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

Ruopeng Gao, Limin Wang
2/14/2026

No official code found. Best implementation: MCG-NJU/MeMOTR (236 stars, MIT, last commit 2025-10-15).

Abstract

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 longterm 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.

View on arXivView PDF

Code Implementations(1)

MCG-NJU/MeMOTRCommunity100%
MIT

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

23622C++, CudaAug 3, 20231 years agoMIT
computer-visiondeep-learningmulti-object-trackingtracking

Similar Papers

MambaLCT: Boosting Tracking via Long-term Context State Space Model

86% match1 repo252024

Long-Term Visual Object Tracking with Event Cameras: An Associative Memory Augmented Tracker and A Benchmark Dataset

86% match1 repo402024

TF-SASM: Training-free Spatial-aware Sparse Memory for Multi-object Tracking

86% match2024

Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation

85% match2024

Spatio-temporal Graph Learning on Adaptive Mined Key Frames for High-performance Multi-Object Tracking

85% match2025

STCMOT: Spatio-Temporal Cohesion Learning for UAV-Based Multiple Object Tracking

85% match1 repo322024

Cite this paper

@article{gao2026memotr,
  title  = {MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking},
  author = {Ruopeng Gao and Limin Wang},
  year   = {2026},
  eprint = {2307.15700},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2307.15700},
  journal = {ICCV 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.15700.svg)](https://codeofpaper.com/paper/2307.15700)

Discussion