用大模型分析视频，自动识别车祸，提升智能交通系统安全性。
Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges
- 结合视觉与语言模型，融合多模态信息进行车祸判断。
- 梳理了主流数据集与模型架构，对比了性能表现。
- 适合关注视频理解与大模型应用的研究者参考。
从视频流中检测车祸是智能交通系统中的关键问题。近年来，大语言模型（LLMs）和视觉-语言模型（VLMs）的发展，彻底改变了我们对多模态信息的处理、推理与摘要方式。本文综述了近期利用大语言模型进行视频车祸检测的方法。系统梳理了融合策略的分类体系，总结了关键数据集，分析了模型架构，对比了性能基准，并探讨了当前面临的挑战与机遇。本综述为该快速发展的视频理解与基础模型交叉领域研究提供了坚实基础。
原文摘要 · Abstract (English)
Crash detection from video feeds is a critical problem in intelligent transportation systems. Recent developments in large language models (LLMs) and vision-language models (VLMs) have transformed how we process, reason about, and summarize multimodal information. This paper surveys recent methods leveraging LLMs for crash detection from video data. We present a structured taxonomy of fusion strategies, summarize key datasets, analyze model architectures, compare performance benchmarks, and discuss ongoing challenges and opportunities. Our review provides a foundation for future research in this fast-growing intersection of video understanding and foundation models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。