Research map / Vision-language and multimodal / Cross-modal learning
Progressively Spiral Mamba Fusion for Multimodal Tracking
Zixuan Wang, Baojie Fan, Jiajun Ai, Wenzhang Zhou
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 DBME (ablation) | PSMTrack · LasHeR | PR: 0.752 -> 0.765 | Improved |
| add CLI (ablation) | PSMTrack · LasHeR | PR: 0.753 -> 0.765 | Improved |
| use HSMF instead of simple concatenation (ablation) | PSMTrack · LasHeR | PR: 0.748 -> 0.765 | Improved |
| use HSMF instead of simple concatenation (ablation) | PSMTrack · VisEvent | Pr: 0.775 -> 0.799 | Improved |
| add DBME and CLI on top of HSMF (ablation) | PSMTrack · LasHeR | PR: 0.733 -> 0.765 | Improved |
| add AConv and SCConv to NC-SSD in CLI (ablation) | CLI · LasHeR | SR: 60.5 -> 60.9 | Improved |
| add SCSA after cross-layer concatenation (ablation) | CLI · LasHeR | SR: 60.9 -> 61.2 | Improved |
| increase router top-k from 1 to 3 layers (ablation) | CLI · LasHeR | SR: 60.7 -> 61.2 | Improved |
| increase top-k from 3 to 4 layers (ablation) | CLI · LasHeR | SR: 61.2 -> 60.8 | Hurt |
| PSMTrack vs STTrack on VOT-RGBD22 robustness | PSMTrack · VOT-RGBD22 | Robustness: 93.7 -> 93.5 | Mixed |
Closest papers by meaning
- RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba (AAAI 2025 · similarity 0.88)
- Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking (AAAI 2025 · similarity 0.87)
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.87)
- Exploring Historical Information for RGBE Visual Tracking with Mamba (CVPR 2025 · similarity 0.86)
- Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model (NeurIPS 2024 · similarity 0.86)
- Bi-directional Adapter for Multimodal Tracking (AAAI 2024 · 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.
