{"ID":2870339,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12913","arxiv_id":"2509.12913","title":"T-SiamTPN: Temporal Siamese Transformer Pyramid Networks for Robust and Efficient UAV Tracking","abstract":"Aerial object tracking remains a challenging task due to scale variations, dynamic backgrounds, clutter, and frequent occlusions. While most existing trackers emphasize spatial cues, they often overlook temporal dependencies, resulting in limited robustness in long-term tracking and under occlusion. Furthermore, correlation-based Siamese trackers are inherently constrained by the linear nature of correlation operations, making them ineffective against complex, non-linear appearance changes. To address these limitations, we introduce T-SiamTPN, a temporal-aware Siamese tracking framework that extends the SiamTPN architecture with explicit temporal modeling. Our approach incorporates temporal feature fusion and attention-based interactions, strengthening temporal consistency and enabling richer feature representations. These enhancements yield significant improvements over the baseline and achieve performance competitive with state-of-the-art trackers. Crucially, despite the added temporal modules, T-SiamTPN preserves computational efficiency. Deployed on the resource-constrained Jetson Nano, the tracker runs in real time at 7.1 FPS, demonstrating its suitability for real-world embedded applications without notable runtime overhead. Experimental results highlight substantial gains: compared to the baseline, T-SiamTPN improves success rate by 13.7% and precision by 14.7%. These findings underscore the importance of temporal modeling in Siamese tracking frameworks and establish T-SiamTPN as a strong and efficient solution for aerial object tracking. Code is available at: https://github.com/to/be/released","short_abstract":"Aerial object tracking remains a challenging task due to scale variations, dynamic backgrounds, clutter, and frequent occlusions. While most existing trackers emphasize spatial cues, they often overlook temporal dependencies, resulting in limited robustness in long-term tracking and under occlusion. Furthermore, correl...","url_abs":"https://arxiv.org/abs/2509.12913","url_pdf":"https://arxiv.org/pdf/2509.12913v1","authors":"[\"Hojat Ardi\",\"Amir Jahanshahi\",\"Ali Diba\"]","published":"2025-09-16T10:06:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":609758,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2870339,"paper_url":"https://arxiv.org/abs/2509.12913","paper_title":"T-SiamTPN: Temporal Siamese Transformer Pyramid Networks for Robust and Efficient UAV Tracking","repo_url":"https://github.com/to/be","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}