arXiv subjects

Zhongcheng Wu

Publications and source records attributed to Zhongcheng Wu.

3 recordsLinked to original sources

arXiv2025

CADD: A Chinese Traffic Accident Dataset for Statute-Based Liability Attribution

As autonomous driving technology advances, the critical challenge evolves beyond collision avoidance to the \textbf{adjudication of liability} when accidents occur. Existing datasets, focused on detection and localization, lack the annotations required for this legal reasoning. To bridge this gap, we introduce the \textbf{C}hinese \textbf{A}ccident \textbf{D}uty-determination \textbf{D}ataset (\textbf{CADD}), the first benchmark for statute-based liability attribution. CADD contains 792 real-world driving recorder videos, each annotated within a novel \textbf{``Behavior--Liability--Statute''} pipeline. This framework provides \textbf{granular, symmetric behavior annotations}, clear responsibility assignments, and, uniquely, links each case to the specific \textbf{Chinese traffic law statute} violated. We demonstrate the utility of CADD through detailed analysis and establish benchmarks for liability prediction and explainable decision-making. By directly connecting perceptual data to legal consequences, CADD provides a foundational resource for developing accountable and legally-grounded autonomous systems.

cs.CY↗

arXiv2024

MIFI: MultI-camera Feature Integration for Roust 3D Distracted Driver Activity Recognition

Distracted driver activity recognition plays a critical role in risk aversion-particularly beneficial in intelligent transportation systems. However, most existing methods make use of only the video from a single view and the difficulty-inconsistent issue is neglected. Different from them, in this work, we propose a novel MultI-camera Feature Integration (MIFI) approach for 3D distracted driver activity recognition by jointly modeling the data from different camera views and explicitly re-weighting examples based on their degree of difficulty. Our contributions are two-fold: (1) We propose a simple but effective multi-camera feature integration framework and provide three types of feature fusion techniques. (2) To address the difficulty-inconsistent problem in distracted driver activity recognition, a periodic learning method, named example re-weighting that can jointly learn the easy and hard samples, is presented. The experimental results on the 3MDAD dataset demonstrate that the proposed MIFI can consistently boost performance compared to single-view models.

cs.CV↗

arXiv2023

CarDD: A New Dataset for Vision-based Car Damage Detection

Automatic car damage detection has attracted significant attention in the car insurance business. However, due to the lack of high-quality and publicly available datasets, we can hardly learn a feasible model for car damage detection. To this end, we contribute with Car Damage Detection (CarDD), the first public large-scale dataset designed for vision-based car damage detection and segmentation. Our CarDD contains 4,000 highresolution car damage images with over 9,000 well-annotated instances of six damage categories. We detail the image collection, selection, and annotation processes, and present a statistical dataset analysis. Furthermore, we conduct extensive experiments on CarDD with state-of-the-art deep methods for different tasks and provide comprehensive analyses to highlight the specialty of car damage detection. CarDD dataset and the source code are available at https://cardd-ustc.github.io.

cs.CV↗