Xinyu Zhang

Effects of Street-Renewal Elements on Pedestrian Safety Behavior and Perception: A Multimodal Immersive Virtual Environment Experiment

Shimeng Hao, Mengjiao Li, Wenbo Guo, Lu Xing et autres

cn (code pays fourni par la source)

Visual-Guidance Interventions for Child Pedestrian Behavior: An Empirical Study Employing Multimodal Experiments

Wenjie Peng, Xinyu Zhang, Bingmiao Zhu, Shimeng Hao et autres

As urbanization accelerates, children’s safety when crossing urban streets has become an increasingly prominent concern. However, current street designs and visual guidance facilities are largely configured around adult users and tend to overlook children’s distinct cognitive and perceptual characteristics. In this study, …

cn (code pays fourni par la source)

Towards Safety-Critical Autonomous Driving: A Survey on the Progressive Evolution of Bird's-Eye-View Perception

Yan Gong, N. Y. Wang, Jianli Lu, Xinyu Zhang et autres

Bird's-Eye-View (BEV) perception has become a foundational paradigm in autonomous driving, enabling unified spatial representations that support robust multi-sensor fusion and multi-agent collaboration. As autonomous vehicles transition from controlled environments to real-world deployment, ensuring the safety and reliability of BEV perception in …

Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Survey

Yan Gong, N. Y. Wang, Jianli Lu, Xinyu Zhang et autres

Bird's-Eye-View (BEV) perception has become a foundational paradigm in autonomous driving, enabling unified spatial representations that support robust multi-sensor fusion and multi-agent collaboration. As autonomous vehicles transition from controlled environments to real-world deployment, ensuring the safety and reliability of BEV perception in …

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding

Muye Huang, Han Lai, Xinyu Zhang, Wenjun Wu et autres

Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart …

cn (code pays fourni par la source)

VProChart: Answering Chart Question Through Visual Perception Alignment Agent and Programmatic Solution Reasoning

Muye Huang, Lingling Zhang, Han Lai, Wenjun Wu et autres

Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in charts. However, chart images are inherently difficult to …

cn (code pays fourni par la source)

Exploring the Role Imagery Preference of Medical Virtual Agents Developed Through Prompt Engineering for the Chinese Elderly: A Mixed-Methods Study

Xinyu Zhang, Chengqi Xue

cn (code pays fourni par la source)

Diagram-Driven Course Questions Generation

Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang et autres

Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Wenjun Wu, Bo Li, Shaowei Wang, Basura Fernando, Jun Liu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

bd, cn, sg (code pays fourni par la source)

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding

Muye Huang, Han Lai, Xinyu Zhang, Wenjun Wu et autres

Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart …

VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning

Muye Huang, Lingling Zhang, Han Lai, Wenjun Wu et autres

Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in charts. However, chart images are inherently difficult to …

Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation

Raphael Tang, Xinyu Zhang, Lixinyu Xu, Yao Lu et autres

Diffusion models are the state of the art in text-to-image generation, but their perceptual variability remains understudied. In this paper, we examine how prompts affect image variability in black-box diffusion-based models. We propose W1KP, a human-calibrated measure of variability in a set …

Interactive Spectral-Spatial Transformer for Hyperspectral Image Classification

Liangliang Song, Zhixi Feng, Shuyuan Yang, Xinyu Zhang et autres

The abundant spectral signatures and spatial contexts are effectively utilized as the key to hyperspectral image (HSI) classification. Existing convolutional neural networks (CNNs), only focus on locally spatial context information and lack the ability to learn global spectral sequence representations, whereas the …

cn (code pays fourni par la source)