mlsanityData to 7 Oct 2026

AVD2: Accident Video Diffusion for Accident Video Description

arXiv 2502.14801 ↗First posted 20 Feb 2025cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Traffic accidents present complex challenges for autonomous driving, often featuring unpredictable scenarios that hinder accurate system interpretation and responses. Nonetheless, prevailing methodologies fall short in elucidating the causes of accidents and proposing preventive measures due to the paucity of training data specific to accident scenarios. In this work, we introduce AVD2 (Accident Video Diffusion for Accident Video Description), a novel framework that enhances accident scene understanding by generating accident videos that aligned with detailed natural language descriptions and reasoning, resulting in the contributed EMM-AU (Enhanced Multi-Modal Accident Video Understanding) dataset. Empirical results reveal that the integration of the EMM-AU dataset establishes state-of-the-art performance across both automated metrics and human evaluations, markedly advancing the domains of accident analysis and prevention. Project resources are available at https://an-answer-tree.github.io

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 53 of its 77 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

53 of 77 references.

References · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  4. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  5. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  7. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  8. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  9. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  10. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  11. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 637
  12. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
38 more
  1. 2016Self-critical Sequence Training for Image Captioningcited by 544
  2. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  3. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  4. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  5. 2016Generating Videos with Scene Dynamicscited by 376
  6. 2023NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenariocited by 258
  7. 2018Stochastic Video Generation with a Learned Priorcited by 244
  8. 2021End-to-end Interpretable Neural Motion Plannercited by 240
  9. 2018Textual Explanations for Self-Driving Vehiclescited by 226
  10. 2018Adaptive Input Representations for Neural Language Modelingcited by 226
  11. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  12. 2018Scaling Neural Machine Translationcited by 204
  13. 2023DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusioncited by 167
  14. 2023Panacea: Panoramic and Controllable Video Generation for Autonomous Drivingcited by 165
  15. 2021SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioningcited by 161
  16. 2023LingoQA: Visual Question Answering for Autonomous Drivingcited by 144
  17. 2021End-to-End Dense Video Captioning with Parallel Decodingcited by 133
  18. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  19. 2017Interpretable Learning for Self-Driving Cars by Visualizing Causal Attentioncited by 106
  20. 2021SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Eventscited by 84
  21. 2023ADAPT: Action-aware Driving Caption Transformercited by 78
  22. 2017Automatic Understanding of Image and Video Advertisementscited by 67
  23. 2018Discriminability objective for training descriptive captionscited by 67
  24. 2022Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answeringcited by 57
  25. 2023Text2Performer: Text-Driven Human Video Generationcited by 53
  26. 2024MagicTime: Time-lapse Video Generation Models as Metamorphic Simulatorscited by 51
  27. 2017Deep Video Generation, Prediction and Completion of Human Action Sequencescited by 50
  28. 2024Abductive Ego-View Accident Video Understanding for Safe Driving Perceptioncited by 43
  29. 2024MonoOcc: Digging into Monocular Semantic Occupancy Predictioncited by 43
  30. 2024Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Drivingcited by 33
  31. 2023Towards Flexible Multi-modal Document Modelscited by 30
  32. 2020A Better Variant of Self-Critical Sequence Trainingcited by 23
  33. 2022Understanding Embodied Reference with Touch-Line Transformercited by 16
  34. 2023Delving into Shape-aware Zero-shot Semantic Segmentationcited by 16
  35. 2023Explaining Autonomous Driving Actions with Visual Question Answeringcited by 16
  36. 2024Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modelingcited by 14
  37. 2024Text2Street: Controllable Text-to-image Generation for Street Viewscited by 13
  38. 2024Is it safe to cross? Interpretable Risk Assessment with GPT-4V for Safety-Aware Street Crossingcited by 12

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 6.

20 papers.

Sort:

By area:

  1. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Modelscited by 60
  2. 2025Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysiscited by 37
  3. 2025Challenger: Affordable Adversarial Driving Video Generationcited by 16
  4. 2025PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Modelcited by 15
  5. 2025CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splattingcited by 11
  6. 2025WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Drivingcited by 9
  7. 2025SafeMVDrive: Multi-view Safety-Critical Driving Video Synthesis in the Real World Domaincited by 6
  8. 2025Ctrl-Crash: Controllable Diffusion for Realistic Car Crashescited by 5
  9. 2025HomeSafeBench: Benchmarking Embodied Vision-Language Models in Free-Exploration Home Safety Inspectioncited by 4
  10. 2025FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Bankscited by 3
  11. 2025Towards Vision Zero: The TUM Traffic Accid3nD Datasetcited by 2
  12. 2025Causal-Entity Reflected Egocentric Traffic Accident Video Synthesiscited by 2
8 more
  1. 2025CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Drivingcited by 2
  2. 2026UniUncer: Unified Dynamic Static Uncertainty for End to End Drivingcited by 2
  3. 2026A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Modelscited by 1
  4. 2025LC4-DViT: Land-cover Creation for Land-cover Classification with Deformable Vision Transformercited by 0
  5. 2026Learning physically grounded traffic accident reconstruction from public accident reportscited by 0
  6. 2026Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipationcited by 0
  7. 2026TRACER: Training-Free Closed-Loop Structured Inference for Traffic Accident Reconstructioncited by 0
  8. 2026SSP: An Event-Matched Syn2Sim2Phy Cross-Domain Evaluation Framework for Autonomous Driving VLA Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
  2. 2025EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis
  3. 2025Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam Videos
  4. 2025VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding
  5. 2025AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports
  6. 2026CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
  7. 2026CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios
  8. 2024Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding