Exploring Enhanced Contextual Information for Video-Level Object Tracking
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 4194-4202
DOI: 10.1609/aaai.v39i4.32440 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Ben Kang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 62-mal zitiert (Crossref).
Abstract (Originalsprache)
Contextual information at the video level has become increasingly crucial for visual object tracking. However, existing methods typically use only a few tokens to convey this information, which can lead to information loss and limit their ability to fully capture the context. To address this issue, we propose a new video-level visual object tracking framework called MCITrack. It leverages Mamba's hidden states to continuously record and transmit extensive contextual information throughout the video stream, resulting in more robust object tracking. The core component of MCITrack is the Contextual Information Fusion module, which consists of the mamba layer and the cross-attention layer. The mamba layer stores historical contextual information, while the cross-attention layer integrates this information into the current visual features of each backbone block. This module enhances the model's ability to capture and utilize contextual information at multiple levels through deep integration with the backbone. Experiments demonstrate that MCITrack achieves competitive performance across numerous benchmarks. For instance, it gets 76.6% AUC on LaSOT and 80.0% AO on GOT-10k, establishing a new state-of-the-art performance.
Zitieren
APA
Kang, B., Chen, X., Lai, S., Liu, Y., Liu, Y., & Wang, D. (2025). Exploring Enhanced Contextual Information for Video-Level Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 4194-4202. https://doi.org/10.1609/aaai.v39i4.32440
Vancouver
Kang B, Chen X, Lai S, Liu Y, Liu Y, Wang D. Exploring Enhanced Contextual Information for Video-Level Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):4194-4202. doi:10.1609/aaai.v39i4.32440
BibTeX
@article{Kang2025,
author = {Kang, Ben and Chen, Xin and Lai, Simiao and Liu, Yang and Liu, Yi and Wang, Dong},
title = {Exploring Enhanced Contextual Information for Video-Level Object Tracking},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {4},
pages = {4194--4202},
doi = {10.1609/aaai.v39i4.32440}
}
EUVIMED