Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for spatio-temporal relationship modeling. While the former relies on physical motion laws, offering wider applicability but yielding suboptimal results for complex object movements, the latter, though achieving high-performance, lacks interpretability and involves complex module designs. This work aims to simplify deep learning-based spatio-temporal relationship models and introduce interpretability into features for data association. Specifically, a lightweight single-layer transformer encoder is utilized to model spatio-temporal relationships. To make features more interpretative, two contrastive regularization losses based on representation alignment are proposed, derived from spatio-temporal consistency rules. By applying weighted summation to affinity matrices, the aligned features can seamlessly integrate into the data association stage of the original tracking workflow. Experimental results showcase that our model enhances the majority of existing tracking networks' performance without excessive complexity, with minimal increase in training overhead and nearly negligible computational and storage costs.

翻译：多目标跟踪算法的高性能实现高度依赖于数据关联阶段中时空关系的建模。主流方法包括基于规则和基于深度学习的时空关系建模方法。前者依赖物理运动规律，具有更广的适用性，但对复杂物体运动效果欠佳；后者虽能取得高性能，却缺乏可解释性且涉及复杂的模块设计。本研究旨在简化基于深度学习的时空关系模型，并为数据关联引入可解释性特征。具体而言，采用轻量级单层Transformer编码器建模时空关系。为增强特征的可解释性，基于时空一致性规则提出两种基于表示对齐的对比正则化损失。通过对亲和矩阵进行加权求和，对齐后的特征可无缝集成至原始跟踪流程的数据关联阶段。实验结果表明，本模型在不增加过度复杂性的前提下，能够提升多数现有跟踪网络的性能，且训练开销增幅极小，计算与存储成本近乎可忽略不计。