Representation alignment contrastive regularisation for multi‐object tracking
IET Computer Vision · 2025-01 · 19 (1)
DOI: 10.1049/cvi2.12331 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Computer Vision, online erschienen am 15.12.2024. Verfasst von Shujie Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Achieving high‐performance in multi‐object tracking algorithms heavily relies on modelling spatial‐temporal relationships during the data association stage. Mainstream approaches encompass rule‐based and deep learning‐based methods for spatial‐temporal relationship modelling. 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 spatial‐temporal relationship models and introduce interpretability into features for data association. Specifically, a lightweight single‐layer transformer encoder is utilised to model spatial‐temporal relationships. To make features more interpretative, two contrastive regularisation losses based on representation alignment are proposed, derived from spatial‐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.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chen, S., Liu, Z., Dong, J., Wang, X., & Zhou, D. (2025). Representation alignment contrastive regularisation for multi‐object tracking. IET Computer Vision, 19(1). https://doi.org/10.1049/cvi2.12331
Vancouver
Chen S, Liu Z, Dong J, Wang X, Zhou D. Representation alignment contrastive regularisation for multi‐object tracking. IET Computer Vision. 2025;19(1). doi:10.1049/cvi2.12331
BibTeX
@article{Chen2025,
author = {Chen, Shujie and Liu, Zhonglin and Dong, Jianfeng and Wang, Xun and Zhou, Di},
title = {Representation alignment contrastive regularisation for multi‐object tracking},
journal = {IET Computer Vision},
year = {2025},
volume = {19},
number = {1},
doi = {10.1049/cvi2.12331}
}
EUVIMED