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 \emph{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 \url{https://github.com/Zhongdao/Towards-Realtime-MOT}.

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="1909.12605")

Code

Syntology Ran 2 of 36 code samples harvested from 6 repositories linked to this paper; 34 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: community (archive-listed): 36 samples from 6 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Zhongdao/Towards-Realtime-MOT officialmentioned in papermentioned on GitHubpytorchMIT report
LKLQQ/JDE mentioned on GitHubmindsporeApache-2.0 report
bellekci/Towards-Realtime-MOT-windows-py37 mentioned on GitHubpytorchMIT report
jh7cha/Towards-Real-Time-MOT mentioned on GitHubpytorchMIT report
junjieinkit/Towards-MOT mentioned on GitHubpytorchMIT report
nemonameless/jde mentioned on GitHubpytorchMIT report
nvlong21/person_Counting mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
scuShaker/jde mentioned on GitHubpytorchMIT 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

36 samples harvested; 2 ran; 0 honoured the contract we drafted; 34 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.

2ran · our draft was wrong
34unverified

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; each sample names its own and says which. “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.

joint_stracks bellekci/Towards-Realtime-MOT-windows-py37/tracker/multitracker.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 557de671825f7887 · report
sub_stracks bellekci/Towards-Realtime-MOT-windows-py37/tracker/multitracker.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 322ac55b144012cf · report
annotate_frames junjieinkit/Towards-MOT/video2frame.py community (archive-listed) unverified MIT (permissive) · 87899348c83dbe05 · report
area JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/region_similarity_calculator.py community (archive-listed) unverified MIT (permissive) · 19308c86a845d28f · report
assert_shape_equal JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/shape_utils.py community (archive-listed) unverified MIT (permissive) · 6e7be223a1f327ee · report
batch_decode JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/box_coder.py community (archive-listed) unverified MIT (permissive) · be05a20e6474fd41 · report
collate_fn bellekci/Towards-Realtime-MOT-windows-py37/utils/datasets.py community (archive-listed) unverified MIT (permissive) · 7ca75b6abf5efc06 · report
combined_static_and_dynamic_shape JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/shape_utils.py community (archive-listed) unverified MIT (permissive) · 9ecb69e61c558f70 · report
count_files junjieinkit/Towards-MOT/video2frame.py community (archive-listed) unverified MIT (permissive) · bb052fa2b8d379a2 · report
create_modules chandanrao007/https-github.com-Zhongdao-Towards-Realtime-MOT/models.py community (archive-listed) unverified MIT (permissive) · 1d0ed55a31730d4a · report
create_modules scuShaker/jde/models.py community (archive-listed) unverified MIT (permissive) · afc666065e74d2cf · report
create_modules bellekci/Towards-Realtime-MOT-windows-py37/models.py community (archive-listed) unverified MIT (permissive) · 07eea32450cfaaa8 · report
get_logger LKLQQ/JDE/src/log.py community (archive-listed) unverified Apache-2.0 (permissive) · 3d8013e60355dac6 · report
im_list_to_blob bellekci/Towards-Realtime-MOT-windows-py37/utils/blob.py community (archive-listed) unverified MIT (permissive) · 015af0d600124541 · report
intersection JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/region_similarity_calculator.py community (archive-listed) unverified MIT (permissive) · c1f2538016698cae · report
iou JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/region_similarity_calculator.py community (archive-listed) unverified MIT (permissive) · 8d064f285ce3f976 · report
keypoint_flip_horizontal JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/preprocessor.py community (archive-listed) unverified MIT (permissive) · 3f359173adba2211 · report
letterbox bellekci/Towards-Realtime-MOT-windows-py37/utils/datasets.py community (archive-listed) unverified MIT (permissive) · 90caac012650cd20 · report
letterbox LKLQQ/JDE/src/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · 8e2d6625f044925e · report
linear_assignment chandanrao007/https-github.com-Zhongdao-Towards-Realtime-MOT/tracker/matching.py community (archive-listed) unverified MIT (permissive) · fa0376e6b3c39f1b · report
merge_matches bellekci/Towards-Realtime-MOT-windows-py37/tracker/matching.py community (archive-listed) unverified MIT (permissive) · de19615aab6efe36 · report
parse_data_cfg chandanrao007/https-github.com-Zhongdao-Towards-Realtime-MOT/utils/parse_config.py community (archive-listed) unverified MIT (permissive) · 5f1e6bf7cfe64409 · report
parse_model_cfg chandanrao007/https-github.com-Zhongdao-Towards-Realtime-MOT/utils/parse_config.py community (archive-listed) unverified MIT (permissive) · 3931670f65ad9328 · report
prep_im_for_blob bellekci/Towards-Realtime-MOT-windows-py37/utils/blob.py community (archive-listed) unverified MIT (permissive) · 80a039675aacc8e4 · report
random_affine bellekci/Towards-Realtime-MOT-windows-py37/utils/datasets.py community (archive-listed) unverified MIT (permissive) · 5e616815ca4cc1ed · report
random_affine LKLQQ/JDE/src/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · b285f4ecc6e86819 · report
random_horizontal_flip JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/preprocessor.py community (archive-listed) unverified MIT (permissive) · a4ffa78d04268fb8 · report
read_mot_results bellekci/Towards-Realtime-MOT-windows-py37/utils/io.py community (archive-listed) unverified MIT (permissive) · 9eb3b334fd02b5d3 · report
read_mot_results LKLQQ/JDE/src/io.py community (archive-listed) unverified Apache-2.0 (permissive) · 5a4cdc2fdc88931d · report
read_results bellekci/Towards-Realtime-MOT-windows-py37/utils/io.py community (archive-listed) unverified MIT (permissive) · 1958a4fce355d7a6 · report
read_results LKLQQ/JDE/src/io.py community (archive-listed) unverified Apache-2.0 (permissive) · 73a4841a44752305 · report
resize_to_range JunweiLiang/Object_Detection_Tracking/efficientdet/object_detection/preprocessor.py community (archive-listed) unverified MIT (permissive) · 64a5dd1bd79ece58 · report
shift_tensor_vertically chandanrao007/https-github.com-Zhongdao-Towards-Realtime-MOT/models.py community (archive-listed) unverified MIT (permissive) · 9eb6a59860b08148 · report
split_video junjieinkit/Towards-MOT/video2frame.py community (archive-listed) unverified MIT (permissive) · 3a10dc1e599ea6a7 · report
unzip_objs bellekci/Towards-Realtime-MOT-windows-py37/utils/io.py community (archive-listed) unverified MIT (permissive) · 261a9c5fae0c1b9f · report
unzip_objs LKLQQ/JDE/src/io.py community (archive-listed) unverified Apache-2.0 (permissive) · 87448ae39d185e1d · 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