Papers › Towards Real-Time Multi-Object Tracking

Towards Real-Time Multi-Object Tracking

27 Sep 2019ECCV 2020 8arXiv:1909.12605archive 2025-07-28

Zhongdao Wang, Liang Zheng, Yixuan Liu, Ya-Li Li, Shengjin Wang

Modern multiple object tracking (MOT) systems usually follow the tracking-by-detection paradigm. It has 1) a detection model for target localization and 2) an appearance embedding model for data association. Having the two models separately executed might lead to efficiency problems, as the running time is simply a sum of the two steps without investigating potential structures that can be shared between them. Existing research efforts on real-time MOT usually focus on the association step, so they are essentially real-time association methods but not real-time MOT system. In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model. Specifically, we incorporate the appearance embedding model into a single-shot detector, such that the model can simultaneously output detections and the corresponding embeddings. We further propose a simple and fast association method that works in conjunction with the joint model. In both components the computation cost is significantly reduced compared with former MOT systems, resulting in a neat and fast baseline for future follow-ups on real-time MOT algorithm design. To our knowledge, this work reports the first (near) real-time MOT system, with a running speed of 22 to 40 FPS depending on the input resolution. Meanwhile, its tracking accuracy is comparable to the state-of-the-art trackers embodying separate detection and embedding (SDE) learning (64.4% MOTA \vs 66.1% MOTA on MOT-16 challenge). Code and models are available at https://github.com/Zhongdao/Towards-Realtime-MOT.

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

No sample from the archive's official repository (Zhongdao/Towards-Realtime-MOT) is linked to this paper; the 36 samples below come from 6 community repositories. Syntology harvested code from Zhongdao/Towards-Realtime-MOT for another paper.

Zhongdao/Towards-Realtime-MOT: Syntology's graph links these samples to Rethinking the competition between detection and ReID in Multi-Object Tracking (arXiv:2010.12138; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 36 code samples harvested from 6 repositories linked to this paper: 30 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 36 samples from 6 repositories, 30 ran (28 with no instrument failure; 2 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Zhongdao/Towards-Realtime-MOT officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking the competition between detection and ReID in Multi-Object Tracking (arXiv:2010.12138; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
JunweiLiang/Object_Detection_Tracking mentioned on GitHubtfMITSyntology: 9 samples, 9 ran (0 instrument-failed) · 0 unverified report
LKLQQ/JDE mentioned on GitHubmindsporeApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
ZhangwenguangHikvision/YoloV5_JDE_TensorRT_for_Track mentioned on GitHubMITSyntology: not harvested report
bellekci/Towards-Realtime-MOT-windows-py37 mentioned on GitHubpytorchMITSyntology: 12 samples, 11 ran (2 instrument-failed) · 1 unverified report
chandanrao007/https-github.com-Zhongdao-Towards-Realtime-MOT mentioned on GitHubpytorchMITSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
jh7cha/Towards-Real-Time-MOT mentioned on GitHubpytorchMITSyntology: not harvested report
junjieinkit/Towards-MOT mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
nemonameless/jde mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking the competition between detection and ReID in Multi-Object Tracking (arXiv:2010.12138; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
nvlong21/person_Counting mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
scuShaker/jde mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified 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

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

36 samples harvested: 30 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 2 where Syntology's instrument failed) · 6 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 · our draft was wrong
28ran
6unverified

Licence: 0 of the 36 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 6 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.

