Papers › Video Object Segmentation Without Temporal Information

Video Object Segmentation Without Temporal Information

18 Sep 2017arXiv:1709.06031archive 2025-07-28

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

Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames. When the temporal smoothness is suddenly broken, such as when an object is occluded, or some frames are missing in a sequence, the result of these methods can deteriorate significantly or they may not even produce any result at all. This paper explores the orthogonal approach of processing each frame independently, i.e disregarding the temporal information. In particular, it tackles the task of semi-supervised video object segmentation: the separation of an object from the background in a video, given its mask in the first frame. We present Semantic One-Shot Video Object Segmentation (OSVOS-S), 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). We show that instance level semantic information, when combined effectively, can dramatically improve the results of our previous method, OSVOS. We perform experiments on two recent video segmentation databases, which show that OSVOS-S is both the fastest and most accurate method in the state of the art.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Foreground SegmentationObjectSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS-S F-measure (Decay) 8.2 #47 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS-S F-measure (Mean) 87.5 #47 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS-S F-measure (Recall) 95.9 #47 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS-S J&F 86.55 #47 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS-S Jaccard (Decay) 5.5 #47 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS-S Jaccard (Mean) 85.6 #47 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OSVOS-S Jaccard (Recall) 96.8 #47 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS-S F-measure (Decay) 21.9 #48 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS-S F-measure (Mean) 62.1 #48 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS-S F-measure (Recall) 70.5 #48 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS-S J&F 57.5 #48 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS-S Jaccard (Decay) 24.1 #48 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS-S Jaccard (Mean) 52.9 #48 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OSVOS-S Jaccard (Recall) 60.2 #48 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS-S F-measure (Decay) 18.5 #63 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS-S F-measure (Mean) 71.3 #63 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS-S F-measure (Recall) 80.7 #63 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS-S J&F 68 #63 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS-S Jaccard (Decay) 15.1 #63 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS-S Jaccard (Mean) 64.7 #63 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OSVOS-S Jaccard (Recall) 74.2 #63 of 81 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