Research map / Vision-language and multimodal / Cross-modal learning
Progressive Multi-cue Alignment for Unaligned RGBT Tracking
Jiandong Jin, Chenglong Li, Hao Feng, Andong Lu, Lili Huang, 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 target-response expert (TRE) (ablation) | PMATrack baseline · MUART244 | PR: 58.7 -> 59.3 | Improved |
| add feature-matching expert (FME) (ablation) | PMATrack baseline · LasHeR-Unaligned | PR: 61.5 -> 62.5 | Improved |
| add detail-perception expert (DPE) (ablation) | PMATrack baseline · LasHeR-Unaligned | PR: 61.5 -> 63.2 | Improved |
| add TOCU offset update mechanism with all three experts (ablation) | PMATrack · LasHeR-Unaligned | PR: 63.2 -> 64.4 | Improved |
| add TOCU offset update mechanism with all three experts (ablation) | PMATrack · MUART244 | PR: 60.9 -> 62.7 | Improved |
| use difficulty-aware router over all experts instead of always using DPE (ablation) | PMATrack · LasHeR-Unaligned | FLOPs (G): 81.4 -> 72.6 | Improved |
| add scale transformation stage after center offset (ablation) | progressive alignment · LasHeR-Unaligned | PR: 63.2 -> 63.6 | Improved |
| add global refinement stage after center and scale (ablation) | progressive alignment · LasHeR-Unaligned | PR: 63.6 -> 64.4 | Improved |
| add center offset stage over baseline (ablation) | progressive alignment · LasHeR-Unaligned | PR: 61.5 -> 63.2 | Improved |
| align all frames using only the first-frame offset instead of online offset prediction | existing RGBT trackers · MUART244 | PR: SDSTrack 46.8 -> 43.3; UnTrack 54.1 -> 54.2 | Mixed |
Closest papers by meaning
- Temporal Adaptive RGBT Tracking with Modality Prompt (AAAI 2024 · similarity 0.89)
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.89)
- RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba (AAAI 2025 · similarity 0.89)
- Cross-modulated Attention Transformer for RGBT Tracking (AAAI 2025 · similarity 0.88)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.88)
- CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features (ICML 2025 · 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.
