# MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding

arXiv: https://arxiv.org/abs/2507.06072 · HTML: https://mlsanity.com/paper/2507.06072/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving.
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Placed in

- End-to-end autonomous driving / [End-to-end system architecture](https://mlsanity.com/driving/end-to-end-system-architecture/)

## Builds on (most cited first, 30 of 33)

- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [Textual Explanations for Self-Driving Vehicles](https://mlsanity.com/paper/1807.11546/) (2018)
- [Query-Dependent Video Representation for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2303.13874/) (2023)
- [SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning](https://mlsanity.com/paper/2111.13196/) (2021)
- [Sequence to Sequence -- Video to Text](https://mlsanity.com/paper/1505.00487/) (2015)
- [LingoQA: Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2312.14115/) (2023)
- [DRAMA: Joint Risk Localization and Captioning in Driving](https://mlsanity.com/paper/2209.10767/) (2022)
- [MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens](https://mlsanity.com/paper/2404.03413/) (2024)
- [Causal Attention for Vision-Language Tasks](https://mlsanity.com/paper/2103.03493/) (2021)
- [CLadder: Assessing Causal Reasoning in Language Models](https://mlsanity.com/paper/2312.04350/) (2023)
- [Video ReCap: Recursive Captioning of Hour-Long Videos](https://mlsanity.com/paper/2402.13250/) (2024)
- [CLIP4Caption: CLIP for Video Caption](https://mlsanity.com/paper/2110.06615/) (2021)
- [ADAPT: Action-aware Driving Caption Transformer](https://mlsanity.com/paper/2302.00673/) (2023)
- [CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving](https://mlsanity.com/paper/2408.10845/) (2024)
- [Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning](https://mlsanity.com/paper/1902.10322/) (2019)
- [Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering](https://mlsanity.com/paper/2207.12647/) (2022)
- [Retrieval-Augmented Egocentric Video Captioning](https://mlsanity.com/paper/2401.00789/) (2024)
- [Text with Knowledge Graph Augmented Transformer for Video Captioning](https://mlsanity.com/paper/2303.12423/) (2023)
- [Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer](https://mlsanity.com/paper/2308.08414/) (2023)
- [TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning](https://mlsanity.com/paper/2404.09275/) (2024)
- [Visual Causal Scene Refinement for Video Question Answering](https://mlsanity.com/paper/2305.04224/) (2023)
- [Weakly-Supervised Video Object Grounding via Causal Intervention](https://mlsanity.com/paper/2112.00475/) (2021)
- [Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval](https://mlsanity.com/paper/2412.19178/) (2024)
- [Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation](https://mlsanity.com/paper/2303.14361/) (2023)
- [Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference](https://mlsanity.com/paper/2401.01426/) (2024)
- [RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2412.11050/) (2024)
- [MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios](https://mlsanity.com/paper/2412.19406/) (2024)

## Built on by (most cited first, 1 of 1)

- [Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning](https://mlsanity.com/paper/2604.15705/) (2026)

## Abstract (arXiv)

Accurate driving behavior recognition and reasoning are critical for autonomous driving video understanding. However, existing methods often tend to dig out the shallow causal, fail to address spurious correlations across modalities, and ignore the ego-vehicle level causality modeling. To overcome these limitations, we propose a novel Multimodal Causal Analysis Model (MCAM) that constructs latent causal structures between visual and language modalities. Firstly, we design a multi-level feature extractor to capture long-range dependencies. Secondly, we design a causal analysis module that dynamically models driving scenarios using a directed acyclic graph (DAG) of driving states. Thirdly, we utilize a vision-language transformer to align critical visual features with their corresponding linguistic expressions. Extensive experiments on the BDD-X, and CoVLA datasets demonstrate that MCAM achieves SOTA performance in visual-language causal relationship learning. Furthermore, the model exhibits superior capability in capturing causal characteristics within video sequences, showcasing its effectiveness for autonomous driving applications. The code is available at https://github.com/SixCorePeach/MCAM.