{"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/one-shot-video-object-segmentation","title":"One-Shot Video Object Segmentation","arxiv_id":"1611.05198","date":"2016-11-16","proceeding":"CVPR 2017 7","authors":["Sergi Caelles","Kevis-Kokitsi Maninis","Jordi Pont-Tuset","Laura Leal-Taixé","Daniel Cremers","Luc van Gool"],"abstract":"This paper tackles the task of semi-supervised video object segmentation,\ni.e., the separation of an object from the background in a video, given the\nmask of the first frame. We present One-Shot Video Object Segmentation (OSVOS),\nbased on a fully-convolutional neural network architecture that is able to\nsuccessively transfer generic semantic information, learned on ImageNet, to the\ntask of foreground segmentation, and finally to learning the appearance of a\nsingle annotated object of the test sequence (hence one-shot). Although all\nframes are processed independently, the results are temporally coherent and\nstable. We perform experiments on two annotated video segmentation databases,\nwhich show that OSVOS is fast and improves the state of the art by a\nsignificant margin (79.8% vs 68.0%).","url_abs":"http://arxiv.org/abs/1611.05198v4","url_pdf":"http://arxiv.org/pdf/1611.05198v4.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":"one-shot-video-object-segmentation","repo_url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/OSVOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"one-shot-video-object-segmentation","repo_url":"https://github.com/MS-Mind/MS-Code-06/tree/main/OSVOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"one-shot-video-object-segmentation","repo_url":"https://github.com/Mind23-2/MindCode-5/tree/main/OSVOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"one-shot-video-object-segmentation","repo_url":"https://github.com/code-implementation1/Code6/tree/main/OSVOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"one-shot-video-object-segmentation","repo_url":"https://github.com/kmaninis/OSVOS-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"one-shot-video-object-segmentation","repo_url":"https://github.com/kmaninis/OSVOS-caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"one-shot-video-object-segmentation","repo_url":"https://github.com/scaelles/OSVOS-TensorFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"one-shot-video-object-segmentation","repo_url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/OSVOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"foreground-segmentation","task_name":"Foreground Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/one-shot-visual-object-segmentation-on","task":"One-shot visual object segmentation","dataset":"YouTube-VOS 2018","model":"OSVOS","rank_in_archive_order":1,"of":2,"metrics":{"F-Measure (Seen)":"60.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"OSVOS","rank_in_archive_order":62,"of":78,"metrics":{"F-measure (Decay)":"15.0","F-measure (Mean)":"80.6","F-measure (Recall)":"92.6","J&F":"80.2","Jaccard (Decay)":"14.9","Jaccard (Mean)":"79.8","Jaccard (Recall)":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"OSVOS","rank_in_archive_order":55,"of":59,"metrics":{"F-measure (Decay)":"19.8","F-measure (Recall)":"59.7","J&F":"50.9","Jaccard (Decay)":"19.2","Jaccard (Mean)":"47.0","Jaccard (Recall)":"52.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"OSVOS","rank_in_archive_order":73,"of":81,"metrics":{"F-measure (Decay)":"27.0","F-measure (Mean)":"63.9","F-measure (Recall)":"73.8","J&F":"60.25","Jaccard (Decay)":"26.1","Jaccard (Mean)":"56.6","Jaccard (Recall)":"63.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube","model":"OSVOS","rank_in_archive_order":3,"of":5,"metrics":{"mIoU":"0.783"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"OSVOS","rank_in_archive_order":50,"of":53,"metrics":{"F-Measure (Seen)":"60.5","F-Measure (Unseen)":"60.7","Jaccard (Seen)":"59.8","Jaccard (Unseen)":"54.2","Overall":"58.8","Speed  (FPS)":"0.10"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-youtube-vos","task":"Visual Object Tracking","dataset":"YouTube-VOS 2018","model":"OSVOS","rank_in_archive_order":1,"of":9,"metrics":{"F-Measure (Seen)":"60.5","F-Measure (Unseen)":"60.7","O (Average of Measures)":"58.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.05198","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}