Papers › MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

28 Jul 2023ICCV 2023 1arXiv:2307.15700archive 2025-07-28

Ruopeng Gao, LiMin Wang

As a video task, Multiple Object Tracking (MOT) is expected to capture temporal information of targets effectively. Unfortunately, most existing methods only explicitly exploit the object features between adjacent frames, while lacking the capacity to model long-term temporal information. In this paper, we propose MeMOTR, a long-term memory-augmented Transformer for multi-object tracking. Our method is able to make the same object's track embedding more stable and distinguishable by leveraging long-term memory injection with a customized memory-attention layer. This significantly improves the target association ability of our model. Experimental results on DanceTrack show that MeMOTR impressively surpasses the state-of-the-art method by 7.9% and 13.0% on HOTA and AssA metrics, respectively. Furthermore, our model also outperforms other Transformer-based methods on association performance on MOT17 and generalizes well on BDD100K. Code is available at https://github.com/MCG-NJU/MeMOTR.

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="2307.15700")

Code

Syntology Ran 10 of 14 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mcg-nju/memotr officialmentioned in papermentioned 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

14 samples harvested; 10 ran; 0 honoured the contract we drafted; 4 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
7ran
4unverified

Licence: 0 of the 14 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 MCG-NJU/MeMOTR. “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.

BackboneWithPE MCG-NJU/MeMOTR/models/memotr.py official repository ran MIT (permissive) · 3b4766dc8db5676c · report
DeformableEncoder MCG-NJU/MeMOTR/models/memotr.py official repository ran MIT (permissive) · 6f70643bd82efe2a · report
MLP MCG-NJU/MeMOTR/models/memotr.py official repository ran MIT (permissive) · dffc33ac23b8e8c7 · report
NestedTensor MCG-NJU/MeMOTR/models/memotr.py official repository ran MIT (permissive) · 9e000b2a48eac77c · report
TrackInstances MCG-NJU/MeMOTR/models/memotr.py official repository ran MIT (permissive) · 3b24f29e53388fbe · report
eval_model mcg-nju/memotr/eval_engine.py official repository ran MIT (permissive) · 871c3d5d01b0c75a · report
get_activation_layer MCG-NJU/MeMOTR/models/memotr.py official repository ran · our draft was wrong MIT (permissive) · d58a53879397eff0 · report
get_clones MCG-NJU/MeMOTR/models/memotr.py official repository ran · our draft was wrong MIT (permissive) · d48189dd4977ee78 · report
inverse_sigmoid MCG-NJU/MeMOTR/models/memotr.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · bd7d1844c78a5ac3 · report
sigmoid_focal_loss mcg-nju/memotr/models/criterion.py official repository ran MIT (permissive) · a542c79696b8b5ae · report
DeformableEncoderLayer MCG-NJU/MeMOTR/models/memotr.py official repository unverified MIT (permissive) · e2c30130f6dac006 · report
DeformableTransformer MCG-NJU/MeMOTR/models/memotr.py official repository unverified MIT (permissive) · a825241e0a1aed5b · report
MeMOTR MCG-NJU/MeMOTR/models/memotr.py official repository unverified MIT (permissive) · 51c349d5ad7507ea · report
build mcg-nju/memotr/models/deformable_transformer.py official repository unverified MIT (permissive) · 8302d68a2f073468 · report

Tasks

Multi-Object TrackingMultiple Object TrackingObjectObject Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack MeMOTR AssA 58.4 #8 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR DetA 80.5 #8 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR HOTA 68.5 #8 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR IDF1 71.2 #8 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR MOTA 89.9 #8 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR (Deformable DETR) AssA 52.3 #16 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR (Deformable DETR) DetA 77.0 #16 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR (Deformable DETR) HOTA 63.4 #16 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR (Deformable DETR) IDF1 65.5 #16 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack MeMOTR (Deformable DETR) MOTA 85.4 #16 of 37 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR AssA 59.1 #14 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR DetA 83.1 #14 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR HOTA 70.0 #14 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR IDF1 71.4 #14 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR MOTA 91.5 #14 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR (Deformable-DETR) AssA 57.8 #16 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR (Deformable-DETR) DetA 82.0 #16 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR (Deformable-DETR) HOTA 68.8 #16 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR (Deformable-DETR) IDF1 69.9 #16 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT MeMOTR (Deformable-DETR) MOTA 90.2 #16 of 22 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR AssA 59.1 #13 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR DetA 83.1 #13 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR HOTA 70.0 #13 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR IDF1 71.4 #13 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR MOTA 91.5 #13 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR (Deformable-DETR) AssA 57.8 #14 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR (Deformable-DETR) DetA 82.0 #14 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR (Deformable-DETR) HOTA 68.8 #14 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR (Deformable-DETR) IDF1 69.9 #14 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT MeMOTR (Deformable-DETR) MOTA 90.2 #14 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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