Papers › MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation

MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation

17 Apr 2019CVPR 2019 6arXiv:1904.08141archive 2025-07-28

Shuangjie Xu, Daizong Liu, Linchao Bao, Wei Liu, Pan Zhou

We address the problem of semi-supervised video object segmentation (VOS), where the masks of objects of interests are given in the first frame of an input video. To deal with challenging cases where objects are occluded or missing, previous work relies on greedy data association strategies that make decisions for each frame individually. In this paper, we propose a novel approach to defer the decision making for a target object in each frame, until a global view can be established with the entire video being taken into consideration. Our approach is in the same spirit as Multiple Hypotheses Tracking (MHT) methods, making several critical adaptations for the VOS problem. We employ the bounding box (bbox) hypothesis for tracking tree formation, and the multiple hypotheses are spawned by propagating the preceding bbox into the detected bbox proposals within a gated region starting from the initial object mask in the first frame. The gated region is determined by a gating scheme which takes into account a more comprehensive motion model rather than the simple Kalman filtering model in traditional MHT. To further design more customized algorithms tailored for VOS, we develop a novel mask propagation score instead of the appearance similarity score that could be brittle due to large deformations. The mask propagation score, together with the motion score, determines the affinity between the hypotheses during tree pruning. Finally, a novel mask merging strategy is employed to handle mask conflicts between objects. Extensive experiments on challenging datasets demonstrate the effectiveness of the proposed method, especially in the case of object missing.

PaperPDFConference PDFCode

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

Code

shuangjiexu/MHP-VOS officialmentioned in papermentioned on GitHubpytorch 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

Decision MakingObjectSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2016 MHP-VOS F-measure (Decay) 9.0 #40 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MHP-VOS F-measure (Mean) 89.5 #40 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MHP-VOS F-measure (Recall) 95.5 #40 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MHP-VOS J&F 88.55 #40 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MHP-VOS Jaccard (Decay) 6.9 #40 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MHP-VOS Jaccard (Mean) 87.6 #40 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MHP-VOS Jaccard (Recall) 97.3 #40 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MHP-VOS F-measure (Decay) 19.1 #41 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MHP-VOS F-measure (Mean) 72.7 #41 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MHP-VOS F-measure (Recall) 82.3 #41 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MHP-VOS J&F 69.5 #41 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MHP-VOS Jaccard (Decay) 18.0 #41 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MHP-VOS Jaccard (Mean) 66.4 #41 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MHP-VOS Jaccard (Recall) 76.0 #41 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MHP-VOS F-measure (Decay) 19.1 #54 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MHP-VOS F-measure (Mean) 78.9 #54 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MHP-VOS F-measure (Recall) 87.2 #54 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MHP-VOS J&F 76.15 #54 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MHP-VOS Jaccard (Decay) 17.8 #54 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MHP-VOS Jaccard (Mean) 73.4 #54 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MHP-VOS Jaccard (Recall) 83.5 #54 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