Research map / Detection and segmentation / Tracking
AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 automatic spatial regularization (ASR) (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | Precision: 0.671 -> 0.716 | Helped |
| Add automatic spatial regularization (ASR) (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | AUC: 0.468 -> 0.489 | Helped |
| Add automatic spatial regularization (ASR) (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | FPS: 28.4 -> 53.7 | Helped |
| Add automatic temporal regularization (ATR) (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | Precision: 0.671 -> 0.714 | Helped |
| Add automatic temporal regularization (ATR) (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | AUC: 0.468 -> 0.492 | Helped |
| Add automatic temporal regularization (ATR) (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | FPS: 28.4 -> 60.0 | Helped |
| Add both automatic spatial and temporal regularization (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | Precision: 0.671 -> 0.724 | Helped |
| Add both automatic spatial and temporal regularization (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | AUC: 0.468 -> 0.495 | Helped |
| Add both automatic spatial and temporal regularization (ablation) | STRCF · Four UAV benchmarks (ablation evaluation) | FPS: 28.4 -> 59.2 | Helped |
| Use automatic spatio-temporal regularization instead of STRCF's fixed regularization | STRCF · Four UAV benchmarks (average of top ten CPU trackers) | precision: 7.9% | Helped |
| Use AutoTrack rather than ECO-HC | CPU trackers · Four UAV benchmarks (average of top ten CPU trackers) | precision: 4.8% | Helped |
| Use AutoTrack rather than STRCF | UAV tracking · Deformation attribute | success rate: 15.9% | Helped |
Closest papers by meaning
- Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers (CVPR 2024 · similarity 0.86)
- Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking (ICML 2024 · similarity 0.85)
- Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking (CVPR 2025 · similarity 0.85)
- LVPTrack: High Performance Domain Adaptive UAV Tracking with Label Aligned Visual Prompt Tuning (AAAI 2025 · similarity 0.85)
- Dynamic Semantic-Aware Correlation Modeling for UAV Tracking (NeurIPS 2025 · similarity 0.84)
- Game4Loc: A UAV Geo-Localization Benchmark from Game Data (AAAI 2025 · similarity 0.84)
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.