MM-AU 多模态事故视频理解数据集

MM-AU 是一个专注于多模态事故视频理解的大型数据集，旨在为安全驾驶感知领域提供高质量的数据支持，由西安交通大学、长安大学、新加坡国立大学、克里夫兰州立大学和南洋理工大学的研究人员于 2024 年发布，相关论文成果为「Abductive Ego-View Accident Video Understanding for Safe Driving Perception」，并被 CVPR2024 Highlight 接收。

MM-AU is a large-scale dataset focused on multimodal accident video understanding, aiming to provide high-quality data support for the field of safe driving perception. It was released in 2024 by researchers from Xi'an Jiaotong University, Chang'an University, National University of Singapore, Cleveland State University, and Nanyang Technological University. Its associated research paper is titled "Abductive Ego-View Accident Video Understanding for Safe Driving Perception", and it was accepted as a Highlight paper at CVPR 2024.

搜集汇总

背景与挑战

背景概述

MM-AU是一个大型多模态事故视频理解数据集，包含11,727个自我视角事故视频和超过223万个道路参与者边界框标注，涵盖58种事故类别。该数据集旨在为安全驾驶感知研究提供高质量数据支持，特别适用于自动驾驶领域。