Research map / Vision-language and multimodal / Cross-modal learning
Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking
Shilei Wang, Pujian Lai, Dong Gao, Jifeng Ning, Gong Cheng
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 decoupled temporal module (two SSMs) (ablation) | MDTrack baseline · LasHeR | AUC: 58.5 -> 60.2 | Improved |
| add decoupled temporal module (two SSMs) (ablation) | MDTrack baseline · DepthTrack | F-score: 65.8 -> 67.6 | Improved |
| add token-based temporal module (ablation) | MDTrack baseline · VisEvent | Success: 62.2 -> 62.3 | No clear effect |
| add single-SSM mixed temporal module (ablation) | MDTrack baseline · LasHeR | AUC: 58.5 -> 59.3 | Improved |
| add unified-expert fusion module (ablation) | MDTrack baseline · DepthTrack | F-score: 65.8 -> 65.9 | No clear effect |
| add modality-aware MoE fusion module (ablation) | MDTrack baseline · LasHeR | AUC: 58.5 -> 59.6 | Improved |
| add modality-aware MoE fusion module (ablation) | MDTrack baseline · VisEvent | Success: 62.2 -> 62.8 | Improved |
| combine decoupled temporal and modality-aware fusion (ablation) | MDTrack baseline · LasHeR | AUC: 58.5 -> 61.1 | Improved |
| combine decoupled temporal and modality-aware fusion (ablation) | MDTrack baseline · VisEvent | Success: 62.2 -> 63.9 | Improved |
| unified-modality training instead of modality-specific | MDTrack · VisEvent | Success: 65.3 -> 63.9 | Hurt |
| unified-modality training instead of modality-specific | MDTrack · VOT-RGBD2022 | EAO: 79.7 -> 80.0 | Improved |
Closest papers by meaning
- 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)
- Bi-directional Adapter for Multimodal Tracking (AAAI 2024 · similarity 0.88)
- Generative-Based Fusion Mechanism for Multi-Modal Tracking (AAAI 2024 · similarity 0.87)
- Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking (AAAI 2025 · similarity 0.87)
- Temporal Adaptive RGBT Tracking with Modality Prompt (AAAI 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.
