{"url":"/task/interactive-video-object-segmentation","name":"Interactive Video Object Segmentation","slug":"interactive-video-object-segmentation","description_markdown":"The interactive scenario assumes the user gives iterative refinement inputs to the algorithm, in our case in the form of a scribble, to segment the objects of interest. Methods have to produce a segmentation mask for that object in all the frames of a video sequence taking into account all the user interactions.","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":16,"papers_with_code":9,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/interactive-video-object-segmentation-on","slug":"interactive-video-object-segmentation-on","dataset":"DAVIS 2017","dataset_url":"/dataset/davis-2017","rows_in_archive":7,"metrics":["AUC-J&F","J&F@60s","AUC-J","J@60s"],"first_row_in_archive_order":{"model":"MiVOS","paper_title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","paper_url":"/paper/modular-interactive-video-object-segmentation","paper_date":"2021-03-14","arxiv_id":"2103.07941","code_links":[{"title":"hkchengrex/MiVOS","url":"https://github.com/hkchengrex/MiVOS"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"hkchengrex/Scribble-to-Mask","url":"https://github.com/hkchengrex/Scribble-to-Mask"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"Vujas-Eteph/CiVOS","url":"https://github.com/Vujas-Eteph/CiVOS"}],"syntology":{"n":18,"n_ran":9,"n_unverified":9,"n_pointer_only":0}}}],"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/mose","name":"MOSE","full_name":"Complex Video Object Segmentation","num_papers_in_archive":49},{"url":"/dataset/bl30k","name":"BL30K","full_name":"","num_papers_in_archive":11},{"url":"/dataset/pumavos","name":"PUMaVOS","full_name":"Partial and Unusual Masks for Video Object Segmentation","num_papers_in_archive":2}],"subtasks":[],"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":9,"of":9,"tagged_in_all":16,"items":[{"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/interactive-video-object-segmentation-using","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","date":"2020-07-16","arxiv_id":"2007.08139","repositories_listed":4,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"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/segment-anything-meets-point-tracking","title":"Segment Anything Meets Point Tracking","date":"2023-07-03","arxiv_id":"2307.01197","repositories_listed":1,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/revisiting-click-based-interactive-video","title":"Revisiting Click-based Interactive Video Object Segmentation","date":"2022-03-03","arxiv_id":"2203.01784","repositories_listed":1,"syntology":null},{"url":"/paper/guided-interactive-video-object-segmentation","title":"Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps","date":"2021-04-21","arxiv_id":"2104.10386","repositories_listed":1,"syntology":{"n":15,"n_ran":6,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/learning-to-recommend-frame-for-interactive","title":"Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild","date":"2021-03-18","arxiv_id":"2103.10391","repositories_listed":1,"syntology":null},{"url":"/paper/fast-interactive-video-object-segmentation","title":"Fast Interactive Video Object Segmentation with Graph Neural Networks","date":"2021-03-05","arxiv_id":"2103.03821","repositories_listed":1,"syntology":null},{"url":"/paper/fast-user-guided-video-object-segmentation-by","title":"Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks","date":"2019-04-22","arxiv_id":"1904.09791","repositories_listed":1,"syntology":null}],"syntology_records":5,"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"}}