Papers › RVOS: End-to-End Recurrent Network for Video Object Segmentation

RVOS: End-to-End Recurrent Network for Video Object Segmentation

13 Mar 2019CVPR 2019 6arXiv:1903.05612archive 2025-07-28

Carles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador, Ferran Marques, Xavier Giro-i-Nieto

Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU.

PaperPDFConference PDFCode

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

Code

imatge-upc/rvos officialpytorchNOASSERTION 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

ObjectOne-shot visual object segmentationSegmentationSemi-Supervised Video Object SegmentationUnsupervised Video Object SegmentationVideo Object Segmentation

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
One-shot visual object segmentation YouTube-VOS RVOS-Mask-ST+ F-Measure (Seen) 67.2 #1 of 1 Archive leaderboard report
One-shot visual object segmentation YouTube-VOS RVOS-Mask-ST+ F-Measure (Unseen) 51 #1 of 1 Archive leaderboard report
One-shot visual object segmentation YouTube-VOS RVOS-Mask-ST+ Jaccard (Seen) 63.6 #1 of 1 Archive leaderboard report
One-shot visual object segmentation YouTube-VOS RVOS-Mask-ST+ Jaccard (Unseen) 45.5 #1 of 1 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS F-measure (Decay) 36.7 #56 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS F-measure (Mean) 52.6 #56 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS F-measure (Recall) 61.7 #56 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS J&F 50.3 #56 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS Jaccard (Decay) 35.7 #56 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS Jaccard (Mean) 47.9 #56 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS Jaccard (Recall) 54.4 #56 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RVOS F-measure (Decay) 28.2 #72 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RVOS F-measure (Mean) 63.6 #72 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RVOS F-measure (Recall) 73.2 #72 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RVOS J&F 60.55 #72 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RVOS Jaccard (Decay) 24.9 #72 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RVOS Jaccard (Mean) 57.5 #72 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RVOS Jaccard (Recall) 65.2 #72 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RVOS F-Measure (Seen) 67.2 #51 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RVOS F-Measure (Unseen) 51.0 #51 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RVOS Jaccard (Seen) 63.6 #51 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RVOS Overall 56.8 #51 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RVOS Speed (FPS) 45.5 #51 of 53 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS F-measure (Decay) 1.8 #6 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS F-measure (Mean) 27.3 #6 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS F-measure (Recall) 24.8 #6 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS J&F 22.5 #6 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS Jaccard (Decay) 1.6 #6 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS Jaccard (Mean) 17.7 #6 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) RVOS Jaccard (Recall) 16.2 #6 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) RVOS F-measure (Mean) 45.7 #10 of 10 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) RVOS F-measure (Recall) 46.4 #10 of 10 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) RVOS J&F 41.2 #10 of 10 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) RVOS Jaccard (Mean) 36.8 #10 of 10 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) RVOS Jaccard (Recall) 40.2 #10 of 10 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