Summary of Abductive Ego-view Accident Video Understanding For Safe Driving Perception, by Jianwu Fang et al.
Abductive Ego-View Accident Video Understanding for Safe Driving Perception
by Jianwu Fang, Lei-lei Li, Junfei Zhou, Junbin Xiao, Hongkai Yu, Chen Lv, Jianru Xue, Tat-Seng Chua
First submitted to arxiv on: 1 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents MM-AU, a novel dataset for Multi-Modal Accident video Understanding, containing 11,727 in-the-wild ego-view accident videos with temporally aligned text descriptions. The dataset is annotated with 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. To this end, the authors propose an Abductive accident Video understanding framework for Safe Driving perception (AdVersa-SD), which consists of an Object-Centric Video Diffusion (OAVD) method driven by an abductive CLIP model. The OAVD method learns the pair co-occurrence of normal, near-accident, and accident frames with corresponding text descriptions, and enforces causal region learning while fixing the content of the original frame background in video generation. The authors conduct extensive experiments to verify the abductive ability of AdVersa-SD and its superiority over state-of-the-art diffusion models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new dataset called MM-AU that helps machines understand car accidents from videos. It has lots of annotated data, which is useful for training AI systems. The authors also propose a special way to analyze these videos using a method called Object-Centric Video Diffusion (OAVD). This method can help predict what caused an accident and how it might have been prevented. The paper shows that their approach works better than others in this field. |
Keywords
» Artificial intelligence » Diffusion » Multi modal
