Representation Alignment Contrastive Regularization for Multi-Object Tracking

arXiv:2404.02562v1 Announce Type: new
Abstract: 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 …

abstract algorithms alignment arxiv association cs.cv data deep learning laws modeling movements object performance regularization relationship relationships representation results stage temporal tracking type