paper-with-me

홈 › Papers

Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipation

2025-07-17 · Yanchen Guan, Haicheng Liao, Chengyue Wang, Bonan Wang, Jiaxun Zhang, Jia Hu, Zhenning Li arxiv

Developing precise and computationally efficient traffic accident anticipation system is crucial for contemporary autonomous driving technologies, enabling timely intervention and loss prevention. In this paper, we propose an accident anticipation framework employing a dual-branch architecture that effectively integrates visual information from dashcam videos with structured textual data derived from accident reports. Furthermore, we introduce a feature aggregation method that facilitates seamless integration of multimodal inputs through large models (GPT-4o, Long-CLIP), complemented by targeted prompt engineering strategies to produce actionable feedback and standardized accident archives. Comprehensive evaluations conducted on benchmark datasets (DAD, CCD, and A3D) validate the superior predictive accuracy, enhanced responsiveness, reduced computational overhead, and improved interpretability of our approach, thus establishing a new benchmark for state-of-the-art performance in traffic accident anticipation.

📄 PDF Abstract BibTeX arXiv:2507.12755

Code (0)

등록된 구현이 없습니다.

Tasks

Accident AnticipationPrompt EngineeringAutonomous Driving

Similar Papers 제목 키워드 기반

FD-DB: Frequency-Decoupled Dual-Branch Network for Unpaired Synthetic-to-Real Domain Translation

2026-02-10 · Chuanhai Zang, Jiabao Hu, XW Song arxiv

Synthetic data provide low-cost, accurately annotated samples for geometry-sensitive vision tasks, but appearance and imaging differences between synthetic and real domains cause severe domain shift and degrade downstrea…

Synthetic-to-Real TranslationSemantic Segmentation

SIEFormer: Spectral-Interpretable and -Enhanced Transformer for Generalized Category Discovery

2026-02-13 · Chunming Li, Shidong Wang, Tong Xin, Haofeng Zhang arxiv

This paper presents a novel approach, Spectral-Interpretable and -Enhanced Transformer (SIEFormer), which leverages spectral analysis to reinterpret the attention mechanism within Vision Transformer (ViT) and enhance fea…

AVD2: Accident Video Diffusion for Accident Video Description

2025-02-20 · Cheng Li, Keyuan Zhou, Tong Liu, Yu Wang 외

Traffic accidents present complex challenges for autonomous driving, often featuring unpredictable scenarios that hinder accurate system interpretation and responses.Nonetheless, prevailing methodologies fall short in el…

Autonomous DrivingScene UnderstandingVideo DescriptionVideo Understanding

Boosting Ultrasound Image Classification via Attribute-Guided Dual-Branch Framework

2026-07-02 · Bo Zhao, Yapeng Li, Juhua Liu, Bo Du arxiv

Ultrasound image classification is essential for computer-aided diagnosis. However, current methods often neglect clinical priors, leading to poor generalization in challenging scenarios and a lack of interpretability th…

Image Classification

Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents

2021-07-31 · Muhammad Monjurul Karim, Yu Li, Ruwen Qin

Traffic accident anticipation is a vital function of Automated Driving Systems (ADSs) for providing a safety-guaranteed driving experience. An accident anticipation model aims to predict accidents promptly and accurately…

Accident AnticipationDecision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)