Research map / Vision-language and multimodal / Cross-modal learning
OCTA-SOT: Online Cross-Modal Trajectory Adjustment for RGBT Anti-UAV Single Object Tracking under Spatio-Temporal Misalignment
Xiaokang Liu, Qi Jia, Jinrui Wang, Chengzhou Li, Yu Liu, Weimin Wang
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 lens motion estimation to DIMP (ablation) | DIMP · Anti-UAV300 mean | AUC: 62.95 -> 67.57 | Improved |
| add handcrafted joint correction module to DIMP (ablation) | DIMP · Anti-UAV300 mean | AUC: 62.95 -> 69.09 (+6.14%) | Improved |
| add handcrafted joint correction on top of motion estimation (ablation) | DIMP + motion estimation · Anti-UAV300 mean | AUC: 67.57 -> 72.23 | Improved |
| add lens motion estimation to DIMP with PBO-tuned correction (ablation) | DIMP + Hpbo · Anti-UAV300 mean | AUC: 69.55 -> 72.21 | Improved |
| replace handcrafted settings with Bayesian-optimized settings (ablation) | OCTA-SOT · Anti-UAV300 mean | AUC: 72.23 -> 72.21 | No clear effect |
| apply OCTA-SOT to base tracker | DIMP · Anti-UAV300 mean | AUC: 62.95 -> 72.23 | Improved |
| apply OCTA-SOT to base tracker | DIMP · Anti-UAV300 mean | Precision: 82.05 -> 94.96 | Improved |
| use RGBT trackers under misalignment instead of RGB-only sequence evaluation | TBSI · Anti-UAV300 thermal | AUC: 72.52 -> 64.51 | Hurt |
Closest papers by meaning
- Unaligned UAV RGBT Tracking: A Largescale Benchmark and a Novel Approach (AAAI 2026 · similarity 0.91)
- PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework (ICCV 2023 · similarity 0.88)
- MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking (CVPR 2025 · similarity 0.86)
- Temporal Adaptive RGBT Tracking with Modality Prompt (AAAI 2024 · similarity 0.85)
- 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 0.84)
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.
