The transformer neural network architecture allows for autoregressive
sequence-to-sequence modeling through the use of attention layers. It was
originally created with the application of machine translation but has
revolutionized natural language processing. Recently, transformers have also
been applied across a wide variety of pattern recognition tasks, particularly
in computer vision. In this literature review, we describe major advances in
computer vision utilizing transformers. We then focus specifically on
Multi-Object Tracking (MOT) and discuss how transformers are increasingly
becoming competitive in state-of-the-art MOT works, yet still lag behind
traditional deep learning methods.

transformer 神经网络结构通过注意力机制实现自回归的序列到序列建模，在自然语言处理和计算机视觉等领域取得了重大突破。本文综述了在计算机视觉领域中应用 transformer 的主要进展，并针对多目标跟踪 (MOT) 进行讨论，指出 transformer 在最新的 MOT 研究中逐渐具备竞争力，但仍然落后于传统深度学习方法。

Transformer 从语言到视觉到 MOT 的发展：对基于 Transformer 的多目标跟踪的文献综述

The Progression of Transformers from Language to Vision to MOT: A  Literature Review on Multi-Object Tracking with Transformers

The DEtection TRansformer (DETR) opened new possibilities for object
detection by modeling it as a translation task: converting image features into
object-level representations. Previous works typically add expensive modules to
DETR to perform Multi-Object Tracking (MOT), resulting in more complicated
architectures. We instead show how DETR can be turned into a MOT model by
employing an instance-level contrastive loss, a revised sampling strategy and a
lightweight assignment method. Our training scheme learns object appearances
while preserving detection capabilities and with little overhead. Its
performance surpasses the previous state-of-the-art by +2.6 mMOTA on the
challenging BDD100K dataset and is comparable to existing transformer-based
methods on the MOT17 dataset.

通过引入实例级对比损失、修订的采样策略和轻量级分配方法，我们展示了如何将 DETR 转化为 MOT 模型，学习目标的外观并保留检测能力，其性能在具有挑战性的 BDD100K 数据集上超过了先前的最新技术水平 2.6 mMOTA，并在 MOT17 数据集上与现有的基于 transformer 的方法相媲美。