# Abductive Ego-View Accident Video Understanding for Safe Driving Perception

arXiv: https://arxiv.org/abs/2403.00436 · HTML: https://mlsanity.com/paper/2403.00436/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 73 references that are in the map.
- First posted on arXiv 1 Mar 2024.

## Builds on (most cited first, 30 of 47)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [ControlVideo: Training-free Controllable Text-to-Video Generation](https://mlsanity.com/paper/2305.13077/) (2023)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://mlsanity.com/paper/2205.09853/) (2022)
- [Self-Chained Image-Language Model for Video Localization and Question Answering](https://mlsanity.com/paper/2305.06988/) (2023)
- [Hierarchical Conditional Relation Networks for Video Question Answering](https://mlsanity.com/paper/2002.10698/) (2020)
- [Can I Trust Your Answer? Visually Grounded Video Question Answering](https://mlsanity.com/paper/2309.01327/) (2023)

## Built on by (most cited first, 30 of 43)

- [StreamForest: Efficient Online Video Understanding with Persistent Event Memory](https://mlsanity.com/paper/2509.24871/) (2025)
- [Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments](https://mlsanity.com/paper/2605.30280/) (2026)
- [Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis](https://mlsanity.com/paper/2506.11526/) (2025)
- [Nexar Dashcam Collision Prediction Dataset and Challenge](https://mlsanity.com/paper/2503.03848/) (2025)
- [AVD2: Accident Video Diffusion for Accident Video Description](https://mlsanity.com/paper/2502.14801/) (2025)
- [VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding](https://mlsanity.com/paper/2507.09815/) (2025)
- [RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives](https://mlsanity.com/paper/2503.21459/) (2025)
- [WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving](https://mlsanity.com/paper/2511.20022/) (2025)
- [Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving](https://mlsanity.com/paper/2609.00111/) (2026)
- [Real-time Traffic Accident Anticipation with Feature Reuse](https://mlsanity.com/paper/2505.17449/) (2025)
- [Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving](https://mlsanity.com/paper/2403.12176/) (2024)
- [SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding](https://mlsanity.com/paper/2508.06763/) (2025)
- [Dual-AEB: Synergizing Rule-Based and Multimodal Large Language Models for Effective Emergency Braking](https://mlsanity.com/paper/2410.08616/) (2024)
- [Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen](https://mlsanity.com/paper/2505.21743/) (2025)
- [Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes](https://mlsanity.com/paper/2506.00227/) (2025)
- [VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models](https://mlsanity.com/paper/2511.18823/) (2025)
- [BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data](https://mlsanity.com/paper/2510.14876/) (2025)
- [Accident Anticipation via Temporal Occurrence Prediction](https://mlsanity.com/paper/2510.22260/) (2025)
- [When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network](https://mlsanity.com/paper/2506.17457/) (2025)
- [Towards Vision Zero: The TUM Traffic Accid3nD Dataset](https://mlsanity.com/paper/2503.12095/) (2025)
- [EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis](https://mlsanity.com/paper/2506.10002/) (2025)
- [Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis](https://mlsanity.com/paper/2506.23263/) (2025)
- [Understanding Real-World Traffic Safety through RoadSafe365 Benchmark](https://mlsanity.com/paper/2602.07212/) (2026)
- [RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation](https://mlsanity.com/paper/2603.27165/) (2026)
- [Hybrid Video Anomaly Detection for Anomalous Scenarios in Autonomous Driving](https://mlsanity.com/paper/2406.06423/) (2024)
- [What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies](https://mlsanity.com/paper/2507.06513/) (2025)
- [MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance](https://mlsanity.com/paper/2509.09730/) (2025)
- [CrashChat: A Multimodal Large Language Model for Multitask Traffic Crash Video Analysis](https://mlsanity.com/paper/2512.18878/) (2025)
- [UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics](https://mlsanity.com/paper/2602.21137/) (2026)
- [Interpretable Traffic Responsibility from Dashcam Video via Legal Multi Agent Reasoning](https://mlsanity.com/paper/2603.17930/) (2026)

## Abstract (arXiv)

We present MM-AU, a novel dataset for Multi-Modal Accident video Understanding. MM-AU contains 11,727 in-the-wild ego-view accident videos, each with temporally aligned text descriptions. We annotate over 2.23 million object boxes and 58,650 pairs of video-based accident reasons, covering 58 accident categories. MM-AU supports various accident understanding tasks, particularly multimodal video diffusion to understand accident cause-effect chains for safe driving. With MM-AU, we present an Abductive accident Video understanding framework for Safe Driving perception (AdVersa-SD). AdVersa-SD performs video diffusion via an Object-Centric Video Diffusion (OAVD) method which is driven by an abductive CLIP model. This model involves a contrastive interaction loss to learn the pair co-occurrence of normal, near-accident, accident frames with the corresponding text descriptions, such as accident reasons, prevention advice, and accident categories. OAVD enforces the causal region learning while fixing the content of the original frame background in video generation, to find the dominant cause-effect chain for certain accidents. Extensive experiments verify the abductive ability of AdVersa-SD and the superiority of OAVD against the state-of-the-art diffusion models. Additionally, we provide careful benchmark evaluations for object detection and accident reason answering since AdVersa-SD relies on precise object and accident reason information.