Research map / Vision-language and multimodal / Cross-modal learning
Cross-Modal Object Tracking: Modality-Aware Representations and a Unified Benchmark
Chenglong Li, Tianhao Zhu, Lei Liu, Xiaonan Si, Zilin Fan, Sulan Zhai
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 MArMOT modality-aware representations and ensemble fusion | DiMP-50 · CMOTB test | PR: 11.2% | Improved |
| Add MArMOT modality-aware representations and ensemble fusion | RT-MDNet · CMOTB test | PR: 15.8% | Improved |
| Retrain the tracker on CMOTB training data | DiMP-50 · CMOTB test | SR-I: ↑ 8.2% | Improved |
| Retrain the tracker on CMOTB training data | RT-MDNet · CMOTB test | SR-I: ↑ 14.7% | Improved |
| Use three-stage training rather than one-stage joint training (ablation) | MArMOT DiMP-50 · CMOTB test | PR: 2.3% | Improved |
| Use three-stage training rather than one-stage joint training (ablation) | MArMOT DiMP-50 · CMOTB test | NPR: 1.7% | Improved |
| Use three-stage training rather than one-stage joint training (ablation) | MArMOT DiMP-50 · CMOTB test | SR-I: 2.0% | Improved |
| Use three-stage training rather than one-stage joint training (ablation) | MArMOT DiMP-50 · CMOTB test | SR-II: 1.6% | Improved |
| Add MArMOT to the DiMP-50 tracker | DiMP-50 · Synthetic RGBT test (GTOT) | PR | Improved |
Closest papers by meaning
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.94)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.93)
- UniSOT: A Unified Framework for Multi-Modality Single Object Tracking (TPAMI 2025 · similarity 0.91)
- Bi-directional Adapter for Multimodal Tracking (AAAI 2024 · similarity 0.90)
- Cross-modulated Attention Transformer for RGBT Tracking (AAAI 2025 · similarity 0.89)
- 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.
