{"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/semi-supervised-video-object-segmentation","name":"Semi-Supervised Video Object Segmentation","slug":"semi-supervised-video-object-segmentation","description_markdown":"The semi-supervised scenario assumes the user inputs a full mask of the object(s) of interest in the first frame of a video sequence. Methods have to produce the segmentation mask for that object(s) in the subsequent frames.","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":147,"papers_with_code":99,"benchmarks":16,"benchmark_tables_in_archive":16,"benchmark_tables_shown":16,"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":13,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","slug":"visual-object-tracking-on-davis-2017","dataset":"DAVIS 2017 (val)","dataset_url":"/dataset/davis-2017","rows_in_archive":81,"metrics":["J&F","Jaccard (Mean)","Jaccard (Recall)","Jaccard (Decay)","F-measure (Mean)","F-measure (Recall)","F-measure (Decay)","Speed (FPS)","Params(M)"],"first_row_in_archive_order":{"model":"SAM2","paper_title":"SAM 2: Segment Anything in Images and Videos","paper_url":"/paper/2408-00714","paper_date":"2024-08-01","arxiv_id":"2408.00714","code_links":[{"title":"facebookresearch/segment-anything","url":"https://github.com/facebookresearch/segment-anything"},{"title":"facebookresearch/sam2","url":"https://github.com/facebookresearch/sam2"},{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"ibaiGorordo/ONNX-SAM2-Segment-Anything","url":"https://github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything"},{"title":"bowang-lab/medsam2","url":"https://github.com/bowang-lab/medsam2"},{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"},{"title":"louisfinner/him2sam","url":"https://github.com/louisfinner/him2sam"},{"title":"MindCode-4/code-4","url":"https://github.com/MindCode-4/code-4/tree/main/sam"},{"title":"dcnieho/segment-anything-2","url":"https://github.com/dcnieho/segment-anything-2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/SAM"}],"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"]}}}},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","slug":"visual-object-tracking-on-davis-2016","dataset":"DAVIS 2016","dataset_url":"/dataset/davis-2016","rows_in_archive":78,"metrics":["J&F","Jaccard (Mean)","Jaccard (Recall)","Jaccard (Decay)","F-measure (Mean)","F-measure (Recall)","F-measure (Decay)","Speed (FPS)"],"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/semi-supervised-video-object-segmentation-on-1","slug":"semi-supervised-video-object-segmentation-on-1","dataset":"DAVIS 2017 (test-dev)","dataset_url":"/dataset/davis-2017","rows_in_archive":59,"metrics":["J&F","Jaccard (Mean)","Jaccard (Recall)","Jaccard (Decay)","F-measure (Mean)","F-measure (Recall)","F-measure (Decay)","FPS"],"first_row_in_archive_order":{"model":"Cutie+ (base, MEGA)","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-youtube-vos","slug":"video-object-segmentation-on-youtube-vos","dataset":"YouTube-VOS 2018","dataset_url":"/dataset/youtube-vos","rows_in_archive":53,"metrics":["Overall","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)","Speed  (FPS)","Params(M)","Speed (FPS)"],"first_row_in_archive_order":{"model":"Cutie+ (base, MEGA)","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/semi-supervised-video-object-segmentation-on-20","slug":"semi-supervised-video-object-segmentation-on-20","dataset":"DAVIS (no YouTube-VOS training)","dataset_url":"/dataset/davis","rows_in_archive":26,"metrics":["D17 val (G)","D17 val (J)","D17 val (F)","D17 test (G)","D17 test (J)","D17 test (F)","D16 val (G)","D16 val (J)","D16 val (F)","FPS"],"first_row_in_archive_order":{"model":"HMMN","paper_title":"Hierarchical Memory Matching Network for Video Object Segmentation","paper_url":"/paper/hierarchical-memory-matching-network-for","paper_date":"2021-09-23","arxiv_id":"2109.11404","code_links":[{"title":"hongje/hmmn","url":"https://github.com/hongje/hmmn"}],"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 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) · 3 unverified","sample_list":"/paper/hierarchical-memory-matching-network-for#ran","syntology_url":"https://syntology.ai/paper/2109.11404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11404"}},"official":{"repos":["hongje/hmmn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-18","slug":"semi-supervised-video-object-segmentation-on-18","dataset":"YouTube-VOS 2019","dataset_url":"/dataset/youtube-vos","rows_in_archive":22,"metrics":["Overall","Jaccard (Seen)","F-Measure (Seen)","Jaccard (Unseen)","F-Measure (Unseen)","FPS","J&F","J score (unseen)"],"first_row_in_archive_order":{"model":"Cutie+ (base, MEGA)","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/semi-supervised-video-object-segmentation-on-15","slug":"semi-supervised-video-object-segmentation-on-15","dataset":"VOT2020","dataset_url":"/dataset/vot2020","rows_in_archive":20,"metrics":["EAO","EAO (real-time)"],"first_row_in_archive_order":{"model":"DAM4SAM","paper_title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","paper_url":"/paper/a-distractor-aware-memory-for-visual-object","paper_date":"2024-11-26","arxiv_id":"2411.17576","code_links":[{"title":"jovanavidenovic/dam4sam","url":"https://github.com/jovanavidenovic/dam4sam"}],"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":11,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-distractor-aware-memory-for-visual-object#ran","syntology_url":"https://syntology.ai/paper/2411.17576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17576"}},"official":{"repos":["jovanavidenovic/dam4sam"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-21","slug":"semi-supervised-video-object-segmentation-on-21","dataset":"MOSE","dataset_url":"/dataset/mose","rows_in_archive":17,"metrics":["J&F","J","F","FPS"],"first_row_in_archive_order":{"model":"SAM2","paper_title":"SAM 2: Segment Anything in Images and Videos","paper_url":"/paper/2408-00714","paper_date":"2024-08-01","arxiv_id":"2408.00714","code_links":[{"title":"facebookresearch/segment-anything","url":"https://github.com/facebookresearch/segment-anything"},{"title":"facebookresearch/sam2","url":"https://github.com/facebookresearch/sam2"},{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"ibaiGorordo/ONNX-SAM2-Segment-Anything","url":"https://github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything"},{"title":"bowang-lab/medsam2","url":"https://github.com/bowang-lab/medsam2"},{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"},{"title":"louisfinner/him2sam","url":"https://github.com/louisfinner/him2sam"},{"title":"MindCode-4/code-4","url":"https://github.com/MindCode-4/code-4/tree/main/sam"},{"title":"dcnieho/segment-anything-2","url":"https://github.com/dcnieho/segment-anything-2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/SAM"}],"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"]}}}},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-13","slug":"semi-supervised-video-object-segmentation-on-13","dataset":"Long Video Dataset","dataset_url":"/dataset/long-video-dataset","rows_in_archive":9,"metrics":["J&F","J","F"],"first_row_in_archive_order":{"model":"ISVOS","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-youtube","slug":"video-object-segmentation-on-youtube","dataset":"YouTube","dataset_url":null,"rows_in_archive":5,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"Spatiotemporal CNN","paper_title":"Spatiotemporal CNN for Video Object Segmentation","paper_url":"/paper/spatiotemporal-cnn-for-video-object","paper_date":"2019-04-04","arxiv_id":"1904.02363","code_links":[{"title":"longyin880815/STCNN","url":"https://github.com/longyin880815/STCNN"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatiotemporal-cnn-for-video-object#ran","syntology_url":"https://syntology.ai/paper/1904.02363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02363"}},"official":{"repos":["longyin880815/STCNN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-14","slug":"semi-supervised-video-object-segmentation-on-14","dataset":"Long Video Dataset (3X)","dataset_url":"/dataset/long-video-dataset-3x","rows_in_archive":2,"metrics":["J&F","J","F"],"first_row_in_archive_order":{"model":"XMem","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/semi-supervised-video-object-segmentation-on-2","slug":"semi-supervised-video-object-segmentation-on-2","dataset":"DAVIS-2017","dataset_url":"/dataset/davis-2017","rows_in_archive":2,"metrics":["F-measure (Mean)","J&F","Jaccard (Mean)","Speed (FPS)"],"first_row_in_archive_order":{"model":"STCN + TrickVOS (PT)","paper_title":"TrickVOS: A Bag of Tricks for Video Object Segmentation","paper_url":"/paper/trickvos-a-bag-of-tricks-for-video-object","paper_date":"2023-06-27","arxiv_id":"2306.15377","code_links":[],"syntology":null}},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-22","slug":"semi-supervised-video-object-segmentation-on-22","dataset":"BURST-val","dataset_url":"/dataset/burst","rows_in_archive":2,"metrics":["HOTA (all)","HOTA (common)","HOTA (uncommon)"],"first_row_in_archive_order":{"model":"Cutie (base, MEGA, 600 pixels)","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/semi-supervised-video-object-segmentation-on-23","slug":"semi-supervised-video-object-segmentation-on-23","dataset":"BURST-test","dataset_url":"/dataset/burst","rows_in_archive":2,"metrics":["HOTA (all)","HOTA (common)","HOTA (uncommon)"],"first_row_in_archive_order":{"model":"Cutie (base, MEGA, 600 pixels)","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/semi-supervised-video-object-segmentation-on-17","slug":"semi-supervised-video-object-segmentation-on-17","dataset":"DAVIS 2017","dataset_url":"/dataset/davis-2017","rows_in_archive":1,"metrics":["F-measure (Decay)","F-measure (Mean)","F-measure (Recall)","J&F","Jaccard (Decay)","Jaccard (Mean)","Jaccard (Recall)"],"first_row_in_archive_order":{"model":"FEELVOS","paper_title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","paper_url":"/paper/feelvos-fast-end-to-end-embedding-learning","paper_date":"2019-02-25","arxiv_id":"1902.09513","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/feelvos"},{"title":"kim-younghan/FEELVOS","url":"https://github.com/kim-younghan/FEELVOS"}],"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"]}}}},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-3","slug":"semi-supervised-video-object-segmentation-on-3","dataset":"DAVIS-2016","dataset_url":null,"rows_in_archive":1,"metrics":["Speed (FPS)"],"first_row_in_archive_order":{"model":"STCN + TrickVOS (PT)","paper_title":"TrickVOS: A Bag of Tricks for Video Object Segmentation","paper_url":"/paper/trickvos-a-bag-of-tricks-for-video-object","paper_date":"2023-06-27","arxiv_id":"2306.15377","code_links":[],"syntology":null}}],"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/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/vot","name":"VOTChallenge","full_name":"Visual Object Tracking","num_papers_in_archive":36},{"url":"/dataset/burst","name":"BURST","full_name":"","num_papers_in_archive":18},{"url":"/dataset/bl30k","name":"BL30K","full_name":"","num_papers_in_archive":11},{"url":"/dataset/vot2020","name":"VOT2020","full_name":"","num_papers_in_archive":9},{"url":"/dataset/long-video-dataset","name":"Long Video Dataset","full_name":"","num_papers_in_archive":6},{"url":"/dataset/long-video-dataset-3x","name":"Long Video Dataset (3X)","full_name":"","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}],"subtasks":[{"url":"/task/one-shot-visual-object-segmentation","name":"One-shot visual object segmentation"}],"parent_tasks":[{"url":"/task/video-object-segmentation","name":"Video Object Segmentation"}],"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":2,"rows_per_page":100,"shown":100,"of":147,"of_with_code":99,"tagged_in_all":147,"counts":{"archive_papers_tagged":147,"with_a_code_link":99,"where_syntology_ran_a_sample":37,"not_listed_spam_title":0,"listed":147,"listed_where_code_ran":37,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":33,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":33,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/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/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/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/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/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/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/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/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/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/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/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/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/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/joint-task-self-supervised-learning-for","slug":"joint-task-self-supervised-learning-for","title":"Joint-task Self-supervised Learning for Temporal Correspondence","date":"2019-09-26","arxiv_id":"1909.11895","repositories_listed":2,"syntology":{"n":23,"n_ran":18,"n_constructed":0,"n_ran_checked":15,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":2,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/joint-task-self-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/1909.11895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11895"}},"official":{"repos":["Liusifei/UVC"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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/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/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/exploring-enhanced-contextual-information-for-1","slug":"exploring-enhanced-contextual-information-for-1","title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","date":"2024-12-15","arxiv_id":"2412.11023","repositories_listed":1,"syntology":null},{"url":"/paper/a-distractor-aware-memory-for-visual-object","slug":"a-distractor-aware-memory-for-visual-object","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","date":"2024-11-26","arxiv_id":"2411.17576","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":11,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-distractor-aware-memory-for-visual-object#ran","syntology_url":"https://syntology.ai/paper/2411.17576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17576"}},"official":{"repos":["jovanavidenovic/dam4sam"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"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/efficient-video-object-segmentation-via-1","slug":"efficient-video-object-segmentation-via-1","title":"Efficient Video Object Segmentation via Modulated Cross-Attention