JunweiLiang/Object_Detection_Tracking community (archive-listed) 9 samples, 9 ran (0 instrument-failed) · 0 unverified
area in 13 papers efficientdet/object_detection/region_similarity_calculator.py ran MIT (permissive) · 19308c86a845d28f · report fixture: signature boxlist:BoxList/0/?, scope:NoneType/0/? · returned SymbolicTensor · level recorded 2026-09-24
assert_shape_equal efficientdet/object_detection/shape_utils.py ran MIT (permissive) · 6e7be223a1f327ee · report fixture: signature shape_a:list/1/int, shape_b:list/1/int · returned Operation · level recorded 2026-09-24
batch_decode efficientdet/object_detection/box_coder.py ran MIT (permissive) · be05a20e6474fd41 · report fixture: signature encoded_boxes:SymbolicTensor/3/float, box_coder:MinimalBoxCoder/0/?, anchors:MinimalBoxList/0/? · returned SymbolicTensor · level recorded 2026-09-24
combined_static_and_dynamic_shape efficientdet/object_detection/shape_utils.py ran MIT (permissive) · 9ecb69e61c558f70 · report fixture: signature tensor:SymbolicTensor/0/float · returned list · level recorded 2026-09-24
intersection in 24 papers efficientdet/object_detection/region_similarity_calculator.py ran MIT (permissive) · c1f2538016698cae · report fixture: signature boxlist1:BoxList/0/?, boxlist2:BoxList/0/?, scope:NoneType/0/? · returned SymbolicTensor · level recorded 2026-09-24
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
efficientdet/object_detection/region_similarity_calculator.py ran MIT (permissive) · 8d064f285ce3f976 · report fixture: signature boxlist1:BoxList/0/?, boxlist2:BoxList/0/?, scope:NoneType/0/? · returned SymbolicTensor · level recorded 2026-09-24
keypoint_flip_horizontal efficientdet/object_detection/preprocessor.py ran MIT (permissive) · 3f359173adba2211 · report fixture: signature keypoints:SymbolicTensor/3/float, flip_point:SymbolicTensor/0/float, flip_permutation:SymbolicTensor/1/int, scope:NoneType/0/? · returned SymbolicTensor · level recorded 2026-09-24
random_horizontal_flip efficientdet/object_detection/preprocessor.py ran MIT (permissive) · a4ffa78d04268fb8 · report fixture: signature image:SymbolicTensor/3/float, boxes:SymbolicTensor/2/float, masks:SymbolicTensor/3/float, keypoints:SymbolicTensor/3/float, keypoint_flip_permutation:SymbolicTensor/1/int, seed:int/0/int · returned tuple · level recorded 2026-09-24
resize_to_range efficientdet/object_detection/preprocessor.py ran MIT (permissive) · 64a5dd1bd79ece58 · report fixture: signature image:SymbolicTensor/3/float, masks:SymbolicTensor/3/float, min_dimension:int/0/int, max_dimension:int/0/int, method:int/0/int, align_corners:bool/0/bool, pad_to_max_dimension:bool/0/bool · returned list · level recorded 2026-09-24
LKLQQ/JDE community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
get_logger in 383 papers src/log.py ran Apache-2.0 (permissive) · 3d8013e60355dac6 · report fixture: signature name:str/0/str · returned Logger · level recorded 2026-09-24
letterbox in 14 papers src/dataset.py ran Apache-2.0 (permissive) · 8e2d6625f044925e · report fixture: signature img:ndarray/3/int, height:int/0/int, width:int/0/int, color:tuple/1/float · returned tuple · level recorded 2026-09-24
random_affine in 7 papers src/dataset.py ran Apache-2.0 (permissive) · b285f4ecc6e86819 · report fixture: signature img:ndarray/3/int, targets:ndarray/2/float, degrees:tuple/1/int, translate:tuple/1/float, scale:tuple/1/float, shear:tuple/1/int, border_value:tuple/1/float · returned tuple · level recorded 2026-09-24
read_mot_results in 6 papers src/io.py ran Apache-2.0 (permissive) · 5a4cdc2fdc88931d · report fixture: signature filename:str/0/str, is_gt:bool/0/bool, is_ignore:bool/0/bool · returned dict · level recorded 2026-09-24
read_results in 19 papers src/io.py ran Apache-2.0 (permissive) · 73a4841a44752305 · report fixture: signature filename:str/0/str, data_type:str/0/str, is_gt:bool/0/bool, is_ignore:bool/0/bool · returned dict · level recorded 2026-09-24
unzip_objs in 5 papers src/io.py ran Apache-2.0 (permissive) · 87448ae39d185e1d · report fixture: signature objs:list/1/tuple · returned tuple · level recorded 2026-09-24
bellekci/Towards-Realtime-MOT-windows-py37 community (archive-listed) 12 samples, 11 ran (2 instrument-failed) · 1 unverified
