Research map / Video / Video-language understanding
What You Have is What You Track: Adaptive and Robust Multimodal Tracking
Yuedong Tan, Jiawei Shao, Eduard Zamfir, Ruanjun Li, Zhaochong An, Chao Ma, Danda Paudel, Luc Van Gool, Radu Timofte, Zongwei Wu
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 video-level masking (ablation) | FlexTrack · LasHeR (missing modality) | P: 61.3 -> 65.1 | Improved |
| add video-level masking (ablation) | FlexTrack · VisEvent (missing modality) | P: 66.3 -> 72.8 | Improved |
| add video-level masking (ablation) | FlexTrack · LasHeR | P: 77.1 -> 77.3 | No clear effect |
| add video-level masking (ablation) | FlexTrack · VisEvent | P: 81.5 -> 81.4 | No clear effect |
| use video-level masking instead of random masking (ablation) | FlexTrack · LasHeR | P: 77.0 -> 77.3 | Improved |
| use video-level masking instead of VideoMAE masking (ablation) | FlexTrack · LasHeR | P: 74.3 -> 77.3 | Improved |
| use video-level masking instead of VideoMAE masking (ablation) | FlexTrack · VisEvent (missing modality) | P: 71.0 -> 72.8 | Improved |
| add gating in HMoE-Fuse (ablation) | FlexTrack · LasHeR (missing modality) | P: 63.1 -> 65.1 | Improved |
| add linear attention in HMoE-Fuse (ablation) | FlexTrack · LasHeR (missing modality) | P: 61.8 -> 65.1 | Improved |
| add linear attention in HMoE-Fuse (ablation) | FlexTrack · VisEvent | P: 78.2 -> 81.4 | Improved |
| add HMoE module (ablation) | FlexTrack · LasHeR | P: 74.2 -> 77.3 | Improved |
| add HMoE module (ablation) | FlexTrack · VisEvent (missing modality) | P: 67.5 -> 72.8 | Improved |
Closest papers by meaning
- Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking (AAAI 2025 · similarity 0.90)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.88)
- SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking (CVPR 2024 · similarity 0.87)
- DreamTrack: Dreaming the Future for Multimodal Visual Object Tracking (CVPR 2025 · similarity 0.87)
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.86)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 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.