Memory","date":"2024-03-26","arxiv_id":"2403.17937","repositories_listed":1,"syntology":null},{"url":"/paper/video-object-segmentation-with-dynamic-query","slug":"video-object-segmentation-with-dynamic-query","title":"Video Object Segmentation with Dynamic Query Modulation","date":"2024-03-18","arxiv_id":"2403.11529","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-surgical-instrument-segmentation-in","slug":"real-time-surgical-instrument-segmentation-in","title":"Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything","date":"2024-03-12","arxiv_id":"2403.08003","repositories_listed":1,"syntology":null},{"url":"/paper/lester-rotoscope-animation-through-video","slug":"lester-rotoscope-animation-through-video","title":"Lester: rotoscope animation through video object segmentation and tracking","date":"2024-02-15","arxiv_id":"2402.09883","repositories_listed":1,"syntology":null},{"url":"/paper/odtrack-online-dense-temporal-token-learning","slug":"odtrack-online-dense-temporal-token-learning","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","date":"2024-01-03","arxiv_id":"2401.01686","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/odtrack-online-dense-temporal-token-learning#ran","syntology_url":"https://syntology.ai/paper/2401.01686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01686"}},"official":{"repos":["gxnu-zhonglab/odtrack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/putting-the-object-back-into-video-object","slug":"putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","arxiv_id":"2310.12982","repositories_listed":1,"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"]}}},{"url":"/paper/sub-token-vit-embedding-via-stochastic","slug":"sub-token-vit-embedding-via-stochastic","title":"Sub-token ViT Embedding via Stochastic Resonance Transformers","date":"2023-10-06","arxiv_id":"2310.03967","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}},"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tracking-anything-in-high-quality","slug":"tracking-anything-in-high-quality","title":"Tracking Anything in High Quality","date":"2023-07-26","arxiv_id":"2307.13974","repositories_listed":1,"syntology":null},{"url":"/paper/readmem-robust-embedding-association-for-a","slug":"readmem-robust-embedding-association-for-a","title":"READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation","date":"2023-05-22","arxiv_id":"2305.12823","repositories_listed":1,"syntology":null},{"url":"/paper/clvos23-a-long-video-object-segmentation","slug":"clvos23-a-long-video-object-segmentation","title":"CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning","date":"2023-04-09","arxiv_id":"2304.04259","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-learn-better-for-video-object","slug":"learning-to-learn-better-for-video-object","title":"Learning to Learn Better for Video Object Segmentation","date":"2022-12-05","arxiv_id":"2212.02112","repositories_listed":1,"syntology":null},{"url":"/paper/global-spectral-filter-memory-network-for","slug":"global-spectral-filter-memory-network-for","title":"Global Spectral Filter Memory Network for Video Object Segmentation","date":"2022-10-11","arxiv_id":"2210.05567","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/global-spectral-filter-memory-network-for#ran","syntology_url":"https://syntology.ai/paper/2210.05567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05567"}},"official":{"repos":["workforai/gsfm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/swem-towards-real-time-video-object-1","slug":"swem-towards-real-time-video-object-1","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","date":"2022-08-22","arxiv_id":"2208.10128","repositories_listed":1,"syntology":null},{"url":"/paper/per-clip-video-object-segmentation-1","slug":"per-clip-video-object-segmentation-1","title":"Per-Clip Video Object Segmentation","date":"2022-08-03","arxiv_id":"2208.01924","repositories_listed":1,"syntology":{"n":12,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":12,"phrase":"4 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; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/per-clip-video-object-segmentation-1#ran","syntology_url":"https://syntology.ai/paper/2208.01924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01924"}},"official":{"repos":["pkyong95/PCVOS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-quality-aware-dynamic-memory-for","slug":"learning-quality-aware-dynamic-memory-for","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","date":"2022-07-16","arxiv_id":"2207.07922","repositories_listed":1,"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/learning-quality-aware-dynamic-memory-for#ran","syntology_url":"https://syntology.ai/paper/2207.