Papers › YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

3 Sep 2018ECCV 2018 9arXiv:1809.00461archive 2025-07-28

Ning Xu, Linjie Yang, Yuchen Fan, Jianchao Yang, Dingcheng Yue, Yuchen Liang, Brian Price, Scott Cohen, Thomas Huang

Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods capturing temporal dependency for segmentation have to depend on pretrained optical flow models, leading to suboptimal solutions for the problem. End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i.e., even the largest video segmentation dataset only contains 90 short video clips. To solve this problem, we build a new large-scale video object segmentation dataset called YouTube Video Object Segmentation dataset (YouTube-VOS). Our dataset contains 3,252 YouTube video clips and 78 categories including common objects and human activities. This is by far the largest video object segmentation dataset to our knowledge and we have released it at https://youtube-vos.org. Based on this dataset, we propose a novel sequence-to-sequence network to fully exploit long-term spatial-temporal information in videos for segmentation. We demonstrate that our method is able to achieve the best results on our YouTube-VOS test set and comparable results on DAVIS 2016 compared to the current state-of-the-art methods. Experiments show that the large scale dataset is indeed a key factor to the success of our model.

PaperPDFConference PDFCode

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

Code

BehradToghi/ConvLSTM_VOS mentioned on GitHubtf report
BehradToghi/ECCV_Youtube_VOS mentioned on GitHubtf report
T-a-g-z/Yotube-VOS-OVS mentioned on GitHubtf report

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

Image SegmentationObjectOne-shot visual object segmentationOptical Flow EstimationSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic SegmentationVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 S2S F-Measure (Seen) 70.0 #48 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 S2S F-Measure (Unseen) 61.2 #48 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 S2S Jaccard (Seen) 71.0 #48 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 S2S Overall 64.4 #48 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 S2S Speed (FPS) 55.5 #48 of 53 Archive leaderboard report
Video Object Segmentation YouTube-VOS 2018 S2S (offline) F-Measure (Unseen) 50.3 #17 of 17 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