paper-with-me

홈 › Papers

Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam Videos

2025-10-14 · Shingo Yokoi, Kento Sasaki, Yu Yamaguchi arxiv

Recent advances in end-to-end (E2E) autonomous driving have been enabled by training on diverse large-scale driving datasets, yet autonomous driving models still struggle in out-of-distribution (OOD) scenarios. The COOOL benchmark targets this gap by encouraging hazard understanding beyond closed taxonomies, and the 2COOOL challenge extends it to generating human-interpretable incident reports. We present a hierarchical reasoning framework for incident report generation from dashcam videos that integrates frame-level captioning, incident frame detection, and fine-grained reasoning within vision-language models (VLMs). We further improve factual accuracy and readability through model ensembling and a Blind A/B Scoring selection protocol. On the official 2COOOL open leaderboard, our method ranks 2nd among 29 teams and achieves the best CIDEr-D score, producing accurate and coherent incident narratives. These results indicate that hierarchical reasoning with VLMs is a promising direction for accident analysis and for broader understanding of safety-critical traffic events. The implementation and code are available at https://github.com/riron1206/kaggle-2COOOL-2nd-Place-Solution.

📄 PDF Abstract BibTeX arXiv:2510.12190

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving

Similar Papers 제목 키워드 기반

Multi-view Phase-aware Pedestrian-Vehicle Incident Reasoning Framework with Vision-Language Models

2025-11-18 · Hao Zhen, Yunxiang Yang, Jidong J. Yang arxiv

Pedestrian-vehicle incidents remain a critical urban safety challenge, with pedestrians accounting for over 20% of global traffic fatalities. Although existing video-based systems can detect when incidents occur, they pr…

Scene UnderstandingQuestion Answering

Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports

2026-05-15 · Anita Srbinovska, Jansen Orfan, Adrian Martin, Ernest Fokoué arxiv

Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural language and require manual reading. W…

Semantic Parsing

AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented Generation

2025-08-18 · Zefang Liu, Arman Anwar arxiv

Incident response (IR) requires fast, coordinated, and well-informed decision-making to contain and mitigate cyber threats. While large language models (LLMs) have shown promise as autonomous agents in simulated IR setti…

Enhancing Traffic Incident Management with Large Language Models: A Hybrid Machine Learning Approach for Severity Classification

2024-03-20 · Artur Grigorev, Khaled Saleh, Yuming Ou, Adriana-Simona Mihaita

This research showcases the innovative integration of Large Language Models into machine learning workflows for traffic incident management, focusing on the classification of incident severity using accident reports. By …

ClassificationFeature EngineeringHybrid Machine LearningLanguage Modelling+1

Extracting Events from Industrial Incident Reports

2021-08-01 · ACL (CASE) 2021 8 · Nitin Ramrakhiyani, Swapnil Hingmire, Sangameshwar Patil, Alok Kumar 외

Incidents in industries have huge social and political impact and minimizing the consequent damage has been a high priority. However, automated analysis of repositories of incident reports has remained a challenge. In th…

Transfer Learning