Papers › One-Shot Video Object Segmentation

One-Shot Video Object Segmentation

16 Nov 2016CVPR 2017 7arXiv:1611.05198archive 2025-07-28

Sergi Caelles, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Laura Leal-Taixé, Daniel Cremers, Luc van Gool

This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Foreground SegmentationObjectSegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo SegmentationVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
One-shot visual object segmentation YouTube-VOS 2018 OSVOS F-Measure (Seen) 60.5 #1 of 2 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS F-measure (Decay) 15.0 #62 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS F-measure (Mean) 80.6 #62 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS F-measure (Recall) 92.6 #62 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS J&F 80.2 #62 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS Jaccard (Decay) 14.9 #62 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS Jaccard (Mean) 79.8 #62 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS Jaccard (Recall) 93.6 #62 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS F-measure (Decay) 19.8 #55 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS F-measure (Recall) 59.7 #55 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS J&F 50.9 #55 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS Jaccard (Decay) 19.2 #55 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS Jaccard (Mean) 47.0 #55 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS Jaccard (Recall) 52.1 #55 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS F-measure (Decay) 27.0 #73 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS F-measure (Mean) 63.9 #73 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS F-measure (Recall) 73.8 #73 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS J&F 60.25 #73 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS Jaccard (Decay) 26.1 #73 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS Jaccard (Mean) 56.6 #73 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS Jaccard (Recall) 63.8 #73 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube OSVOS mIoU 0.783 #3 of 5 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 OSVOS F-Measure (Seen) 60.5 #50 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 OSVOS F-Measure (Unseen) 60.7 #50 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 OSVOS Jaccard (Seen) 59.8 #50 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 OSVOS Jaccard (Unseen) 54.2 #50 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 OSVOS Overall 58.8 #50 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 OSVOS Speed (FPS) 0.10 #50 of 53 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OSVOS F-Measure (Seen) 60.5 #1 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OSVOS F-Measure (Unseen) 60.7 #1 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OSVOS O (Average of Measures) 58.8 #1 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections