Research map / Vision-language and multimodal / Cross-modal learning
Efficient RGB-T Tracking via Cross-Modality Distillation
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 |
|---|---|---|---|
| Add SCFD to the compact student (ablation) | Student RGB-T tracker · RGBT234 | PR: 78.1 -> 80.3 | Helped |
| Add SCFD to the compact student (ablation) | Student RGB-T tracker · RGBT234 | SR: 56.0 -> 57.4 | Helped |
| Add MPSD after SCFD (ablation) | Student RGB-T tracker · RGBT234 | PR: 80.3 -> 82.2 | Helped |
| Add MPSD after SCFD (ablation) | Student RGB-T tracker · RGBT234 | SR: 57.4 -> 58.3 | Helped |
| Add HFRD after SCFD and MPSD (ablation) | Student RGB-T tracker · RGBT234 | PR: 82.2 -> 82.4 | Helped |
| Add HFRD after SCFD and MPSD (ablation) | Student RGB-T tracker · RGBT234 | SR: 58.3 -> 58.4 | Helped |
| Use SCFD instead of simple addition, SEM-only, or CEM-only feature distillation (ablation) | Student RGB-T tracker · RGBT234 | PR: 78.7, 79.2, 79.6, 80.3 | Helped |
| Replace MPSD with spatial attention fusion (ablation) | Student + SCFD · RGBT234 | PR: 81.9 vs 82.2 | Hurt |
| Replace MPSD with channel attention fusion (ablation) | Student + SCFD · RGBT234 | PR: 81.1 vs 82.2 | Hurt |
| Use the teacher's fusion strategy in every student layer instead of MPSD (ablation) | Student + SCFD · RGBT234 | PR: 82.2 -> 82.6 | Helped |
| Distill with CMD rather than KD, FitNets, ReviewKD, or MD (ablation) | Single-stream ResNet18 student · RGBT234 | PR: 78.4, 79.3, 80.5, 80.0 -> 82.4 | Helped |
| Distill a compact single-stream tracker rather than using it without distillation | ResNet18 student · LasHeR | PR: 55.4 -> 59.0 | Helped |
Closest papers by meaning
- Cross-modulated Attention Transformer for RGBT Tracking (AAAI 2025 · similarity 0.90)
- 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 0.89)
- Temporal Adaptive RGBT Tracking with Modality Prompt (AAAI 2024 · similarity 0.89)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.88)
- SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking (CVPR 2024 · similarity 0.87)
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.