作者：Jiarui Cai， Mingze Xu， Wei Li， Yuanjun Xiong， Wei Xia， Zhuowen Tu， Stefano Soatto，

作者单位：University of Washington(华盛顿大学)，AWS AI Labs

发布时间：2022

发布期刊/会议：CVPR

论文全称：MeMot : Multi-Object Tracking with Memory

论文地址：

论文代码：

地位：

个人理解

• 创新点：使用一个很大的时空内存来保存跟踪对象的身份嵌入信息（需要很大的显存）
• 为什么：设计更加优越的多目标跟踪模型
• 怎么做：提出了一个基于Transformer的跟踪模型——MeMOT，
• 个人想法：使用了8张 Tesla A100 GPUs（平均一张售价20w ￥），这是用钱跑出来的性能！

一、摘要

We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core information from the memory for each tracked object; and 3) Memory Decoding that solves the object detection and data association tasks simultaneously for multi-object tracking. When evaluated on widely adopted MOT benchmark datasets, MeMOT observes very competitive performance.

• 本文提出了一种在线跟踪模型——MeMOT，该模型能够同时完成目标检测任务和数据关联任务。