Yanchen Guan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yanchen Guan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Zhenning Li
University of Macau
5 shared publications - Chengyue Wang
State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China
3 shared publications - Haicheng Liao
State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China
3 shared publications - Cheng-Zhong Xu
State Key Laboratory of IoTSC, University of Macau, Macau, Macao
2 shared publications - Jiaxun Zhang
University of Macau
2 shared publications Bin Rao
State Key Laboratory of Internet of Things for Smart City, University of Macau, Zhuhai, Macau
1 shared publication
Latest Publications
- 15 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-15
U3A: Uncertainty-Aware Accident Anticipation for Reliable Autonomous Driving
Accident anticipation is essential for autonomous driving, yet existing video-based models often exhibit unstable predictions because they insufficiently account for the uncertainty that accumulates over long temporal sequences. Such instability leads to fluctuating confidence and unreliable alert timing in complex traffic environments. We propose U3A, an uncertainty-aware framework that improves the reliability of accident anticipation by jointly stabilizing representations and regulating decision behavior. U3A introduces a dual diffusion refinement module that enforces temporal coherence at both image and object levels, reducing abrupt feature shifts caused by occlusion and scene variability. To quantify epistemic uncertainty, the framework applies Monte Carlo Dropout over historical states and incorporates these estimates into a time-sensitive actor–critic policy, which learns to delay alerts under unstable confidence and issue warnings only when risk is consistently supported. Experiments on DAD, CCD, A3D, and AoTA show that U3A achieves state-of-the-art accuracy and mean time-to-accident, while producing smoother and more dependable alert trajectories. The results demonstrate that integrating diffusion-based feature refinement with uncertainty-guided policy learning offers a practical path toward more reliable accident anticipation for autonomous vehicles.
- 15 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-15
U3A: Uncertainty-Aware Accident Anticipation for Reliable Autonomous Driving
Accident anticipation is essential for autonomous driving, yet existing video-based models often exhibit unstable predictions because they insufficiently account for the uncertainty that accumulates over long temporal sequences. Such instability leads to fluctuating confidence and unreliable alert timing in complex traffic environments. We propose U3A, an uncertainty-aware framework that improves the reliability of accident anticipation by jointly stabilizing representations and regulating decision behavior. U3A introduces a dual diffusion refinement module that enforces temporal coherence at both image and object levels, reducing abrupt feature shifts caused by occlusion and scene variability. To quantify epistemic uncertainty, the framework applies Monte Carlo Dropout over historical states and incorporates these estimates into a time-sensitive actor–critic policy, which learns to delay alerts under unstable confidence and issue warnings only when risk is consistently supported. Experiments on DAD, CCD, A3D, and AoTA show that U3A achieves state-of-the-art accuracy and mean time-to-accident, while producing smoother and more dependable alert trajectories. The results demonstrate that integrating diffusion-based feature refinement with uncertainty-guided policy learning offers a practical path toward more reliable accident anticipation for autonomous vehicles.
- 16 January 2026
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 228, 108414
ROAR: Robust accident recognition and anticipation for autonomous driving
- 16 January 2026
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 228, 108414
ROAR: Robust accident recognition and anticipation for autonomous driving
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12054-12063
Eyes on the Road, Mind Beyond Vision: Context-Aware Multi-modal Enhanced Risk Anticipation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12054-12063
Open AccessEyes on the Road, Mind Beyond Vision: Context-Aware Multi-modal Enhanced Risk Anticipation
- 9 April 2025
- Published by Elsevier in Information Fusion
- Vol. 122
LATTE: A Real-time Lightweight Attention-based Traffic Accident Anticipation Engine
- 9 April 2025
- Published by Elsevier in Information Fusion
- Vol. 122
LATTE: A Real-time Lightweight Attention-based Traffic Accident Anticipation Engine
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8-17
When, Where, and What? A Benchmark for Accident Anticipation and Localization with Large Language Models
As autonomous driving systems increasingly become part of daily transportation, the ability to accurately anticipate and mitigate potential traffic accidents is paramount. Traditional accident anticipation models primarily utilizing dashcam videos are adept at predicting when an accident may occur but fall short in localizing the incident and identifying involved entities. Addressing this gap, this study introduces a novel framework that integrates Large Language Models (LLMs) to enhance predictive capabilities across multiple dimensions-what, when, and where accidents might occur. We develop an innovative chain-based attention mechanism that dynamically adjusts to prioritize high-risk elements within complex driving scenes. This mechanism is complemented by a three-stage model that processes outputs from smaller models into detailed multimodal inputs for LLMs, thus enabling a more nuanced understanding of traffic dynamics. Empirical validation on the DAD, CCD, and A3D datasets demonstrates superior performance in Average Precision (AP) and Mean Time-To-Accident (mTTA), establishing new benchmarks for accident prediction technology. Our approach not only advances the technological framework for autonomous driving safety but also enhances human-AI interaction, making predictive insights generated by autonomous systems more intuitive and actionable.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8-17
Open AccessWhen, Where, and What? A Benchmark for Accident Anticipation and Localization with Large Language Models
As autonomous driving systems increasingly become part of daily transportation, the ability to accurately anticipate and mitigate potential traffic accidents is paramount. Traditional accident anticipation models primarily utilizing dashcam videos are adept at predicting when an accident may occur but fall short in localizing the incident and identifying involved entities. Addressing this gap, this study introduces a novel framework that integrates Large Language Models (LLMs) to enhance predictive capabilities across multiple dimensions-what, when, and where accidents might occur. We develop an innovative chain-based attention mechanism that dynamically adjusts to prioritize high-risk elements within complex driving scenes. This mechanism is complemented by a three-stage model that processes outputs from smaller models into detailed multimodal inputs for LLMs, thus enabling a more nuanced understanding of traffic dynamics. Empirical validation on the DAD, CCD, and A3D datasets demonstrates superior performance in Average Precision (AP) and Mean Time-To-Accident (mTTA), establishing new benchmarks for accident prediction technology. Our approach not only advances the technological framework for autonomous driving safety but also enhances human-AI interaction, making predictive insights generated by autonomous systems more intuitive and actionable.