Papers › Track to Detect and Segment: An Online Multi-Object Tracker

Track to Detect and Segment: An Online Multi-Object Tracker

16 Mar 2021CVPR 2021 1arXiv:2103.08808archive 2025-07-28

Jialian Wu, Jiale Cao, Liangchen Song, Yu Wang, Ming Yang, Junsong Yuan

Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment), exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features for improving current object detection and segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets, including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS (instance segmentation tracking). Project page: https://jialianwu.com/projects/TraDeS.html.

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="2103.08808")

Code

Syntology Ran 4 of 4 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

JialianW/TraDeS officialmentioned 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

4 samples harvested; 4 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.

3ran · our draft was wrong
1ran

Licence: 0 of the 4 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 JialianW/TraDeS. “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.

CostVolumeLoss1D JialianW/TraDeS/src/lib/model/losses.py official repository ran MIT (permissive) · 73050dc5b6e34509 · report
_gather_feat JialianW/TraDeS/src/lib/model/losses.py official repository ran · our draft was wrong MIT (permissive) · e1ccb8546b47ae19 · report
_only_neg_loss JialianW/TraDeS/src/lib/model/losses.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 81d2bca3ba7f29f1 · report
_tranpose_and_gather_feat_1d JialianW/TraDeS/src/lib/model/losses.py official repository ran · our draft was wrong MIT (permissive) · 065423f71a6e4e6d · report

Tasks

3D Multi-Object TrackingInstance SegmentationMulti-Object TrackingObjectObject DetectionObject TrackingOnline Multi-Object TrackingSegmentationSemantic SegmentationVideo Instance Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation nuScenes TraDeS MOTA 68.2 #1 of 1 Archive leaderboard report
Multi-Object Tracking DanceTrack TraDes AssA 25.4 #35 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack TraDes DetA 74.5 #35 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack TraDes HOTA 43.3 #35 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack TraDes IDF1 41.2 #35 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack TraDes MOTA 86.2 #35 of 37 Archive leaderboard report
Multi-Object Tracking MOT15 Baseline+MFW MOTA 66.5 #1 of 2 Archive leaderboard report
Multi-Object Tracking MOT16 TraDeS IDF1 64.7 #9 of 24 Archive leaderboard report
Multi-Object Tracking MOT16 TraDeS MOTA 70.1 #9 of 24 Archive leaderboard report
Multi-Object Tracking MOT17 TraDeS IDF1 63.9 #34 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 TraDeS MOTA 69.1 #34 of 48 Archive leaderboard report
Multi-Object Tracking MOTS20 TraDes IDF1 58.7 #5 of 6 Archive leaderboard report
Multi-Object Tracking MOTS20 TraDes sMOTSA 50.8 #5 of 6 Archive leaderboard report
Online Multi-Object Tracking MOT16 TraDeS MOTA 67.7 #2 of 5 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation TraDeS AP50 52.6 #37 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation TraDeS AP75 32.8 #37 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation TraDeS mask AP 32.6 #37 of 44 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: TraDeS

TraDeS

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