{"url":"/sota/video-object-segmentation-on-davis-2016","task":{"name":"Video Object Segmentation","url":"/task/video-object-segmentation","note":null},"dataset":{"name":"DAVIS 2016","url":"/dataset/davis-2016"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Video object segmentation is a binary labeling problem aiming to separate foreground object(s) from the background region of a video.\r\n\r\nFor leaderboards please refer to the different subtasks.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["J&F","F-Score","Jaccard (Mean)","mIoU","Contour Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"J&F":null,"F-Score":"higher","Jaccard (Mean)":null,"mIoU":null,"Contour Accuracy":"higher"}},"counts":{"rows":24,"rows_with_code":6,"rows_with_paper_page":24,"rows_dated":24,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"ISVOS (BL30K, MS)","metrics":{"F-Score":"94.2","J&F":"93.4","Jaccard (Mean)":"92.5"},"uses_additional_data":false,"paper_date":"2022-12-13","paper":"/paper/look-before-you-match-instance-understanding","paper_url":"https://arxiv.org/abs/2212.06826v1","paper_title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"XMem (BL30K, MS)","metrics":{"F-Score":"94.4","J&F":"93.3","Jaccard (Mean)":"92.2"},"uses_additional_data":false,"paper_date":"2022-07-14","paper":"/paper/xmem-long-term-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","code":"https://github.com/hkchengrex/XMem","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"BATMAN (val)","metrics":{"F-Score":"94.2","J&F":"92.5","Jaccard (Mean)":"90.7"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"STCN (val)","metrics":{"F-Score":"92.5","J&F":"91.6","Jaccard (Mean)":"90.8"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"XMem","metrics":{"F-Score":"92.7","J&F":"91.5","Jaccard (Mean)":"90.4"},"uses_additional_data":false,"paper_date":"2022-07-14","paper":"/paper/xmem-long-term-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","code":"https://github.com/hkchengrex/XMem","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":6,"model":"MobileVOS (val)","metrics":{"F-Score":"92.6","J&F":"91.4","Jaccard (Mean)":"90.3"},"uses_additional_data":false,"paper_date":"2023-03-14","paper":"/paper/mobilevos-real-time-video-object-segmentation","paper_url":"https://arxiv.org/abs/2303.07815v1","paper_title":"MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"AOT (val)","metrics":{"F-Score":"92.1","J&F":"91.1","Jaccard (Mean)":"90.1"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"LCM (val)","metrics":{"F-Score":"91.4","J&F":"90.7","Jaccard (Mean)":"89.9"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"RPCMVOS (val)","metrics":{"F-Score":"94","J&F":"90.6","Jaccard (Mean)":"87.1"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"KMN (val)","metrics":{"F-Score":"91.5","J&F":"90.5","Jaccard (Mean)":"89.5"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"TransVOS (val)","metrics":{"F-Score":"91.2","J&F":"90.5","Jaccard (Mean)":"89.8"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"CFBI+ (val)","metrics":{"F-Score":"91.1","J&F":"89.9","Jaccard (Mean)":"88.7"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"ViTAE-T-Stage","metrics":{"F-Score":"90.4","J&F":"89.8","Jaccard (Mean)":"89.2"},"uses_additional_data":false,"paper_date":"2021-06-07","paper":"/paper/vitae-vision-transformer-advanced-by","paper_url":"https://arxiv.org/abs/2106.03348v4","paper_title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","code":"https://github.com/ViTAE-Transformer/ViTAE-Transformer","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":14,"model":"CFBI (val)","metrics":{"F-Score":"90.5","J&F":"89.4","Jaccard (Mean)":"88.3"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"RMN (val)","metrics":{"F-Score":"88.7","J&F":"88.8","Jaccard (Mean)":"88.9"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"AOC-MF (val)","metrics":{"F-Score":"94.7","Jaccard (Mean)":"88.5"},"uses_additional_data":false,"paper_date":"2022-07-02","paper":"/paper/towards-robust-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.00887v1","paper_title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","code":"https://github.com/jerryx1110/robust-video-object-segmentation","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":17,"model":"STM (val)","metrics":{"F-Score":"89.9","Jaccard (Mean)":"88.7"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/batman-bilateral-attention-transformer-in","paper_url":"https://arxiv.org/abs/2208.01159v4","paper_title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"3DC-Seg","metrics":{"F-Score":"84.7","Jaccard (Mean)":"84.3"},"uses_additional_data":true,"paper_date":"2020-08-26","paper":"/paper/making-a-case-for-3d-convolutions-for-object","paper_url":"https://arxiv.org/abs/2008.11516v2","paper_title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","code":"https://github.com/sabarim/3DC-Seg","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"DFNet","metrics":{"F-Score":"81.8"},"uses_additional_data":false,"paper_date":"2020-08-04","paper":"/paper/learning-discriminative-feature-with-crf-for","paper_url":"https://arxiv.org/abs/2008.01270v1","paper_title":"Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"Ours","metrics":{"Jaccard (Mean)":"83.4"},"uses_additional_data":false,"paper_date":"2020-08-04","paper":"/paper/learning-discriminative-feature-with-crf-for","paper_url":"https://arxiv.org/abs/2008.01270v1","paper_title":"Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"VOSwL (Mask+Language)","metrics":{"mIoU":"84.5"},"uses_additional_data":false,"paper_date":"2018-03-21","paper":"/paper/video-object-segmentation-with-language","paper_url":"http://arxiv.org/abs/1803.08006v3","paper_title":"Video Object Segmentation with Language Referring Expressions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"VOSwL (Language)","metrics":{"mIoU":"82.8"},"uses_additional_data":false,"paper_date":"2018-03-21","paper":"/paper/video-object-segmentation-with-language","paper_url":"http://arxiv.org/abs/1803.08006v3","paper_title":"Video Object Segmentation with Language Referring Expressions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"LOCATE","metrics":{"Contour Accuracy":"88.7","mIoU":"80.9"},"uses_additional_data":false,"paper_date":"2023-08-22","paper":"/paper/locate-self-supervised-object-discovery-via","paper_url":"https://arxiv.org/abs/2308.11239v3","paper_title":"LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training","code":"https://github.com/silky1708/locate","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":24,"model":"FODVid","metrics":{"mIoU":"78.71"},"uses_additional_data":false,"paper_date":"2023-07-10","paper":"/paper/fodvid-flow-guided-object-discovery-in-videos","paper_url":"https://arxiv.org/abs/2307.04392v1","paper_title":"FODVid: Flow-guided Object Discovery in Videos","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":13,"n_unverified":11,"n_samples":24,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":13,"n_samples":27,"n_pointer_only_licence":16,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}