Research map / Vision-language and multimodal / Cross-modal learning
Bridging Search Region Interaction With Template for RGB-T Tracking
Read the paperCheck 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 |
|---|---|---|---|
| Use ViT-Base with SOT pretraining and TBSI instead of mfDiMP | RGB-T tracking · LasHeR testing set | Precision: 59.9 -> 69.2 | Helped |
| Use TBSI instead of mfDiMP | RGB-T tracking · RGBT234 | Precision: 84.2 -> 87.1 | Helped |
| Use TBSI instead of mfDiMP* | RGB-T tracking · RGBT210 | Success: 59.3 -> 62.5 | Helped |
| Add TIR image pairs to RGB-only input (ablation) | ViT-Base tracker · LasHeR | Success: 40.1 -> 42.5 | Helped |
| Add direct bidirectional RGB-T search-region interaction without template bridging (ablation) | RGB-T Baseline · LasHeR | Success: 42.5 -> 47.4 | Helped |
| Add template-mediated bridging for cross-modal search-region interaction (ablation) | Direct RGB-T search-region interaction · LasHeR | Success: 47.4 -> 50.6 | Helped |
| Add RGB-to-template-medium-to-TIR interaction (ablation) | Unidirectional TBSI · LasHeR | Success: 46.6 -> 50.6 | Helped |
| Add updating original templates with enriched multimodal contexts (ablation) | Bidirectional TBSI · LasHeR | Success: 49.7 -> 50.6 | Helped |
| Insert TBSI at the 4-th layer (ablation) | ViT-Base RGB-T tracker · LasHeR | Success: 42.5 -> 47.8 | Helped |
| Add a TBSI insertion at the 7-th layer (ablation) | TBSI at layer 4 · LasHeR | Success: 47.8 -> 49.8 | Helped |
| Add a TBSI insertion at the 10-th layer (ablation) | TBSI at layers 4 and 7 · LasHeR | Success: 49.8 -> 50.6 | Helped |
Closest papers by meaning
- Temporal Adaptive RGBT Tracking with Modality Prompt (AAAI 2024 · similarity 0.90)
- Cross-modulated Attention Transformer for RGBT Tracking (AAAI 2025 · similarity 0.89)
- RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba (AAAI 2025 · similarity 0.89)
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.87)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.86)
- CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features (ICML 2025 · similarity 0.86)
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.