-new-dataset-and-a-baseline-model","title":"ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection","date":"2024-06-18","arxiv_id":"2406.12536","repositories_listed":1,"syntology":null},{"url":"/paper/1st-place-solution-for-mevis-track-in-cvpr","slug":"1st-place-solution-for-mevis-track-in-cvpr","title":"1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation","date":"2024-06-11","arxiv_id":"2406.07043","repositories_listed":1,"syntology":null},{"url":"/paper/lvos-a-benchmark-for-large-scale-long-term","slug":"lvos-a-benchmark-for-large-scale-long-term","title":"LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation","date":"2024-04-30","arxiv_id":"2404.19326","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-in-static-hybrid-visual","slug":"dynamic-in-static-hybrid-visual","title":"Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation","date":"2024-04-21","arxiv_id":"2404.13505","repositories_listed":1,"syntology":null}],"syntology_records":40,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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_where_code_ran":95,"papers_where_code_ran_first_page":"/task/video-object-segmentation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":6,"url":"/task/video-object-segmentation/papers/2","json":"/task/video-object-segmentation/papers/2.json","rows":100},{"order":"archive","page":3,"of":6,"url":"/task/video-object-segmentation/papers/3","json":"/task/video-object-segmentation/papers/3.json","rows":100},{"order":"archive","page":4,"of":6,"url":"/task/video-object-segmentation/papers/4","json":"/task/video-object-segmentation/papers/4.json","rows":100},{"order":"archive","page":5,"of":6,"url":"/task/video-object-segmentation/papers/5","json":"/task/video-object-segmentation/papers/5.json","rows":100},{"order":"archive","page":6,"of":6,"url":"/task/video-object-segmentation/papers/6","json":"/task/video-object-segmentation/papers/6.json","rows":51},{"order":"ran","page":1,"of":1,"url":"/task/video-object-segmentation/papers/ran/1","json":"/task/video-object-segmentation/papers/ran/1.json","rows":95}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"4a8a63e68f71ff68a408a51404ed12c0208e646d4638c06860bdd08fff4e3560","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}