collate_fn in 500 papers utils/datasets.py ran MIT (permissive) · 7ca75b6abf5efc06 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-25
create_modules in 5 papers models.py ran MIT (permissive) · 07eea32450cfaaa8 · report fixture: signature module_defs:list/1/dict · returned tuple · level recorded 2026-09-24
joint_stracks in 8 papers tracker/multitracker.py ran · our draft was wrong MIT (permissive) · 557de671825f7887 · report fixture: signature tlista:list/1/Track, tlistb:list/1/Track · returned list · level recorded 2026-09-22
letterbox in 14 papers utils/datasets.py ran MIT (permissive) · 90caac012650cd20 · report fixture: signature img:ndarray/3/int, height:int/0/int, width:int/0/int, color:tuple/1/float · returned tuple · level recorded 2026-09-25
merge_matches in 5 papers tracker/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
prep_im_for_blob utils/blob.py ran MIT (permissive) · 80a039675aacc8e4 · report fixture: signature im:ndarray/3/int, pixel_means:ndarray/1/float, target_size:int/0/int, max_size:int/0/int · returned tuple · level recorded 2026-09-25
random_affine in 7 papers utils/datasets.py ran MIT (permissive) · 5e616815ca4cc1ed · report fixture: signature img:ndarray/3/int, targets:ndarray/2/float, degrees:tuple/1/int, translate:tuple/1/float, scale:tuple/1/float, shear:tuple/1/int, borderValue:tuple/1/float · returned tuple · level recorded 2026-09-25
read_mot_results in 6 papers utils/io.py ran MIT (permissive) · 9eb3b334fd02b5d3 · report fixture: signature filename:str/0/str, is_gt:bool/0/bool, is_ignore:bool/0/bool · returned dict · level recorded 2026-09-25
read_results in 19 papers utils/io.py ran MIT (permissive) · 1958a4fce355d7a6 · report fixture: signature filename:str/0/str, data_type:str/0/str, is_gt:bool/0/bool, is_ignore:bool/0/bool · returned dict · level recorded 2026-09-25
sub_stracks in 8 papers tracker/multitracker.py ran · our draft was wrong MIT (permissive) · 322ac55b144012cf · report fixture: signature tlista:list/1/Track, tlistb:list/1/Track · returned list · level recorded 2026-09-22
unzip_objs in 5 papers utils/io.py ran MIT (permissive) · 261a9c5fae0c1b9f · report fixture: signature objs:list/1/tuple · returned tuple · level recorded 2026-09-25
im_list_to_blob in 5 papers utils/blob.py unverified MIT (permissive) · 015af0d600124541 · report
chandanrao007/https-github.com-Zhongdao-Towards-Realtime-MOT community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
linear_assignment in 7 papers tracker/matching.py ran fingerprinted MIT (permissive) · fa0376e6b3c39f1b · report fixture: signature cost_matrix:ndarray/2/float, thresh:float/0/float · returned tuple · level recorded 2026-09-25
parse_data_cfg in 5 papers utils/parse_config.py ran MIT (permissive) · 5f1e6bf7cfe64409 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-25
parse_model_cfg in 5 papers utils/parse_config.py ran MIT (permissive) · 3931670f65ad9328 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
create_modules in 5 papers models.py unverified MIT (permissive) · 1d0ed55a31730d4a · report
shift_tensor_vertically models.py unverified MIT (permissive) · 9eb6a59860b08148 · report
junjieinkit/Towards-MOT community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
count_files video2frame.py ran MIT (permissive) · bb052fa2b8d379a2 · report fixture: signature path:str/0/str, filename_starts_with:str/0/str · returned int · level recorded 2026-09-24
annotate_frames video2frame.py unverified MIT (permissive) · 87899348c83dbe05 · report
split_video video2frame.py unverified MIT (permissive) · 3a10dc1e599ea6a7 · report
scuShaker/jde community (archive-listed) 1 sample, 0 ran · 1 unverified
create_modules in 5 papers models.py unverified MIT (permissive) · afc666065e74d2cf · report

Tasks

Multi-Object TrackingMulti-Task LearningMultiple Object TrackingObjectObject TrackingReal-Time Multi-Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking HiEve JDE IDF1 36.0 #4 of 4 Archive leaderboard report
Multi-Object Tracking HiEve JDE MOTA 33.1 #4 of 4 Archive leaderboard report
Multi-Object Tracking MOT16 JDE MOTA 64.4 #14 of 24 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