作者：Ruopeng Gao,Limin Wang

作者单位：南京大学新型软件技术国家重点实验室，上海人工智能实验室

发布时间：2023

发布期刊/会议：Arxiv

出版商：

**论文全称：**MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

论文地址：

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

论文代码：

https://github.com/MCG-NJU/MeMOTR

地位：

个人理解

• 为什么：
  • 现有的多目标跟踪方法大多只能在相邻帧之间明确利用目标特征，缺乏对长期时间信息的建模能力
• 创新点：
  • 提出了一种长期记忆增强的Transformer模型（MeMOTR）用于多目标跟踪。该方法通过使用定制的记忆-注意力层注入长期记忆，使得同一目标的跟踪嵌入更加稳定和可区分。这显著提高了模型的目标关联能力

一、摘要

As a video task, Multi-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-theart 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

• 大多数现有多目标跟踪方法仅显式地利用相邻帧之间的对象特征，而缺乏建模长期时间信息的能力
• 提出了**MeMOTR，**一种用于多目标跟踪的长期记忆增强 Transformer。
  • 通过使用自定义的记忆注意层来利用长期记忆注入（Long term memory injection），使同一对象的轨迹嵌入更加稳定和可区分，显著提高了模型的目标关联能力

二、MeMOTR