{"url":"/sota/semi-supervised-video-object-segmentation-on-15","task":{"name":"Semi-Supervised Video Object Segmentation","url":"/task/semi-supervised-video-object-segmentation","note":null},"dataset":{"name":"VOT2020","url":"/dataset/vot2020"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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.","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":["EAO","EAO (real-time)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"EAO":null,"EAO (real-time)":"lower"}},"counts":{"rows":20,"rows_with_code":19,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DAM4SAM","metrics":{"EAO":"0.729"},"uses_additional_data":false,"paper_date":"2024-11-26","paper":"/paper/a-distractor-aware-memory-for-visual-object","paper_url":"https://arxiv.org/abs/2411.17576v2","paper_title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","code":"https://github.com/jovanavidenovic/dam4sam","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":2,"model":"MCITrack-L384","metrics":{"EAO":"0.624"},"uses_additional_data":false,"paper_date":"2024-12-15","paper":"/paper/exploring-enhanced-contextual-information-for-1","paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","code":"https://github.com/kangben258/MCITrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"SwinB-DeAOT-L","metrics":{"EAO":"0.622","EAO (real-time)":"0.559"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"MCITrack-B224","metrics":{"EAO":"0.619"},"uses_additional_data":false,"paper_date":"2024-12-15","paper":"/paper/exploring-enhanced-contextual-information-for-1","paper_url":"https://arxiv.org/abs/2412.11023v1","paper_title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","code":"https://github.com/kangben258/MCITrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"R50-DeAOT-L","metrics":{"EAO":"0.613","EAO (real-time)":"0.571"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"ODTrack-L","metrics":{"EAO":"0.605"},"uses_additional_data":false,"paper_date":"2024-01-03","paper":"/paper/odtrack-online-dense-temporal-token-learning","paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","code":"https://github.com/gxnu-zhonglab/odtrack","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"DeAOT-S","metrics":{"EAO":"0.593","EAO (real-time)":"0.559"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"DeAOT-L","metrics":{"EAO":"0.591","EAO (real-time)":"0.554"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"SwinB-AOT-L","metrics":{"EAO":"0.586","EAO (real-time)":"0.523"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"ODTrack-B","metrics":{"EAO":"0.581"},"uses_additional_data":false,"paper_date":"2024-01-03","paper":"/paper/odtrack-online-dense-temporal-token-learning","paper_url":"https://arxiv.org/abs/2401.01686v1","paper_title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","code":"https://github.com/gxnu-zhonglab/odtrack","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"AOT-L","metrics":{"EAO":"0.574","EAO (real-time)":"0.560"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"DeAOT-B","metrics":{"EAO":"0.571","EAO (real-time)":"0.542"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"R50-AOT-L","metrics":{"EAO":"0.569","EAO (real-time)":"0.540"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"MixFormer-L","metrics":{"EAO":"0.555"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/mixformer-end-to-end-tracking-with-iterative-1","paper_url":"https://arxiv.org/abs/2203.11082v2","paper_title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","code":"https://github.com/MCG-NJU/MixFormer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"AOT-B","metrics":{"EAO":"0.541","EAO (real-time)":"0.533"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"RPT","metrics":{"EAO":"0.530","EAO (real-time)":"0.290"},"uses_additional_data":false,"paper_date":"2020-08-08","paper":"/paper/rpt-learning-point-set-representation-for","paper_url":"https://arxiv.org/abs/2008.03467v2","paper_title":"RPT: Learning Point Set Representation for Siamese Visual Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"AOT-S","metrics":{"EAO":"0.512","EAO (real-time)":"0.499"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"AlphaRef","metrics":{"EAO":"0.482","EAO (real-time)":"0.486"},"uses_additional_data":false,"paper_date":"2020-12-12","paper":"/paper/alpha-refine-boosting-tracking-performance-by-1","paper_url":"https://arxiv.org/abs/2012.06815v3","paper_title":"Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation","code":"https://github.com/MasterBin-IIAU/AlphaRefine","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"DeAOT-T","metrics":{"EAO":"0.472","EAO (real-time)":"0.463"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":20,"model":"AOT-T","metrics":{"EAO":"0.435","EAO (real-time)":"0.433"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+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":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":8,"n_samples":13,"n_pointer_only_licence":11,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":8,"n_samples":14,"n_pointer_only_licence":11,"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"}}}