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07922"}},"official":{"repos":["workforai/qdmn"],"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/tackling-background-distraction-in-video","slug":"tackling-background-distraction-in-video","title":"Tackling Background Distraction in Video Object Segmentation","date":"2022-07-14","arxiv_id":"2207.06953","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tackling-background-distraction-in-video#ran","syntology_url":"https://syntology.ai/paper/2207.06953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06953"}},"official":{"repos":["suhwan-cho/tbd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-robust-video-object-segmentation-with","slug":"towards-robust-video-object-segmentation-with","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","date":"2022-07-02","arxiv_id":"2207.00887","repositories_listed":1,"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"]}}},{"url":"/paper/recurrent-dynamic-embedding-for-video-object","slug":"recurrent-dynamic-embedding-for-video-object","title":"Recurrent Dynamic Embedding for Video Object Segmentation","date":"2022-05-08","arxiv_id":"2205.03761","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-video-object-segmentation-based-on","slug":"boosting-video-object-segmentation-based-on","title":"Boosting Video Object Segmentation based on Scale Inconsistency","date":"2022-05-02","arxiv_id":"2205.01197","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-memory-management-for-video-object","slug":"adaptive-memory-management-for-video-object","title":"Adaptive Memory Management for Video Object Segmentation","date":"2022-04-13","arxiv_id":"2204.06626","repositories_listed":1,"syntology":null},{"url":"/paper/mixformer-end-to-end-tracking-with-iterative-1","slug":"mixformer-end-to-end-tracking-with-iterative-1","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","date":"2022-03-21","arxiv_id":"2203.11082","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/mixformer-end-to-end-tracking-with-iterative-1#ran","syntology_url":"https://syntology.ai/paper/2203.11082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11082"}},"official":{"repos":["MCG-NJU/MixFormer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/siamese-network-with-interactive-transformer","slug":"siamese-network-with-interactive-transformer","title":"Siamese Network with Interactive Transformer for Video Object Segmentation","date":"2021-12-28","arxiv_id":"2112.13983","repositories_listed":1,"syntology":null},{"url":"/paper/reliable-propagation-correction-modulation","slug":"reliable-propagation-correction-modulation","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","date":"2021-12-06","arxiv_id":"2112.02853","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reliable-propagation-correction-modulation#ran","syntology_url":"https://syntology.ai/paper/2112.02853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02853"}},"official":{"repos":["jerryx1110/rpcmvos"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/faminet-learning-real-time-semi-supervised","slug":"faminet-learning-real-time-semi-supervised","title":"FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical Flow","date":"2021-11-20","arxiv_id":"2111.10531","repositories_listed":1,"syntology":null},{"url":"/paper/dense-unsupervised-learning-for-video","slug":"dense-unsupervised-learning-for-video","title":"Dense Unsupervised Learning for Video Segmentation","date":"2021-11-11","arxiv_id":"2111.06265","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dense-unsupervised-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2111.06265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06265"}},"official":{"repos":["visinf/dense-ulearn-vos"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-the-semi-supervised-video-object","slug":"exploring-the-semi-supervised-video-object","title":"Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic Perspective","date":"2021-11-02","arxiv_id":"2111.01323","repositories_listed":1,"syntology":null},{"url":"/paper/pixel-level-bijective-matching-for-video","slug":"pixel-level-bijective-matching-for-video","title":"Pixel-Level Bijective Matching for Video Object Segmentation","date":"2021-10-04","arxiv_id":"2110.01644","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-memory-matching-network-for","slug":"hierarchical-memory-matching-network-for","title":"Hierarchical Memory Matching Network for Video Object Segmentation","date":"2021-09-23","arxiv_id":"2109.11404","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 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) · 3 unverified","sample_list":"/paper/hierarchical-memory-matching-network-for#ran","syntology_url":"https://syntology.ai/paper/2109.11404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11404"}},"official":{"repos":["hongje/hmmn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/joint-inductive-and-transductive-learning-for","slug":"joint-inductive-and-transductive-learning-for","title":"Joint Inductive and Transductive Learning for Video Object