Papers › Siam R-CNN: Visual Tracking by Re-Detection

Siam R-CNN: Visual Tracking by Re-Detection

28 Nov 2019CVPR 2020 6arXiv:1911.12836archive 2025-07-28

Paul Voigtlaender, Jonathon Luiten, Philip H. S. Torr, Bastian Leibe

We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking. We combine this with a novel tracklet-based dynamic programming algorithm, which takes advantage of re-detections of both the first-frame template and previous-frame predictions, to model the full history of both the object to be tracked and potential distractor objects. This enables our approach to make better tracking decisions, as well as to re-detect tracked objects after long occlusion. Finally, we propose a novel hard example mining strategy to improve Siam R-CNN's robustness to similar looking objects. Siam R-CNN achieves the current best performance on ten tracking benchmarks, with especially strong results for long-term tracking. We make our code and models available at www.vision.rwth-aachen.de/page/siamrcnn.

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 4 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 4 samples from 1 repository, 2 ran (2 with no instrument failure; 0 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.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

VisualComputingInstitute/SiamR-CNN tfMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified 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

4 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

2ran
2unverified

Licence: 0 of the 4 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 VisualComputingInstitute/SiamR-CNN. “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.

VisualComputingInstitute/SiamR-CNN community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
box_to_point8 common.py ran fingerprinted MIT (permissive) · dd749a6b43682a14 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-24
point8_to_box common.py ran fingerprinted MIT (permissive) · e99bbed8ef483eba · report fixture: signature points:ndarray/2/float · returned ndarray · level recorded 2026-09-24
freeze_affine_getter basemodel.py unverified MIT (permissive) · 69d5512d768ea9dd · report
segmentation_to_mask common.py unverified MIT (permissive) · 72f76b2aba37ad06 · report

Tasks

ObjectObject DetectionObject TrackingSemi-Supervised Video Object SegmentationVisual Object TrackingVisual Trackingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Tracking COESOT SiamR-CNN Precision Rate 67.5 #5 of 12 Archive leaderboard report
Object Tracking COESOT SiamR-CNN Success Rate 60.9 #5 of 12 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Siam R-CNN F-measure (Decay) 4.0 #63 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Siam R-CNN F-measure (Mean) 80.4 #63 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Siam R-CNN F-measure (Recall) 87.6 #63 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Siam R-CNN J&F 78.6 #63 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Siam R-CNN Jaccard (Decay) 2.2 #63 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Siam R-CNN Jaccard (Mean) 76.8 #63 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Siam R-CNN Jaccard (Recall) 86.4 #63 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) Siam R-CNN F-measure (Decay) 20.2 #50 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) Siam R-CNN F-measure (Mean) 58.6 #50 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) Siam R-CNN F-measure (Recall) 62.3 #50 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) Siam R-CNN J&F 53.3 #50 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) Siam R-CNN Jaccard (Decay) 21.8 #50 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) Siam R-CNN Jaccard (Mean) 48.0 #50 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) Siam R-CNN Jaccard (Recall) 53.9 #50 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) Siam R-CNN F-measure (Decay) 16.2 #60 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) Siam R-CNN F-measure (Mean) 75.0 #60 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) Siam R-CNN F-measure (Recall) 82.8 #60 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) Siam R-CNN J&F 70.55 #60 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) Siam R-CNN Jaccard (Decay) 15.8 #60 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) Siam R-CNN Jaccard (Mean) 66.1 #60 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) Siam R-CNN Jaccard (Recall) 74.8 #60 of 81 Archive leaderboard report
Visual Object Tracking GOT-10k Siam R-CNN Average Overlap 64.9 #33 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k Siam R-CNN Success Rate 0.5 72.8 #33 of 42 Archive leaderboard report
Visual Object Tracking LaSOT Siam R-CNN AUC 64.8 #38 of 46 Archive leaderboard report
Visual Object Tracking LaSOT Siam R-CNN Normalized Precision 72.2 #38 of 46 Archive leaderboard report
Visual Object Tracking TrackingNet Siam R-CNN Accuracy 81.2 #28 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet Siam R-CNN Normalized Precision 85.4 #28 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet Siam R-CNN Precision 80.0 #28 of 40 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