Papers › SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

18 Nov 2024arXiv:2411.11922archive 2025-07-28

Cheng-Yen Yang, Hsiang-Wei Huang, Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang

The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects. Furthermore, the fixed-window memory approach in the original model does not consider the quality of memories selected to condition the image features for the next frame, leading to error propagation in videos. This paper introduces SAMURAI, an enhanced adaptation of SAM 2 specifically designed for visual object tracking. By incorporating temporal motion cues with the proposed motion-aware memory selection mechanism, SAMURAI effectively predicts object motion and refines mask selection, achieving robust, accurate tracking without the need for retraining or fine-tuning. SAMURAI operates in real-time and demonstrates strong zero-shot performance across diverse benchmark datasets, showcasing its ability to generalize without fine-tuning. In evaluations, SAMURAI achieves significant improvements in success rate and precision over existing trackers, with a 7.1% AUC gain on LaSOTₑₓₜ and a 3.5% AO gain on GOT-10k. Moreover, it achieves competitive results compared to fully supervised methods on LaSOT, underscoring its robustness in complex tracking scenarios and its potential for real-world applications in dynamic environments.

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="2411.11922")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

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

yangchris11/samurai 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

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 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.

1ran · our draft was wrong

Licence: 0 of the 1 sample 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 yangchris11/samurai. “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.

load_lasot_gt yangchris11/samurai/scripts/main_inference.py official repository ran · our draft was wrong Apache-2.0 (permissive) · fc2fcc0303a921c0 · report

Tasks

Object TrackingVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Object Tracking DiDi SAMURAI Tracking quality 0.680 #2 of 11 Archive leaderboard report
Visual Object Tracking GOT-10k SAMURAI-L Average Overlap 81.7 #1 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k SAMURAI-L Success Rate 0.5 92.2 #1 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k SAMURAI-L Success Rate 0.75 76.9 #1 of 42 Archive leaderboard report
Visual Object Tracking LaSOT SAMURAI-L AUC 74.2 #10 of 46 Archive leaderboard report
Visual Object Tracking LaSOT SAMURAI-L Normalized Precision 82.7 #10 of 46 Archive leaderboard report
Visual Object Tracking LaSOT SAMURAI-L Precision 80.2 #10 of 46 Archive leaderboard report
Visual Object Tracking LaSOT-ext SAMURAI-L AUC 61.0 #1 of 18 Archive leaderboard report
Visual Object Tracking LaSOT-ext SAMURAI-L Normalized Precision 73.9 #1 of 18 Archive leaderboard report
Visual Object Tracking LaSOT-ext SAMURAI-L Precision 72.2 #1 of 18 Archive leaderboard report
Visual Object Tracking NeedForSpeed SAMURAI-L AUC 0.692 #1 of 10 Archive leaderboard report
Visual Object Tracking OTB-2015 SAMURAI-L AUC 0.715 #5 of 18 Archive leaderboard report
Visual Object Tracking TrackingNet SAMURAI-L Accuracy 85.3 #14 of 40 Archive leaderboard report
Zero-Shot Single Object Tracking LaSOT SAMURAI-L AUC 74.2 #1 of 2 Archive leaderboard report
Zero-Shot Single Object Tracking LaSOT SAMURAI-L Normalized Precision 82.7 #1 of 2 Archive leaderboard report
Zero-Shot Single Object Tracking LaSOT SAMURAI-L Precision 80.2 #1 of 2 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

SAM

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