Segmentation","date":"2021-08-08","arxiv_id":"2108.03679","repositories_listed":1,"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/joint-inductive-and-transductive-learning-for#ran","syntology_url":"https://syntology.ai/paper/2108.03679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03679"}},"official":{"repos":["maoyunyao/joint"],"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/self-supervised-video-object-segmentation-by-1","slug":"self-supervised-video-object-segmentation-by-1","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","date":"2021-07-27","arxiv_id":"2107.12569","repositories_listed":1,"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":0,"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/self-supervised-video-object-segmentation-by-1#ran","syntology_url":"https://syntology.ai/paper/2107.12569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12569"}},"official":{"repos":["bo-miao/MAMP"],"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"]}}},{"url":"/paper/do-different-tracking-tasks-require-different","slug":"do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","repositories_listed":1,"syntology":{"n":17,"n_ran":6,"n_constructed":4,"n_ran_checked":4,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/do-different-tracking-tasks-require-different#ran","syntology_url":"https://syntology.ai/paper/2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}},"official":{"repos":["Zhongdao/UniTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/transvos-video-object-segmentation-with","slug":"transvos-video-object-segmentation-with","title":"TransVOS: Video Object Segmentation with Transformers","date":"2021-06-01","arxiv_id":"2106.00588","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-regional-memory-network-for-video","slug":"efficient-regional-memory-network-for-video","title":"Efficient Regional Memory Network for Video Object Segmentation","date":"2021-03-24","arxiv_id":"2103.12934","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 5 unverified","sample_list":"/paper/efficient-regional-memory-network-for-video#ran","syntology_url":"https://syntology.ai/paper/2103.12934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12934"}},"official":{"repos":["hzxie/RMNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/separable-structure-modeling-for-semi","slug":"separable-structure-modeling-for-semi","title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","date":"2021-02-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/swiftnet-real-time-video-object-segmentation","slug":"swiftnet-real-time-video-object-segmentation","title":"SwiftNet: Real-time Video Object Segmentation","date":"2021-02-09","arxiv_id":"2102.04604","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":5,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/swiftnet-real-time-video-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2102.04604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04604"}},"official":{"repos":["haochenheheda/SwiftNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sstvos-sparse-spatiotemporal-transformers-for","slug":"sstvos-sparse-spatiotemporal-transformers-for","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","date":"2021-01-21","arxiv_id":"2101.08833","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 5 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) · 2 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/sstvos-sparse-spatiotemporal-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2101.08833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08833"}},"official":{"repos":["dukebw/SSTVOS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/2012-11655","slug":"2012-11655","title":"Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation","date":"2020-12-21","arxiv_id":"2012.11655","repositories_listed":1,"syntology":null},{"url":"/paper/alpha-refine-boosting-tracking-performance-by-1","slug":"alpha-refine-boosting-tracking-performance-by-1","title":"Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation","date":"2020-12-12","arxiv_id":"2012.06815","repositories_listed":1,"syntology":null},{"url":"/paper/ttvos-lightweight-video-object-segmentation","slug":"ttvos-lightweight-video-object-segmentation","title":"TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss","date":"2020-11-09","arxiv_id":"2011.04445","repositories_listed":1,"syntology":null},{"url":"/paper/delving-into-the-cyclic-mechanism-in-semi","slug":"delving-into-the-cyclic-mechanism-in-semi","title":"Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation","date":"2020-10-23","arxiv_id":"2010.12176","repositories_listed":1,"syntology":null},{"url":"/paper/video-object-segmentation-with-adaptive","slug":"video-object-segmentation-with-adaptive","title":"Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement","date":"2020-10-15","arxiv_id":"2010.07958","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-video-object-segmentation-by-1","slug":"collaborative-video-object-segmentation-by-1","title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","date":"2020-10-13","arxiv_id":"2010.06349","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/collaborative-video-object-segmentation-by-1#ran","syntology_url":"https://syntology.ai/paper/2010.06349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06349"}},"official":{"repos":["z-x-yang/CFBI"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lsmvos-long-short-term-similarity-matching","slug":"lsmvos-long-short-term-similarity-matching","title":"LSMVOS: