Papers › ByteTrack: Multi-Object Tracking by Associating Every Detection Box

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

13 Oct 2021arXiv 2021 10arXiv:2110.06864archive 2025-07-28

Yifu Zhang, Peize Sun, Yi Jiang, Dongdong Yu, Fucheng Weng, Zehuan Yuan, Ping Luo, Wenyu Liu, Xinggang Wang

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. The objects with low detection scores, e.g. occluded objects, are simply thrown away, which brings non-negligible true object missing and fragmented trajectories. To solve this problem, we present a simple, effective and generic association method, tracking by associating almost every detection box instead of only the high score ones. For the low score detection boxes, we utilize their similarities with tracklets to recover true objects and filter out the background detections. When applied to 9 different state-of-the-art trackers, our method achieves consistent improvement on IDF1 score ranging from 1 to 10 points. To put forwards the state-of-the-art performance of MOT, we design a simple and strong tracker, named ByteTrack. For the first time, we achieve 80.3 MOTA, 77.3 IDF1 and 63.1 HOTA on the test set of MOT17 with 30 FPS running speed on a single V100 GPU. ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks. The source code, pre-trained models with deploy versions and tutorials of applying to other trackers are released at https://github.com/ifzhang/ByteTrack.

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 12 code samples harvested from 2 repositories linked to this paper: 10 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; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 6 ran (6 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ifzhang/ByteTrack officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (1 instrument-failed) · 2 unverified report
2023-MindSpore-1/ms-code-28 mentioned on GitHubmindsporeSyntology: not harvested report
HaojunYuPKU/MOT_detectron mentioned on GitHubpytorchSyntology: not harvested report
Robotmurlock/Motrack mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Multi-Object Tracking Baselines: Hyperparameter Optimization with... (arXiv:2609.12261; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
levinwil/MulteTrack mentioned on GitHubpytorchMITSyntology: not harvested report
levinwil/MyteTrack mentioned on GitHubpytorchMITSyntology: not harvested report
mikel-brostrom/boxmot mentioned on GitHubpytorchAGPL-3.0Syntology: not harvested report
wuhengliangliang/ByteTrack mentioned on GitHubmindsporeSyntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
kadirnar/bytetrack-pip MITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 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.

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

12 samples harvested: 10 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; 1 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 last changed ; 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
9ran
2unverified

Licence: 1 of the 12 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ifzhang/ByteTrack official repository 6 samples, 4 ran (1 instrument-failed) · 2 unverified
clip_boxes in 10 papers yolox/motdt_tracker/reid_model.py ran fingerprinted MIT (permissive) · b5a232fabf1662a3 · report fixture: signature boxes:ndarray/2/float, im_shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
get_activation in 218 papers yolox/models/network_blocks.py ran · our draft was wrong MIT (permissive) · 6e3d5f4c3ce305d7 · report fixture: signature name:str/0/str, inplace:bool/0/bool · returned SiLU · level recorded 2026-09-26
make_layers in 155 papers yolox/deepsort_tracker/reid_model.py ran MIT (permissive) · c0b3d0e6e5a858ad · report fixture: signature c_in:int/0/int, c_out:int/0/int, repeat_times:int/0/int, is_downsample:bool/0/bool · returned Sequential · level recorded 2026-09-25
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
yolox/models/losses.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 774f31ba06110943 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-24
load_net in 10 papers yolox/motdt_tracker/reid_model.py unverified MIT (permissive) · f817f88d2e7ca234 · report
load_reid_model yolox/motdt_tracker/reid_model.py unverified MIT (permissive) · 8002b7c39cb1946f · report
kadirnar/bytetrack-pip community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
ious bytetracker/matching.py ran MIT (permissive) · eaec7fd70e56f5c1 · report fixture: signature atlbrs:list/1/list, btlbrs:list/1/list · returned ndarray · level recorded 2026-09-24
linear_assignment in 7 papers bytetracker/matching.py ran fingerprinted MIT (permissive) · 23b675d2fae7c414 · report fixture: signature cost_matrix:ndarray/2/float, thresh:float/0/float · returned tuple · level recorded 2026-09-24
merge_matches in 5 papers bytetracker/matching.py ran MIT (permissive) · de19615aab6efe36 · report fixture: signature m1:ndarray/2/int, m2:ndarray/2/int, shape:tuple/1/int · returned tuple · level recorded 2026-09-25
xywh2xyxy in 11 papers bytetracker/byte_tracker.py ran fingerprinted MIT (permissive) · 868ee4234d591b9d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
xyxy2ltwh bytetracker/byte_tracker.py ran fingerprinted MIT (permissive) · 98eb5091f9b29b36 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
xyxy2xywh in 19 papers bytetracker/byte_tracker.py ran fingerprinted MIT (permissive) · a4670e5c22212ec4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24

Tasks

Multi-Object TrackingMultiple Object TrackingObjectObject Tracking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack ByteTrack AssA 31.5 #32 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack ByteTrack DetA 70.5 #32 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack ByteTrack HOTA 47.1 #32 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack ByteTrack IDF1 51.9 #32 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack ByteTrack MOTA 88.2 #32 of 37 Archive leaderboard report
Multi-Object Tracking MOT17 ByteTrack HOTA 63.1 #15 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 ByteTrack IDF1 77.3 #15 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 ByteTrack MOTA 80.3 #15 of 48 Archive leaderboard report
Multi-Object Tracking MOT20 ByteTrack HOTA 61.3 #13 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 ByteTrack IDF1 75.2 #13 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 ByteTrack MOTA 77.8 #13 of 27 Archive leaderboard report
Multi-Object Tracking SportsMOT ByteTrack AssA 52.3 #18 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT ByteTrack DetA 78.5 #18 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT ByteTrack HOTA 64.1 #18 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT ByteTrack IDF1 71.4 #18 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT ByteTrack MOTA 95.9 #18 of 22 Archive leaderboard report
Multiple Object Tracking BDD100K test ByteTrack mIDF1 55.8 #3 of 5 Archive leaderboard report
Multiple Object Tracking BDD100K test ByteTrack mMOTA 40.1 #3 of 5 Archive leaderboard report
Multiple Object Tracking BDD100K val ByteTrack AssocA 51.5 #1 of 9 Archive leaderboard report
Multiple Object Tracking BDD100K val ByteTrack TETA 55.7 #1 of 9 Archive leaderboard report
Multiple Object Tracking BDD100K val ByteTrack mIDF1 54.8 #1 of 9 Archive leaderboard report
Multiple Object Tracking BDD100K val ByteTrack mMOTA 45.5 #1 of 9 Archive leaderboard report
Multiple Object Tracking SportsMOT ByteTrack AssA 52.3 #16 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT ByteTrack DetA 78.5 #16 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT ByteTrack HOTA 64.1 #16 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT ByteTrack IDF1 71.4 #16 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT ByteTrack MOTA 95.9 #16 of 19 Archive leaderboard report
Object Tracking QuadTrack ByteTrack HOTA 20.66 #4 of 8 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

(2+1)D ConvolutionSPEEDTest

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