paper-with-me

홈 › Papers

EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights

2025-01-01 · CVPR 2025 1 · Zhenghao Xing, Hao Chen, Binzhu Xie, Jiaqi Xu, Ziyu Guo, Xuemiao Xu, Jianye Hao, Chi-Wing Fu, Xiaowei Hu, Pheng-Ann Heng

Traffic Anomaly Understanding (TAU) is essential for improving public safety and transportation efficiency by enabling timely detection and response to incidents. Beyond existing methods, which rely largely on visual data, we propose to consider audio cues, a valuable source that offers strong hints to anomaly scenarios such as crashes and honking. Our contributions are twofold. First, we compile AV-TAU, the first large-scale audio-visual dataset for TAU, providing 29,865 traffic anomaly videos and 149,325 Q&A pairs, while supporting five essential TAU tasks. Second, we develop EchoTraffic, a multimodal LLM that integrates audio and visual data for TAU, through our audio-insight frame selector and dynamic connector to effectively extract crucial audio cues for anomaly understanding with a two-phase training framework. Experimental results on AV-TAU manifest that EchoTraffic sets a new SOTA performance in TAU, outperforming the existing multimodal LLMs. Our contributions, including AV-TAU and EchoTraffic, pave a new direction for multimodal TAU.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Audio-Visual Dataset and Method for Anomaly Detection in Traffic Videos

2023-05-24 · Błażej Leporowski, Arian Bakhtiarnia, Nicole Bonnici, Adrian Muscat 외

We introduce the first audio-visual dataset for traffic anomaly detection taken from real-world scenes, called MAVAD, with a diverse range of weather and illumination conditions. In addition, we propose a novel method na…

Anomaly Detection

TAU-R1: Visual Language Model for Traffic Anomaly Understanding

2026-03-19 · Yuqiang Lin, Kehua Chen, Sam Lockyer, Arjun Yadav 외 arxiv

Traffic Anomaly Understanding (TAU) is important for traffic safety in Intelligent Transportation Systems. Recent vision-language models (VLMs) have shown strong capabilities in video understanding. However, progress on …

Anomaly Classification

Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding

2024-07-08 · Aaron Lohner, Francesco Compagno, Jonathan Francis, Alessandro Oltramari

Recognizing a traffic accident is an essential part of any autonomous driving or road monitoring system. An accident can appear in a wide variety of forms, and understanding what type of accident is taking place may be u…

Autonomous Driving

TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding

2026-08-26 · Yuqiang Lin, Yan Shi, Sam Lockyer, Harish Tayyar Madabushi 외 arxiv

Traffic Anomaly Understanding (TAU) requires models and systems to detect, reason about, and explain anomalous events in transportation videos. To address this challenge, we propose TAU-Agent, an agentic retrieval-augmen…

Answer GenerationVideo Captioning

From Vision to Sound: Advancing Audio Anomaly Detection with Vision-Based Algorithms

2025-02-25 · Manuel Barusco, Francesco Borsatti, Davide Dalle Pezze, Francesco Paissan 외

Recent advances in Visual Anomaly Detection (VAD) have introduced sophisticated algorithms leveraging embeddings generated by pre-trained feature extractors. Inspired by these developments, we investigate the adaptation …

Anomaly Detection