Long-Short-Term Similarity Matching for Video Object","date":"2020-09-02","arxiv_id":"2009.00771","repositories_listed":1,"syntology":null},{"url":"/paper/kernelized-memory-network-for-video-object","slug":"kernelized-memory-network-for-video-object","title":"Kernelized Memory Network for Video Object Segmentation","date":"2020-07-16","arxiv_id":"2007.08270","repositories_listed":1,"syntology":null},{"url":"/paper/fast-template-matching-and-update-for-video","slug":"fast-template-matching-and-update-for-video","title":"Fast Template Matching and Update for Video Object Tracking and Segmentation","date":"2020-04-16","arxiv_id":"2004.07538","repositories_listed":1,"syntology":null},{"url":"/paper/a-transductive-approach-for-video-object","slug":"a-transductive-approach-for-video-object","title":"A Transductive Approach for Video Object Segmentation","date":"2020-04-15","arxiv_id":"2004.07193","repositories_listed":1,"syntology":null},{"url":"/paper/learning-video-object-segmentation-from-2","slug":"learning-video-object-segmentation-from-2","title":"Learning Video Object Segmentation from Unlabeled Videos","date":"2020-03-10","arxiv_id":"2003.05020","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-video-object-segmentation-from-2#ran","syntology_url":"https://syntology.ai/paper/2003.05020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05020"}},"official":{"repos":["carrierlxk/MuG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/state-aware-tracker-for-real-time-video","slug":"state-aware-tracker-for-real-time-video","title":"State-Aware Tracker for Real-Time Video Object Segmentation","date":"2020-03-01","arxiv_id":"2003.00482","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/state-aware-tracker-for-real-time-video#ran","syntology_url":"https://syntology.ai/paper/2003.00482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00482"}},"official":{"repos":["MegviiDetection/video_analyst"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/directional-deep-embedding-and-appearance","slug":"directional-deep-embedding-and-appearance","title":"Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation","date":"2020-02-17","arxiv_id":"2002.06736","repositories_listed":1,"syntology":null},{"url":"/paper/crvos-clue-refining-network-for-video-object","slug":"crvos-clue-refining-network-for-video-object","title":"CRVOS: Clue Refining Network for Video Object Segmentation","date":"2020-02-10","arxiv_id":"2002.03651","repositories_listed":1,"syntology":null},{"url":"/paper/fast-video-object-segmentation-using-the","slug":"fast-video-object-segmentation-using-the","title":"Fast Video Object Segmentation using the Global Context Module","date":"2020-01-30","arxiv_id":"2001.11243","repositories_listed":1,"syntology":null},{"url":"/paper/unovost-unsupervised-offline-video-object","slug":"unovost-unsupervised-offline-video-object","title":"UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking","date":"2020-01-15","arxiv_id":"2001.05425","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/unovost-unsupervised-offline-video-object#ran","syntology_url":"https://syntology.ai/paper/2001.05425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.05425"}},"official":null}},{"url":"/paper/siam-r-cnn-visual-tracking-by-re-detection","slug":"siam-r-cnn-visual-tracking-by-re-detection","title":"Siam R-CNN: Visual Tracking by Re-Detection","date":"2019-11-28","arxiv_id":"1911.12836","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/siam-r-cnn-visual-tracking-by-re-detection#ran","syntology_url":"https://syntology.ai/paper/1911.12836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12836"}},"official":null}},{"url":"/paper/agss-vos-attention-guided-single-shot-video","slug":"agss-vos-attention-guided-single-shot-video","title":"AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation","date":"2019-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/capsulevos-semi-supervised-video-object","slug":"capsulevos-semi-supervised-video-object","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","date":"2019-09-30","arxiv_id":"1910.00132","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-roi-generation-for-video-object","slug":"adaptive-roi-generation-for-video-object","title":"Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning","date":"2019-09-27","arxiv_id":"1909.12482","repositories_listed":1,"syntology":null},{"url":"/paper/dmm-net-differentiable-mask-matching-network