Research map / Vision-language and multimodal / Cross-modal learning
CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking
Hao Li, Yuhao Wang, Xiantao Hu, Wenning Hao, Pingping Zhang, Dong Wang, Huchuan Lu
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 deformable alignment module (DAM) (ablation) | CADTrack baseline · LasHeR | PR: 69.1 -> 72.7 | Improved |
| add Mamba-based feature interaction (MFI) (ablation) | CADTrack baseline · LasHeR | PR: 72.7 -> 74.1 | Improved |
| add contextual aggregation module (CAM) (ablation) | CADTrack baseline · LasHeR | PR: 74.1 -> 75.8 | Improved |
| add template update (ablation) | baseline ViT-B tracker · LasHeR | PR: 67.9 -> 69.1 | Improved |
| use DropMAE pretraining instead of SOT (ablation) | CADTrack · LasHeR | PR: 75.8 -> 77.7 | Improved |
| use MFI instead of TBSI for modality interaction (ablation) | CADTrack · LasHeR | PR: 74.5 -> 77.7 (FPS 29 -> 40) | Improved |
| use MFI instead of BSI (ablation) | CADTrack · LasHeR | PR: 76.9 -> 77.7 | Improved |
| place MFI at layers 4, 7 and 10 instead of fewer positions (ablation) | CADTrack · LasHeR | PR: 75.2 -> 77.7 | Improved |
| use 2 Mamba layers in MFI instead of 1 (ablation) | MFI · LasHeR | PR: 75.4 -> 77.7 | Improved |
| use 3 Mamba layers in MFI instead of 2 (ablation) | MFI · LasHeR | PR: 77.7 -> 77.1 | Hurt |
| select top-6 experts versus 4 or 8 in CAM (ablation) | CAM · LasHeR | PR: k=4 75.5, k=6 77.7, k=8 74.3 | Mixed |
| use learned router selection instead of fixed-interval layer selection (ablation) | CAM · LasHeR | PR: 75.8 -> 77.7 | 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)
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.87)
- CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features (ICML 2025 · similarity 0.87)
- SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking (CVPR 2024 · similarity 0.87)
- Cross-modulated Attention Transformer for RGBT Tracking (AAAI 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.
