Papers › Fast Online Object Tracking and Segmentation: A Unifying Approach

Fast Online Object Tracking and Segmentation: A Unifying Approach

12 Dec 2018CVPR 2019 6arXiv:1812.05050archive 2025-07-28

Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H. S. Torr

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017. The project website is http://www.robots.ox.ac.uk/~qwang/SiamMask.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 10 samples from 1 repository, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

ezelikman/anonymal mentioned on GitHubpytorchMITSyntology: 10 samples, 6 ran (1 instrument-failed) · 4 unverified report
foolwood/SiamMask mentioned on GitHubpytorchMITSyntology: not harvested report
shallowtoil/DROL mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks (arXiv:1812.11703; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

10 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
5ran
4unverified

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ezelikman/anonymal. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ezelikman/anonymal community (archive-listed) 10 samples, 6 ran (1 instrument-failed) · 4 unverified
conv2d_dw_group models/rpn.py ran fingerprinted MIT (permissive) · ed07034dd18cfc8f · report fixture: signature x:Tensor/4/float, kernel:Tensor/4/float · returned Tensor · level recorded 2026-09-26
conv3x3 in 1,376 papers experiments/siammask_base/resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
get_cls_loss in 7 papers models/siamrpn.py ran MIT (permissive) · 3f1957b700e9ed16 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int, select:Tensor/1/int · returned Tensor · level recorded 2026-09-25
get_cls_loss in 7 papers models/siammask.py ran MIT (permissive) · ef70c620a00de25b · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int, select:Tensor/1/int · returned Tensor · level recorded 2026-09-26
select_cross_entropy_loss in 6 papers models/siammask.py ran fingerprinted MIT (permissive) · 8c846e3850e50c54 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int · returned Tensor · level recorded 2026-09-26
select_cross_entropy_loss in 6 papers models/siamrpn.py ran fingerprinted MIT (permissive) · 2d85fa7671a85da4 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int · returned Tensor · level recorded 2026-09-26
crop_hwc datasets/siam_mask_dataset.py unverified MIT (permissive) · 3be374ea8fee76b5 · report
resnet18 in 432 papers experiments/siammask_sharp/resnet.py unverified MIT (permissive) · 02b73f913b091c75 · report
resnet34 in 148 papers experiments/siammask_sharp/resnet.py unverified MIT (permissive) · 82928ae508d22d28 · report
weight_l1_loss models/siammask.py unverified MIT (permissive) · 27f3175caf7f84b6 · report

Tasks

ObjectObject TrackingReal-Time Visual TrackingSegmentationSemi-Supervised Semantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Object TrackingVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2016 SiamMask F-measure (Decay) 2.1 #70 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 SiamMask F-measure (Mean) 67.8 #70 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 SiamMask F-measure (Recall) 79.8 #70 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 SiamMask J&F 69.75 #70 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 SiamMask Jaccard (Decay) 3.0 #70 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 SiamMask Jaccard (Mean) 71.7 #70 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 SiamMask Jaccard (Recall) 86.8 #70 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) SiamMask F-measure (Decay) 22.4 #58 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) SiamMask F-measure (Mean) 45.8 #58 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) SiamMask F-measure (Recall) 45.3 #58 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) SiamMask J&F 43.2 #58 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) SiamMask Jaccard (Decay) 21.9 #58 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) SiamMask Jaccard (Mean) 40.6 #58 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) SiamMask Jaccard (Recall) 44.5 #58 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SiamMask F-measure (Decay) 20.9 #76 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SiamMask F-measure (Mean) 58.5 #76 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SiamMask F-measure (Recall) 67.5 #76 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SiamMask J&F 56.4 #76 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SiamMask Jaccard (Decay) 19.3 #76 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SiamMask Jaccard (Mean) 54.3 #76 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SiamMask Jaccard (Recall) 62.8 #76 of 81 Archive leaderboard report
Video Object Tracking NT-VOT211 SiamMask AUC 35.14 #22 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 SiamMask Precision 46.49 #22 of 43 Archive leaderboard report
Visual Object Tracking VOT2017/18 SiamMask Expected Average Overlap (EAO) 0.380 #8 of 15 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 SiamMask F-Measure (Seen) 58.2 #3 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 SiamMask F-Measure (Unseen) 47.7 #3 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 SiamMask Jaccard (Seen) 54.3 #3 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 SiamMask Jaccard (Unseen) 45.1 #3 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 SiamMask O (Average of Measures) 52.8 #3 of 9 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.

Methods

SPEED

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