Papers › Tracking Objects as Points

Tracking Objects as Points

2 Apr 2020ECCV 2020 8arXiv:2004.01177archive 2025-07-28

Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection. In this paper, we present a simultaneous detection and tracking algorithm that is simpler, faster, and more accurate than the state of the art. Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. Given this minimal input, CenterTrack localizes objects and predicts their associations with the previous frame. That's it. CenterTrack is simple, online (no peeking into the future), and real-time. It achieves 67.3% MOTA on the MOT17 challenge at 22 FPS and 89.4% MOTA on the KITTI tracking benchmark at 15 FPS, setting a new state of the art on both datasets. CenterTrack is easily extended to monocular 3D tracking by regressing additional 3D attributes. Using monocular video input, it achieves 28.3% AMOTA@0.2 on the newly released nuScenes 3D tracking benchmark, substantially outperforming the monocular baseline on this benchmark while running at 28 FPS.

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="2004.01177")

Code

Syntology Ran 4 of 16 code samples harvested from 3 repositories linked to this paper; 12 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 1 ran; community (archive-listed): 11 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xingyizhou/CenterTrack officialmentioned in papermentioned on GitHubpytorchMIT report
Feynman1999/MgeEditing mentioned on GitHub report
JialianW/TraDeS mentioned on GitHubpytorch report
danielzgsilva/MOT mentioned on GitHubpytorch report
hampen2929/CenterTrack mentioned on GitHubpytorchMIT report
qa276390/searchtrack 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

16 samples harvested; 4 ran; 0 honoured the contract we drafted; 12 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.

3ran · our draft was wrong
1ran
12unverified

Licence: 0 of the 16 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 3 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.

load_model xingyizhou/CenterTrack/src/lib/model/model.py official repository ran · our draft was wrong MIT (permissive) · d7425309b038c87c · report
DataParallel xingyizhou/CenterTrack/src/lib/model/data_parallel.py official repository unverified MIT (permissive) · ddb5a5004c8da97a · report
compute_rot_loss xingyizhou/CenterTrack/src/lib/model/losses.py official repository unverified MIT (permissive) · 8accefa95d8419ec · report
data_parallel xingyizhou/CenterTrack/src/lib/model/data_parallel.py official repository unverified MIT (permissive) · 61bf3906cbd2ee87 · report
generic_decode xingyizhou/CenterTrack/src/lib/model/decode.py official repository unverified MIT (permissive) · 7c992af205c8aa75 · report
compute_bin_loss qa276390/searchtrack/src/lib/model/losses.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 65d7a40d70c53ed9 · report
compute_res_loss qa276390/searchtrack/src/lib/model/losses.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 7df13fb9e54d592b · report
parse_dynamic_params qa276390/searchtrack/src/lib/model/decode.py community (archive-listed) ran MIT (permissive) · 46f34dc9f9a94b67 · report
gen_nan_mat hampen2929/CenterTrack/notebook/CenterTrack.py community (archive-listed) unverified MIT (permissive) · 8deded4e22a90040 · report
get_images hampen2929/CenterTrack/notebook/util.py community (archive-listed) unverified MIT (permissive) · e5ab43a0ed3a9d85 · report
get_json_file_paths hampen2929/CenterTrack/notebook/util.py community (archive-listed) unverified MIT (permissive) · 2e11ec34b5533614 · report
load_json hampen2929/CenterTrack/notebook/util.py community (archive-listed) unverified MIT (permissive) · f0654f3740c34713 · report
load_model qa276390/searchtrack/src/lib/model/model.py community (archive-listed) unverified MIT (permissive) · b0dcae8d7c7f7659 · report
ltrb_amodal_decode qa276390/searchtrack/src/lib/model/decode.py community (archive-listed) unverified MIT (permissive) · 581674d14c6feb31 · report
queue hampen2929/CenterTrack/notebook/CenterTrack.py community (archive-listed) unverified MIT (permissive) · 53c06df9693423cb · report
wh_decode qa276390/searchtrack/src/lib/model/decode.py community (archive-listed) unverified MIT (permissive) · a8979ecac7a82a7c · report

Tasks

Multi-Object TrackingMultiple Object TrackingObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack CenterTrack AssA 22.6 #36 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack CenterTrack DetA 78.1 #36 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack CenterTrack HOTA 41.8 #36 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack CenterTrack IDF1 35.7 #36 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack CenterTrack MOTA 86.8 #36 of 37 Archive leaderboard report
Multi-Object Tracking SportsMOT CenterTrack AssA 48.0 #19 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT CenterTrack DetA 82.1 #19 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT CenterTrack HOTA 62.7 #19 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT CenterTrack IDF1 60.0 #19 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT CenterTrack MOTA 90.8 #19 of 22 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) CenterTrack HOTA 73.02 #15 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) CenterTrack MOTA 89.44 #15 of 34 Archive leaderboard report
Multiple Object Tracking SportsMOT CenterTrack AssA 48.0 #17 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT CenterTrack DetA 82.1 #17 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT CenterTrack HOTA 62.7 #17 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT CenterTrack IDF1 60.0 #17 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT CenterTrack MOTA 90.8 #17 of 19 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

Introduced by this paper: CenterTrack

CenterTrack

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