Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2505.04088 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915336161329152 |
|---|---|
| author | Zhang, Shang Zhang, Huanbin Feng, Dali Cui, Yujie Xiong, Ruoyan He, Cen |
| author_facet | Zhang, Shang Zhang, Huanbin Feng, Dali Cui, Yujie Xiong, Ruoyan He, Cen |
| contents | Thermal infrared (TIR) object tracking often suffers from challenges such as target occlusion, motion blur, and background clutter, which significantly degrade the performance of trackers. To address these issues, this paper pro-poses a novel Siamese Motion Mamba Tracker (SMMT), which integrates a bidirectional state-space model and a self-attention mechanism. Specifically, we introduce the Motion Mamba module into the Siamese architecture to ex-tract motion features and recover overlooked edge details using bidirectional modeling and self-attention. We propose a Siamese parameter-sharing strate-gy that allows certain convolutional layers to share weights. This approach reduces computational redundancy while preserving strong feature represen-tation. In addition, we design a motion edge-aware regression loss to improve tracking accuracy, especially for motion-blurred targets. Extensive experi-ments are conducted on four TIR tracking benchmarks, including LSOTB-TIR, PTB-TIR, VOT-TIR2015, and VOT-TIR 2017. The results show that SMMT achieves superior performance in TIR target tracking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04088 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SMMT: Siamese Motion Mamba with Self-attention for Thermal Infrared Target Tracking Zhang, Shang Zhang, Huanbin Feng, Dali Cui, Yujie Xiong, Ruoyan He, Cen Computer Vision and Pattern Recognition Thermal infrared (TIR) object tracking often suffers from challenges such as target occlusion, motion blur, and background clutter, which significantly degrade the performance of trackers. To address these issues, this paper pro-poses a novel Siamese Motion Mamba Tracker (SMMT), which integrates a bidirectional state-space model and a self-attention mechanism. Specifically, we introduce the Motion Mamba module into the Siamese architecture to ex-tract motion features and recover overlooked edge details using bidirectional modeling and self-attention. We propose a Siamese parameter-sharing strate-gy that allows certain convolutional layers to share weights. This approach reduces computational redundancy while preserving strong feature represen-tation. In addition, we design a motion edge-aware regression loss to improve tracking accuracy, especially for motion-blurred targets. Extensive experi-ments are conducted on four TIR tracking benchmarks, including LSOTB-TIR, PTB-TIR, VOT-TIR2015, and VOT-TIR 2017. The results show that SMMT achieves superior performance in TIR target tracking. |
| title | SMMT: Siamese Motion Mamba with Self-attention for Thermal Infrared Target Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.04088 |