Research map / Video / Video-language understanding
MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding
Tongtong Cheng, Rongzhen Li, Yixin Xiong, Tao Zhang, Jing Wang, Kai Liu
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 causal analysis module (CAM) to MFE + VLT (ablation) | MCAM · BDD-X reasoning | CIDEr: 79.8 -> 92.9 | Improved |
| add CAM to MFE + VLT (ablation) | MCAM · BDD-X narration | BLEU-4: 33.4 -> 35.3 | Improved |
| add CAM to VidSwin + VLT (ablation) | VidSwin + VLT · BDD-X reasoning | CIDEr: 74.3 -> 80.3 | Improved |
| add CAM to VidSwin + VLT (ablation) | VidSwin + VLT · BDD-X narration | BLEU-4: 32.9 -> 34.2 | Improved |
| add 3DResNet local features to VidSwin via MFE (with VLT) (ablation) | VidSwin + VLT · BDD-X narration | BLEU-4: 32.9 -> 33.4 | Improved |
| add 3DResNet local features to VidSwin via MFE (with VLT) (ablation) | VidSwin + VLT · BDD-X narration | CIDEr: 235.8 -> 218.1 | Hurt |
| use VidSwin instead of 3DResNet encoder with VLT (ablation) | VLT · BDD-X reasoning | CIDEr: 55.3 -> 74.3 | Improved |
| use full MCAM instead of baseline ADAPT | MCAM · CoVLA | CIDEr: 236.9 -> 275.4 | Improved |
| use full MCAM instead of baseline ADAPT | MCAM · BDD-X reasoning | METEOR: 14.6 -> 14.0 | Hurt |
| MCAM versus RAG-Driver (7.08B params) | MCAM · BDD-X narration | CIDEr: 260.8 -> 252.0 | Hurt |
| MCAM versus DriveGPT4 on reasoning | MCAM · BDD-X reasoning | CIDEr: 102.7 -> 94.1 | Hurt |
| MCAM versus LCP on DRAMA | MCAM · DRAMA | BLEU-4: 54.7 -> 62.4 | Improved |
Closest papers by meaning
- CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention (CVPR 2026 · similarity 0.88)
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models (ICML 2025 · similarity 0.87)
- H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving (AAAI 2025 · similarity 0.87)
- Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models (CVPR 2024 · similarity 0.86)
- MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception (CVPR 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.
