{"url":"/sota/unsupervised-video-object-segmentation-on-3","task":{"name":"Unsupervised Video Object Segmentation","url":"/task/unsupervised-video-object-segmentation","note":null},"dataset":{"name":"SegTrack v2","url":"/dataset/segtrack-v2-1"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The unsupervised scenario assumes that the user does not interact with the algorithm to obtain the segmentation masks. Methods should provide a set of object candidates with no overlapping pixels that span through the whole video sequence. This set of objects should contain at least the objects that capture human attention when watching the whole video sequence i.e objects that are more likely to be followed by human gaze.","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":["Mean IoU","Jaccard (Mean)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean IoU":"higher","Jaccard (Mean)":null}},"counts":{"rows":4,"rows_with_code":3,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"FrameSelect","metrics":{"Mean IoU":"72.2"},"uses_additional_data":false,"paper_date":"2021-01-05","paper":"/paper/mask-selection-and-propagation-for","paper_url":"https://openaccess.thecvf.com/content/WACV2021/html/Garg_Mask_Selection_and_Propagation_for_Unsupervised_Video_Object_Segmentation_WACV_2021_paper.html","paper_title":"Mask Selection and Propagation for Unsupervised Video Object Segmentation","code":"https://github.com/vidit98/FrameSelect","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"EpO+","metrics":{"Mean IoU":"70.9"},"uses_additional_data":false,"paper_date":"2019-09-29","paper":"/paper/exploiting-geometric-constraints-on-dense","paper_url":"https://arxiv.org/abs/1909.13258v2","paper_title":"EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency","code":"https://github.com/mfaisal59/EpONet","n_code_links":3,"syntology":null},{"rank_in_archive_order":3,"model":"LVO","metrics":{"Mean IoU":"57.3"},"uses_additional_data":false,"paper_date":"2017-04-19","paper":"/paper/learning-video-object-segmentation-with","paper_url":"http://arxiv.org/abs/1704.05737v2","paper_title":"Learning Video Object Segmentation with Visual Memory","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"SSL-VOS","metrics":{"Jaccard (Mean)":"74.9"},"uses_additional_data":false,"paper_date":"2022-09-19","paper":"/paper/a-simple-and-powerful-global-optimization-for","paper_url":"https://arxiv.org/abs/2209.09341v2","paper_title":"A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation","code":"https://github.com/ponimatkin/ssl-vos","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0}}],"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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0,"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"}}}