Papers › PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation

PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation

24 Jul 2018arXiv:1807.09190archive 2025-07-28

Jonathon Luiten, Paul Voigtlaender, Bastian Leibe

We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations. Towards this goal, we present the PReMVOS algorithm (Proposal-generation, Refinement and Merging for Video Object Segmentation). Our method separates this problem into two steps, first generating a set of accurate object segmentation mask proposals for each video frame and then selecting and merging these proposals into accurate and temporally consistent pixel-wise object tracks over a video sequence in a way which is designed to specifically tackle the difficult challenges involved with segmenting multiple objects across a video sequence. Our approach surpasses all previous state-of-the-art results on the DAVIS 2017 video object segmentation benchmark with a J & F mean score of 71.6 on the test-dev dataset, and achieves first place in both the DAVIS 2018 Video Object Segmentation Challenge and the YouTube-VOS 1st Large-scale Video Object Segmentation Challenge.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1807.09190")

Code

Syntology Ran 3 of 15 code samples harvested from 2 repositories linked to this paper; 12 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: community (archive-listed): 12 samples from 2 repositories, 0 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

AyaLotfy/PReMVOS-trial mentioned on GitHubtfMIT report
AyaLotfy/premvos-tmp mentioned on GitHubtfMIT report
JonathonLuiten/PReMVOS mentioned on GitHubtfMIT report
gunpowder78/PReMVOS mentioned on GitHubtfMIT 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

15 samples harvested; 3 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
12unverified

Licence: 3 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

average_gradients AyaLotfy/PReMVOS-trial/code/ReID_net/Util.py community (archive-listed) unverified MIT (permissive) · d82c26b8b96a063f · report
bbox2 AyaLotfy/PReMVOS-trial/code/ReID_net/prepare_input.py community (archive-listed) unverified MIT (permissive) · 3d9a814bfc32150c · report
clip_gradients AyaLotfy/PReMVOS-trial/code/ReID_net/Util.py community (archive-listed) unverified MIT (permissive) · fe9c62a98e81d5ca · report
compute_binary_ious_tf AyaLotfy/PReMVOS-trial/code/ReID_net/Measures.py community (archive-listed) unverified MIT (permissive) · 68d695364fd9f0ca · report
compute_ious AyaLotfy/PReMVOS-trial/code/ReID_net/Interface.py community (archive-listed) unverified MIT (permissive) · b92ab02e58b761db · report
create_confusion_matrix AyaLotfy/PReMVOS-trial/code/ReID_net/Measures.py community (archive-listed) unverified MIT (permissive) · c463048a0a86251e · report
detection_extractor AyaLotfy/PReMVOS-trial/code/ReID_net/Interface.py community (archive-listed) unverified MIT (permissive) · 8a0a002fa0a8e01b · report
extract AyaLotfy/PReMVOS-trial/code/MergeTrack/refinement_net_functions.py community (archive-listed) unverified MIT (permissive) · 1ea937ed7f4c6dbb · report
get_average_precision AyaLotfy/PReMVOS-trial/code/ReID_net/Measures.py community (archive-listed) unverified MIT (permissive) · 9746592ab02ab201 · report
load_detections VisualComputingInstitute/mots_trackingonly_tools/io_utils.py community (archive-listed) unverified MIT (permissive) · 99b934888578c83a · report
load_detections_for_seq VisualComputingInstitute/mots_trackingonly_tools/io_utils.py community (archive-listed) unverified MIT (permissive) · 093913a1b1c9347a · report
load_seqmap VisualComputingInstitute/mots_trackingonly_tools/io_utils.py community (archive-listed) unverified MIT (permissive) · 24124b92fe9f5ae2 · report
conv identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 2d0cae2c772e2af4 · report
deconv identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · dc4fb7628379691e · report
predict_flow identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · c3f23a008d953af5 · report

Tasks

ObjectOne-shot visual object segmentationSegmentationSemantic 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 PReMVOS F-measure (Decay) 9.8 #46 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 PReMVOS F-measure (Mean) 88.6 #46 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 PReMVOS F-measure (Recall) 94.7 #46 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 PReMVOS J&F 86.75 #46 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 PReMVOS Jaccard (Decay) 8.8 #46 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 PReMVOS Jaccard (Mean) 84.9 #46 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 PReMVOS Jaccard (Recall) 96.1 #46 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) PReMVOS F-measure (Decay) 20.6 #40 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) PReMVOS F-measure (Mean) 75.8 #40 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) PReMVOS F-measure (Recall) 84.3 #40 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) PReMVOS J&F 71.6 #40 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) PReMVOS Jaccard (Decay) 21.7 #40 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) PReMVOS Jaccard (Mean) 67.5 #40 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) PReMVOS Jaccard (Recall) 76.8 #40 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) PReMVOS F-measure (Decay) 19.5 #48 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) PReMVOS F-measure (Mean) 81.8 #48 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) PReMVOS F-measure (Recall) 88.9 #48 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) PReMVOS J&F 77.85 #48 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) PReMVOS Jaccard (Decay) 16.2 #48 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) PReMVOS Jaccard (Mean) 73.9 #48 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) PReMVOS Jaccard (Recall) 83.1 #48 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