Research map / Detection and segmentation / Tracking
Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline
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 |
|---|---|---|---|
| Combine RGB-T inputs with Complementary Image Fusion (CIF) (ablation) | DiMP · RGB-T tracking ablation | MSR: +3.2% | Helped |
| Combine RGB-T features with Discriminative Feature Fusion (DFF) (ablation) | DiMP · RGB-T tracking ablation | MSR: +4.4% | Helped |
| Average the responses from CIF and DFF branches (ablation) | DiMP+CIF+DFF · RGB-T tracking ablation | MSR | Hurt |
| Add Adaptive Decision Fusion (ADF) instead of simply averaging branch responses (ablation) | DiMP+CIF+DFF · RGB-T tracking ablation | MSR: +2.6% | Helped |
| Add Adaptive Decision Fusion (ADF) instead of simply averaging branch responses (ablation) | DiMP+CIF+DFF · RGB-T tracking ablation | MPR: +2.7% | Helped |
| Add GlobalTrack as a global detector and RTMDNet as a tracker switcher | HMFT · VTUAV long-term | MSR: 29.8% relative promotion | Helped |
| Add GlobalTrack as a global detector and RTMDNet as a tracker switcher | HMFT · VTUAV long-term | MPR: 29.4% relative promotion | Helped |
| Use hierarchical image, feature, and decision fusion | HMFT · GTOT | MSR: 49.0 -> 74.9 | Helped |
| Use hierarchical image, feature, and decision fusion | HMFT · RGBT210 | MSR: 52.2 -> 53.5 | Helped |
| Use hierarchical image, feature, and decision fusion | HMFT · RGBT234 | MSR: 57.1 vs 56.8 | Mixed |
Closest papers by meaning
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.89)
- MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking (CVPR 2025 · similarity 0.88)
- MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking (NeurIPS 2025 · similarity 0.86)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.86)
- UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles (NeurIPS 2024 · similarity 0.85)
- Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking (ICML 2024 · similarity 0.85)
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.