Research map / Vision-language and multimodal / Cross-modal learning
Exploiting All Mamba Fusion for Efficient RGB-D Tracking
Ge Ying, Dawei Zhang, Chengzhuan Yang, Wei Liu, Sang-Woon Jeon, Hua Wang, Changqin Huang, Zhonglong Zheng
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 second-stage 3M fusion module (ablation) | AMTrack-S · DepthTrack | F-score: 59.7 -> 61.7 | Improved |
| use multimodal MSSM instead of plain SSM in 3M (ablation) | AMTrack-S · DepthTrack | F-score: 60.6 -> 61.7 | Improved |
| use one-stream backbone instead of two-stream shared-weight Vim (ablation) | AMTrack-S · DepthTrack | F-score: 61.1 -> 61.7 | Improved |
| use bidirectional instead of unidirectional Mamba scan (ablation) | AMTrack-S · DepthTrack | F-score: 61.5 -> 61.7 | Improved |
| replace Vim backbone with ViT (ablation) | AMTrack-S · DepthTrack | F-score: 61.7 -> 61.9 | No clear effect |
| AMTrack-S full model vs dual-branch OSTrack baseline (ablation) | OSTrack · DepthTrack | F-score: 56.7 -> 61.7 | Improved |
| AMTrack-M vs transformer trackers on CDTB (noisy depth) | AMTrack-M · CDTB | F-score: 72.1 -> 74.2 vs TABBTrack | Mixed |
| apply AMTrack-M to RGB-T and RGB-E tracking | AMTrack-M · RGBT234 / VisEvent | MPR / Pr: 89.4 MPR vs SUTrack-B224 92.2; 79.7 Pr vs 79.9 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SDSTrack — SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking (CVPR 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Exploring Historical Information for RGBE Visual Tracking with Mamba (CVPR 2025 · similarity 0.90)
- RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba (AAAI 2025 · similarity 0.89)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.89)
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.89)
- SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking (CVPR 2024 · similarity 0.88)
- Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking (AAAI 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.
