Papers › STMTrack: Template-free Visual Tracking with Space-time Memory Networks

STMTrack: Template-free Visual Tracking with Space-time Memory Networks

1 Apr 2021CVPR 2021 1arXiv:2104.00324archive 2025-07-28

Zhihong Fu, Qingjie Liu, Zehua Fu, Yunhong Wang

Boosting performance of the offline trained siamese trackers is getting harder nowadays since the fixed information of the template cropped from the first frame has been almost thoroughly mined, but they are poorly capable of resisting target appearance changes. Existing trackers with template updating mechanisms rely on time-consuming numerical optimization and complex hand-designed strategies to achieve competitive performance, hindering them from real-time tracking and practical applications. In this paper, we propose a novel tracking framework built on top of a space-time memory network that is competent to make full use of historical information related to the target for better adapting to appearance variations during tracking. Specifically, a novel memory mechanism is introduced, which stores the historical information of the target to guide the tracker to focus on the most informative regions in the current frame. Furthermore, the pixel-level similarity computation of the memory network enables our tracker to generate much more accurate bounding boxes of the target. Extensive experiments and comparisons with many competitive trackers on challenging large-scale benchmarks, OTB-2015, TrackingNet, GOT-10k, LaSOT, UAV123, and VOT2018, show that, without bells and whistles, our tracker outperforms all previous state-of-the-art real-time methods while running at 37 FPS. The code is available at https://github.com/fzh0917/STMTrack.

PaperPDFConference PDFCodeCode 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="2104.00324")

Code

Syntology Ran 8 of 11 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 6 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

fzh0917/STMTrack 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

11 samples harvested; 8 ran; 0 honoured the contract we drafted; 3 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.

6ran · our draft was wrong
2ran
3unverified

Licence: 0 of the 11 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 fzh0917/STMTrack. “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.

Registry fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran BSD-3-Clause (permissive) · 3f950a5c3a805857 · report
conv_bn_relu fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran fingerprinted BSD-3-Clause (permissive) · f2bebbb153632753 · report
filter_reused_missing_keys fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · f05dd1f0fbc22a83 · report
get_missing_parameters_message fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · afa2b03cb5dc9dbe · report
get_unexpected_parameters_message fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · ea09e35f7d4ca931 · report
group_checkpoint_keys fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · 289de134af2bd65d · report
md5sum fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · df35e234671d8855 · report
named_modules_with_dup fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · 07588af5a652bf1f · report
ModuleBase fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository unverified BSD-3-Clause (permissive) · aafaacd38dc55bcb · report
STMTrack fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository unverified BSD-3-Clause (permissive) · ccee80e86f38a6bc · report
_register_generic fzh0917/STMTrack/videoanalyst/model/task_model/taskmodel_impl/stmtrack_model.py official repository unverified BSD-3-Clause (permissive) · 42a153ed65fc5b82 · report

Tasks

Video Object TrackingVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Tracking NT-VOT211 STMTrack AUC 36.84 #12 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 STMTrack Precision 50.34 #12 of 43 Archive leaderboard report
Visual Object Tracking GOT-10k STMTrack Average Overlap 64.2 #35 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k STMTrack Success Rate 0.5 73.7 #35 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k STMTrack Success Rate 0.75 57.5 #35 of 42 Archive leaderboard report
Visual Object Tracking OTB-2015 STMTrack AUC 0.719 #4 of 18 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

Memory Network

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