EUVIMEDEUVIMED entdecken
Crossref

MambaLCT: Boosting Tracking via Long-term Context State Space Model

Xiaohai Li, Bineng Zhong, Qihua Liang, Guorong Li, Zhiyi Mo, Shuxiang Song

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (5) · 4986-4994

DOI: 10.1609/aaai.v39i5.32528 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Xiaohai Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effectively constructing context information with long-term dependencies from video sequences is crucial for object tracking. However, the context length constructed by existing work is limited, only considering object information from adjacent frames or video clips, leading to insufficient utilization of contextual information. To address this issue, we propose MambaLCT, which constructs and utilizes target variation cues from the first frame to the current frame for robust tracking. First, a novel unidirectional Context Mamba module is designed to scan frame features along the temporal dimension, gathering target change cues throughout the entire sequence. Specifically, target-related information in frame features is compressed into a hidden state space through a selective scanning mechanism. The target information across the entire video is continuously aggregated into target variation cues. Next, we inject the target change cues into the attention mechanism, providing temporal information for modeling the relationship between the template and search frames. The advantage of MambaLCT is its ability to continuously extend the length of the context, capturing complete target change cues, which enhances the stability and robustness of the tracker. Extensive experiments show that long-term context information enhances the model's ability to perceive targets in complex scenarios. MambaLCT achieves new SOTA performance on six benchmarks while maintaining real-time runing speeds.

Zitieren

APA

Li, X., Zhong, B., Liang, Q., Li, G., Mo, Z., & Song, S. (2025). MambaLCT: Boosting Tracking via Long-term Context State Space Model. Proceedings of the AAAI Conference on Artificial Intelligence, 39(5), 4986-4994. https://doi.org/10.1609/aaai.v39i5.32528

Vancouver

Li X, Zhong B, Liang Q, Li G, Mo Z, Song S. MambaLCT: Boosting Tracking via Long-term Context State Space Model. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(5):4986-4994. doi:10.1609/aaai.v39i5.32528

BibTeX
@article{Li2025,
  author = {Li, Xiaohai and Zhong, Bineng and Liang, Qihua and Li, Guorong and Mo, Zhiyi and Song, Shuxiang},
  title = {MambaLCT: Boosting Tracking via Long-term Context State Space Model},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {5},
  pages = {4986--4994},
  doi = {10.1609/aaai.v39i5.32528}
}
Kostenlos starten →