Research map / Architectures and efficiency / Attention and transformers
Foreground-Aware Token Routing Vision Transformer for Real-Time Satellite Video Tracking
Jiahao Wang, Fang Liu, Licheng Jiao, Shuo Li, Hao Wang, Lingling Li, Xinyi Wang, Xu Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ASM instead of linear mapping (ablation) | FATrack-Base · SV248S | Success: 0.432 -> 0.468 | Improved |
| add ASM instead of linear mapping (ablation) | FATrack-Base · VISO | SR: 0.245 -> 0.286 | Improved |
| use ASM instead of bilinear interpolation (ablation) | FATrack-Base · SV248S | Success: 0.421 -> 0.468 | Improved |
| use ASM instead of zero padding (ablation) | FATrack-Base · SatSOT | Success: 0.425 -> 0.470 | Improved |
| add Shrinkage-Expansion token routing (ablation) | FATrack-Base · VISO | SR: 0.167 -> 0.286 | Improved |
| add Shrinkage-Expansion token routing (ablation) | FATrack-Base · SV248S | FPS: 100 -> 142 | Improved |
| apply shrink-expand only at first and last layers (ablation) | FATrack-Base · SV248S | Success: 0.468 -> 0.433 | Hurt |
| use centrality-guided filtering instead of attention-guided (ablation) | OSTrack-style tracker · SV248S | SR: 39.9 -> 46.8 | Improved |
| use centrality-guided filtering instead of no filtering (ablation) | FATrack-Base · SV248S | MACs (G): 29.0 -> 17.3 | Improved |
| use random token filtering instead of centrality-guided (ablation) | FATrack-Base · SV248S | SR: 46.8 -> 38.1 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SiamRPN++ — SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks (CVPR 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking (ICML 2024 · similarity 0.86)
- Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking (CVPR 2025 · similarity 0.85)
- Sequential Fusion Based Multi-Granularity Consistency for Space-Time Transformer Tracking (AAAI 2024 · similarity 0.84)
- ODTrack: Online Dense Temporal Token Learning for Visual Tracking (AAAI 2024 · similarity 0.83)
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.83)
- Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
