{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tukey-inspired-video-object-segmentation","title":"Tukey-Inspired Video Object Segmentation","arxiv_id":"1811.07958","date":"2018-11-19","proceeding":null,"authors":["Brent A. Griffin","Jason J. Corso"],"abstract":"We investigate the problem of strictly unsupervised video object\nsegmentation, i.e., the separation of a primary object from background in video\nwithout a user-provided object mask or any training on an annotated dataset. We\nfind foreground objects in low-level vision data using a John Tukey-inspired\nmeasure of \"outlierness\". This Tukey-inspired measure also estimates the\nreliability of each data source as video characteristics change (e.g., a camera\nstarts moving). The proposed method achieves state-of-the-art results for\nstrictly unsupervised video object segmentation on the challenging DAVIS\ndataset. Finally, we use a variant of the Tukey-inspired measure to combine the\noutput of multiple segmentation methods, including those using supervision\nduring training, runtime, or both. This collectively more robust method of\nsegmentation improves the Jaccard measure of its constituent methods by as much\nas 28%.","url_abs":"http://arxiv.org/abs/1811.07958v2","url_pdf":"http://arxiv.org/pdf/1811.07958v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tukey-inspired-video-object-segmentation","repo_url":"https://github.com/griffbr/TIS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"tukey-inspired-video-object-segmentation","repo_url":"https://github.com/griffbr/VOSVS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}