Papers › CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing

CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing

30 Sep 2019ICCV 2019 10arXiv:1910.00132archive 2025-07-28

Kevin Duarte, Yogesh S Rawat, Mubarak Shah

In this work we propose a capsule-based approach for semi-supervised video object segmentation. Current video object segmentation methods are frame-based and often require optical flow to capture temporal consistency across frames which can be difficult to compute. To this end, we propose a video based capsule network, CapsuleVOS, which can segment several frames at once conditioned on a reference frame and segmentation mask. This conditioning is performed through a novel routing algorithm for attention-based efficient capsule selection. We address two challenging issues in video object segmentation: 1) segmentation of small objects and 2) occlusion of objects across time. The issue of segmenting small objects is addressed with a zooming module which allows the network to process small spatial regions of the video. Apart from this, the framework utilizes a novel memory module based on recurrent networks which helps in tracking objects when they move out of frame or are occluded. The network is trained end-to-end and we demonstrate its effectiveness on two benchmark video object segmentation datasets; it outperforms current offline approaches on the Youtube-VOS dataset while having a run-time that is almost twice as fast as competing methods. The code is publicly available at https://github.com/KevinDuarte/CapsuleVOS.

PaperPDFConference PDFCode

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

Code

KevinDuarte/CapsuleVOS officialmentioned in papermentioned 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

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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CapsuleVOS F-measure (Mean) 55.2 #54 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CapsuleVOS F-measure (Recall) 64.6 #54 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CapsuleVOS J&F 51.3 #54 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CapsuleVOS Jaccard (Mean) 47.4 #54 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CapsuleVOS Jaccard (Recall) 54.1 #54 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CapsuleVOS F-Measure (Seen) 68.1 #49 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CapsuleVOS F-Measure (Unseen) 59.9 #49 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CapsuleVOS Jaccard (Seen) 67.3 #49 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CapsuleVOS Jaccard (Unseen) 53.7 #49 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CapsuleVOS Overall 62.3 #49 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CapsuleVOS Speed (FPS) 13.5 #49 of 53 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