","slug":"dmm-net-differentiable-mask-matching-network","title":"DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation","date":"2019-09-27","arxiv_id":"1909.12471","repositories_listed":1,"syntology":null},{"url":"/paper/a-spectral-approach-to-unsupervised-object","slug":"a-spectral-approach-to-unsupervised-object","title":"A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time","date":"2019-07-05","arxiv_id":"1907.02731","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/a-spectral-approach-to-unsupervised-object#ran","syntology_url":"https://syntology.ai/paper/1907.02731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.02731"}},"official":{"repos":["bit-ml/sfseg"],"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":["official"]}}},{"url":"/paper/proposal-tracking-and-segmentation-pts-a","slug":"proposal-tracking-and-segmentation-pts-a","title":"Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation","date":"2019-07-02","arxiv_id":"1907.01203","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-for-video","slug":"self-supervised-learning-for-video","title":"Self-supervised Learning for Video Correspondence Flow","date":"2019-05-02","arxiv_id":"1905.00875","repositories_listed":1,"syntology":null},{"url":"/paper/190408141","slug":"190408141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","date":"2019-04-17","arxiv_id":"1904.08141","repositories_listed":1,"syntology":null},{"url":"/paper/spatiotemporal-cnn-for-video-object","slug":"spatiotemporal-cnn-for-video-object","title":"Spatiotemporal CNN for Video Object Segmentation","date":"2019-04-04","arxiv_id":"1904.02363","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":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatiotemporal-cnn-for-video-object#ran","syntology_url":"https://syntology.ai/paper/1904.02363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02363"}},"official":{"repos":["longyin880815/STCNN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bubblenets-learning-to-select-the-guidance","slug":"bubblenets-learning-to-select-the-guidance","title":"BubbleNets: Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames","date":"2019-03-28","arxiv_id":"1903.11779","repositories_listed":1,"syntology":null},{"url":"/paper/learning-correspondence-from-the-cycle","slug":"learning-correspondence-from-the-cycle","title":"Learning Correspondence from the Cycle-Consistency of Time","date":"2019-03-18","arxiv_id":"1903.07593","repositories_listed":1,"syntology":null},{"url":"/paper/rvos-end-to-end-recurrent-network-for-video","slug":"rvos-end-to-end-recurrent-network-for-video","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","date":"2019-03-13","arxiv_id":"1903.05612","repositories_listed":1,"syntology":null},{"url":"/paper/a-generative-appearance-model-for-end-to-end","slug":"a-generative-appearance-model-for-end-to-end","title":"A Generative Appearance Model for End-to-end Video Object Segmentation","date":"2018-11-28","arxiv_id":"1811.11611","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-generative-appearance-model-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/1811.11611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11611"}},"official":null}},{"url":"/paper/efficient-video-object-segmentation-via","slug":"efficient-video-object-segmentation-via","title":"Efficient Video Object Segmentation via Network Modulation","date":"2018-02-04","arxiv_id":"1802.01218","repositories_listed":1,"syntology":null},{"url":"/paper/segflow-joint-learning-for-video-object","slug":"segflow-joint-learning-for-video-object","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","date":"2017-09-20","arxiv_id":"1709.06750","repositories_listed":1,"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/segflow-joint-learning-for-video-object#ran","syntology_url":"https://syntology.ai/paper/1709.06750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.06750"}},"official":{"repos":["JingchunCheng/SegFlow"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":null,"slug":"thu-warwick-submission-for-epic-kitchen","title":"THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation","date":"2025-06-07","arxiv_id":"2506.06748","repositories_listed":0,"syntology":null}],"syntology_records":43,"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":37,"papers_where_code_ran_first_page":"/task/semi-supervised-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":2,"url":"/task/semi-supervised-video-object-segmentation/papers/2","json":"/task/semi-supervised-video-object-segmentation/papers/2.json","rows":47},{"order":"ran","page":1,"of":1,"url":"/task/semi-supervised-video-object-segmentation/papers/ran/1","json":"/task/semi-supervised-video-object-segmentation/papers/ran/1.json","rows":37}],"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":"c98bac70cc737e3141e00b8a6143bcb597302a2f0b139c48cadd934137ba4a04","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}