Bin Ren

A survey on urban traffic signal control using deep reinforcement learning

Hao Zhang, Bin Ren, Chunhong He

Urban traffic congestion has become increasingly severe, and traffic signal control has emerged as a key mitigation measure. In recent years, deep reinforcement learning (DRL) has been widely applied to the field of traffic signal control due to its advantages in perception …

cn (code pays fourni par la source)

A review of graph neural networks in traffic forecasting

Bin Ren, Hexiao Fan, Chunhong He

Intelligent transportation is of great significance in urban construction, traffic prediction constitutes a vital component within intelligent transportation systems(ITS). Deep learning methods, especially convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have become the main framework for contemporary traffic prediction tasks. …

cn (code pays fourni par la source)

Optimizing 3D Gaussian Splattering for Mobile GPUs

Md Musfiqur Rahman Sanim, Zhihao Shu, Bahram Afsharmanesh, AmirAli Mirian et autres

Image-based 3D scene reconstruction, which transforms multi-view images into a structured 3D representation of the surrounding environment, is a common task across many modern applications. 3D Gaussian Splatting (3DGS) is a new paradigm to address this problem and offers considerable efficiency as …

us (code pays fourni par la source)

Wavelength-selective multifunctional light control with inverse designed dielectric metasurface

Zhenyu Wang, Bin Ren, Fei Xie, Mingzhao Song

The metasurface has emerged as a powerful platform for achieving versatile and precise light control due to its extraordinary optical properties. However, multifunctional metasurface-based devices, usually employing shared apertures or cascading with different metasurfaces, suffer from inherent interference and complex configurations. Here, …

cn (code pays fourni par la source)

A Survey of Deep Reinforcement Learning for Robotic Arm Trajectory Planning

Bin Ren, Chunhong He

With the continuous development of intelligent manufacturing and industrial automation, the accuracy of robotic arm trajectory planning has become increasingly crucial. This accuracy is decisive for performing complex tasks, achieving dynamic obstacle avoidance, and enhancing the safety of human-machine collaboration. However, traditional …

cn (code pays fourni par la source)

Layered hierarchical porous nitrogen-doped carbon-supported PtFe alloy catalysts for oxygen reduction reaction

Bingjie Zhou, Yuankai Shao, Weikang Zhu, Shuoyao Yin et autres

Abstract The development of cost-effective and durable oxygen reduction reaction (ORR) catalysts is crucial for advancing proton exchange membrane fuel cells (PEMFCs). PtFe alloy catalysts have emerged as a key research focus. However, weak interactions between conventional carbon supports and transition metals …

cn (code pays fourni par la source)

Modeling of the Bearing Capacity Degradation of Tunnel Invert Structures under Corrosion-Fatigue Coupling Effects

Wenzheng He, Bin Ren

In salt-rich environments, tunnel inverts are subjected to the combined effects of corrosion and fatigue loads.Fatigue loads accelerate the transport of corrosion ions and the degradation of the bearing capacity of inverts.To elucidate the attenuation behavior of the bearing capacity of tunnel …

cn (code pays fourni par la source)

Silver nanoparticles embedded chitosan-gelatin polymeric composite: Green synthesis, characterization, and investigation of its catalytic activity and protective effect on cerebral ischemia-reperfusion injury in rats

Bin Ren, Xiaocong Wei, Leifang Yang

After an ischemic stroke, mechanical recanalization or thrombolysis can be used to restore blood flow. Reperfusion, however, may worsen the ischemia-induced harm in certain patients, resulting in a condition known as “cerebral reperfusion injury.” This injury is caused by various pathogenic events, …

cn (code pays fourni par la source)

The Tenth NTIRE 2025 Image Denoising Challenge Report

Lei Sun, Hang Guo, Bin Ren, Luc Van Gool et autres

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge ($\sigma=50$), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising performance, quantitatively evaluated using PSNR, without constraints on …

bg, it, gr (code pays fourni par la source)

NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results

Yuqian Fu, Xingyu Qiu, Bin Ren, Yanwei Fu et autres

Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains. In conjunction with NTIRE 2025, we organized the 1st CDFSOD Challenge, aiming to advance the performance of current object detectors on entirely …

NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results

Yuqian Fu, Xingyu Qiu, Bin Ren, Yanwei Fu et autres

Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains. In conjunction with NTIRE 2025, we organized the 1st CD-FSOD Challenge, aiming to advance the performance of current object detectors on entirely …

An Adaptive Grid Generation Approach to Pipeline Leakage Rapid Localization Based on Time Reversal

Yu Wang, Haoyang Chen, Yang Yang, Haoyu Zhou et autres

Gas pipeline leakage will result in casualties and property losses if not detected in time. Conventional leakage localization methods usually rely on dense grid distribution, leading to high computational costs. This study proposes a time-reversal-based adaptive grid generation approach to enhance computational …

cn (code pays fourni par la source)