TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918079512969216 |
|---|---|
| author | Liu, Bingxi Chen, Calvin Li, Junhao Yu, Guyang Song, Haoqian Liu, Xuchen Cui, Jinqiang Zhang, Hong |
| author_facet | Liu, Bingxi Chen, Calvin Li, Junhao Yu, Guyang Song, Haoqian Liu, Xuchen Cui, Jinqiang Zhang, Hong |
| contents | The Vision Transformer (ViT) model has long struggled with the challenge of quadratic complexity, a limitation that becomes especially critical in unmanned aerial vehicle (UAV) tracking systems, where data must be processed in real time. In this study, we explore the recently proposed State-Space Model, Mamba, leveraging its computational efficiency and capability for long-sequence modeling to effectively process dense image sequences in tracking tasks. First, we highlight the issue of temporal inconsistency in existing Mamba-based methods, specifically the failure to account for temporal continuity in the Mamba scanning mechanism. Secondly, building upon this insight,we propose TrackingMiM, a Mamba-in-Mamba architecture, a minimal-computation burden model for handling image sequence of tracking problem. In our framework, the mamba scan is performed in a nested way while independently process temporal and spatial coherent patch tokens. While the template frame is encoded as query token and utilized for tracking in every scan. Extensive experiments conducted on five UAV tracking benchmarks confirm that the proposed TrackingMiM achieves state-of-the-art precision while offering noticeable higher speed in UAV tracking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01535 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking Liu, Bingxi Chen, Calvin Li, Junhao Yu, Guyang Song, Haoqian Liu, Xuchen Cui, Jinqiang Zhang, Hong Computer Vision and Pattern Recognition The Vision Transformer (ViT) model has long struggled with the challenge of quadratic complexity, a limitation that becomes especially critical in unmanned aerial vehicle (UAV) tracking systems, where data must be processed in real time. In this study, we explore the recently proposed State-Space Model, Mamba, leveraging its computational efficiency and capability for long-sequence modeling to effectively process dense image sequences in tracking tasks. First, we highlight the issue of temporal inconsistency in existing Mamba-based methods, specifically the failure to account for temporal continuity in the Mamba scanning mechanism. Secondly, building upon this insight,we propose TrackingMiM, a Mamba-in-Mamba architecture, a minimal-computation burden model for handling image sequence of tracking problem. In our framework, the mamba scan is performed in a nested way while independently process temporal and spatial coherent patch tokens. While the template frame is encoded as query token and utilized for tracking in every scan. Extensive experiments conducted on five UAV tracking benchmarks confirm that the proposed TrackingMiM achieves state-of-the-art precision while offering noticeable higher speed in UAV tracking. |
| title | TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.01535 |