Research map / Vision-language and multimodal / Cross-modal learning
Challenge-Aware RGBT Tracking
Chenglong Li, Lei Liu, Andong Lu, Qing Ji, Jin Tang
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 guidance modules (vs removing all, CAT-NA) (ablation) | CAT · GTOT | PR: 0.861 -> 0.889 | Improved |
| add guidance modules (vs removing all, CAT-NA) (ablation) | CAT · RGBT210 | PR: 0.750 -> 0.792 | Improved |
| add guidance modules (vs removing all, CAT-NA) (ablation) | CAT · RGBT234 | SR: 0.535 -> 0.561 | Improved |
| add gate operations in guidance modules (vs CAT-NS) (ablation) | CAT · RGBT234 | PR: 0.787 -> 0.804 | Improved |
| add gate operations in guidance modules (vs CAT-NS) (ablation) | CAT · GTOT | SR: 0.708 -> 0.717 | Improved |
| add conv operations in guidance module (CAT-NS vs CAT-NG) (ablation) | CAT · RGBT234 | PR: 0.781 -> 0.787 | Improved |
| add guidance module with gate (vs FiLM) (ablation) | CAT · GTOT | PR: 0.848 -> 0.889 | Improved |
| add guidance module with gate (vs FiLM) (ablation) | CAT · RGBT234 | SR: 0.540 -> 0.561 | Improved |
| add challenge-aware branches in conv1 only (ablation) | RT-MDNet+RGBT · GTOT | PR: 0.839 -> 0.877 | Improved |
| add challenge-aware branches in conv3 only (ablation) | RT-MDNet+RGBT · GTOT | PR: 0.839 -> 0.880 | Improved |
| add branches in conv1 and conv2 (two layers) (ablation) | RT-MDNet+RGBT · GTOT | PR: 0.839 -> 0.865 | Mixed |
| add branches in all three conv layers (vs best single layer conv3) (ablation) | CAT · GTOT | PR: 0.880 -> 0.889 | Improved |
Closest papers by meaning
- Temporal Adaptive RGBT Tracking with Modality Prompt (AAAI 2024 · similarity 0.89)
- RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba (AAAI 2025 · similarity 0.88)
- Cross-modulated Attention Transformer for RGBT Tracking (AAAI 2025 · similarity 0.87)
- 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 0.85)
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.
