{"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":28,"n_unverified":21,"n_pointer_only":0}}},{"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_unverified":2,"n_pointer_only":0}}},{"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_unverified":2,"n_pointer_only":0}}},{"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_unverified":3,"n_pointer_only":8}}},{"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_unverified":2,"n_pointer_only":0}}},{"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":3,"n_unverified":8,"n_pointer_only":11}}},{"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":28,"n_unverified":21,"n_pointer_only":0}}},{"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_unverified":0,"n_pointer_only":1}}},{"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_unverified":2,"n_pointer_only":2}}},{"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_unverified":2,"n_pointer_only":0}}},{"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_unverified":2,"n_pointer_only":0}}},{"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":1,"n_unverified":8,"n_pointer_only":0}}},{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":99,"tagged_in_all":147,"items":[{"url":"/paper/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":28,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/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","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":9,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/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":3,"n_unverified":12,"n_pointer_only":3}},{"url":"/paper/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","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","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","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_unverified":4,"n_pointer_only":2}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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_unverified":2,"n_pointer_only":2}},{"url":"/paper/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","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_unverified":2,"n_pointer_only":2}},{"url":"/paper/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","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","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","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","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","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":4,"n_unverified":19,"n_pointer_only":0}},{"url":"/paper/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":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/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_unverified":3,"n_pointer_only":3}},{"url":"/paper/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","title":"Learning Video Object Segmentation from Static Images","date":"2016-12-08","arxiv_id":"1612.02646","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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","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":3,"n_unverified":8,"n_pointer_only":11}},{"url":"/paper/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}],"syntology_records":16,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}