CGATracker: Correlation-Aware Graph Alignment for Referring Multi-Object Tracking
IEEE Transactions on Circuits and Systems for Video Technology · 2025-11 · 35 (11) · 11337-11349
DOI: 10.1109/tcsvt.2025.3576341 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-11. Verfasst von Siping Zhuang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City, Natural Science Foundation of Fujian Province.
Abstract (Originalsprache)
Referring multi-object tracking (RMOT) aims to identify specific targets based on sentence descriptions. To enhance multi-modal learning, previous works typically rely on a simple fusion module at early or late stages. However, those methods frequently underutilize textual semantics and struggle to model the relationships between region-level features and word-level features. To address these limitations, we propose CGATracker, a correlation-aware graph alignment method for RMOT, which facilitates precise relationship modeling through relational scoring. Specifically, we design a Language-driven Relational Alignment (LRA) module, which establishes two connection graphs to generate positive and negative samples for the visual-textual alignment. Additionally, to effectively leverage referring information, we introduce a Semantic Clarify Booster (SCBooster) module based on a semantic infusion mechanism and a bias-aware verification mechanism for interactions with different modalities. Moreover, by designing a Multi-level Cross-modal Fusion (MCF) module, our method aggregates contextual features at multiple depths to enable the creation of the enriched correlation-aware graph. Extensive experiments conducted on the Refer-KITTI and Refer-KITTI-V2 datasets demonstrate the effectiveness of CGATracker.
Förderung
- National Natural Science Foundation of China
- Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City
- Natural Science Foundation of Fujian Province
Zitieren
APA
Zhuang, S., Li, G., Wu, Q., Lu, Y., Hu, H., & Wang, H. (2025). CGATracker: Correlation-Aware Graph Alignment for Referring Multi-Object Tracking. IEEE Transactions on Circuits and Systems for Video Technology, 35(11), 11337-11349. https://doi.org/10.1109/tcsvt.2025.3576341
Vancouver
Zhuang S, Li G, Wu Q, Lu Y, Hu H, Wang H. CGATracker: Correlation-Aware Graph Alignment for Referring Multi-Object Tracking. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(11):11337-11349. doi:10.1109/tcsvt.2025.3576341
BibTeX
@article{Zhuang2025,
author = {Zhuang, Siping and Li, Guangyao and Wu, Qiangqiang and Lu, Yang and Hu, Hai-Miao and Wang, Hanzi},
title = {CGATracker: Correlation-Aware Graph Alignment for Referring Multi-Object Tracking},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {11},
pages = {11337--11349},
doi = {10.1109/tcsvt.2025.3576341}
}
EUVIMED