Zhigang Wang

In situ observation of comparative ZrO2 role in binary Al2O3-ZrO2 and ternary Al2O3-Er3Al5O12-ZrO2 eutectic microcantilever bending behavior

Xiaoqian Wang, Y. P. Zhang, Jiabei Zhang, Yonghui Ma et autres

Dual‐Aircraft Cooperative Occupying Method for Beyond‐Visual‐Range Engagement Based on Radar Blind Zone Analysis and Bézier Trajectory Optimization

Zhigang Wang, Huajun Gong, Denghui Zhang, Jingping Shi

Unmanned autonomous air combat, characterized by advantages such as zero casualties, low cost, and high maneuverability, represents the primary direction for future air combat development. The key to achieving victory in beyond‐visual‐range autonomous air combat lies in the drone′s ability to accurately …

cn (code pays fourni par la source)

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models

Hyunin Lee, Yong Zhang, Hoang Vu Nguyen, Xiaoyi Liu et autres

Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance alignment and improve recommendation performance, its underlying mechanism is not fully understood. Most researchers interpret cross-attention as residual alignment, where …

Ensemble weighted DJPMMD based deep transfer metric learning method for fault diagnosis of bearing under variable working conditions

Zengbing Xu, You‐Rong Li, Zhigang Wang

Intelligent fault diagnosis of bearings under variable working conditions remains a challenging task. Although the deep transfer learning model can effectively diagnose the faults of bearing under variable working conditions, the diagnosis accuracy and stability of the individual deep transfer learning model …

cn (code pays fourni par la source)

A Method for Anomaly Traffic Detection in Power Wireless Access Networks Based on an Improved Transformer Model

Mengjie Yang, Di Liu, Jian Xu, Yanru Wang et autres

With the increasing intelligence of power systems, the security of power wireless access networks has become a critical issue. To address the challenges of anomaly traffic detection, this paper proposes an improved Transformer-based detection method. By introducing relative position encoding and dilated …

cn (code pays fourni par la source)

Flink-based Streaming Data Processing for Power Wireless Private Networks

Ming Lu, Zhongping Xu, Yanru Wang, Zhigang Wang et autres

In order to break through the processing bottleneck of massive real-time streaming data in the electric power wireless private network, an innovative scheme integrating Flink distributed stream processing architecture and weathercoupled LSTM prediction is proposed. By constructing a threelayer stream processing framework, …

cn (code pays fourni par la source)

Stack-based Ensemble Learning for Performance Indirect Testing of Analog Integrated Circuits

Jiawei Cao, Houjun Wang, Zhigang Wang, Hao Li

Performance testing of analog integrated circuits (ICs) is essential before deployment and real-world use. The conventional method for testing ICs’ specifications relied on complex test circuits and diverse stimuli with high time and hardware costs. To reduce costs, we propose a two-stage …

cn (code pays fourni par la source)

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

Haipeng Chen, Sifan Wu, Zhigang Wang, Yifang Yin et autres

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models …

cn, sg (code pays fourni par la source)

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

Yingying Jiao, Zhigang Wang, Zhenguang Liu, Shaojing Fan et autres

Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One aspect that has been overlooked so far is …

cn, sg (code pays fourni par la source)

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

Yingying Jiao, Zhigang Wang, Sifan Wu, Shaojing Fan et autres

Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-range temporal dependencies and overlook the complementary relationship between temporal …

cn, sg (code pays fourni par la source)

Optimizing Small-Scale Language Models for Robotic Task Planning: Insights into Prompt Design

Fan Wu, Zhigang Wang, Yikang Li, Qiang En Wu

Large-scale language models (LLMs) have demonstrated significant potential in robotic task planning, however, their resource-intensive nature poses challenges for on-device deployment in resource-constrained environments, such as autonomous robots. In this paper, we explore the feasibility of utilizing Small-Scale Language Models(SSLMs) for robotic …

cn, us (code pays fourni par la source)

Modulating d z 2 -orbital occupancy of Au cocatalysts for enhanced photocatalytic H2O2 production

Xiaofang Li, Zhigang Wang

A NiS-induced electron transfer reversal is developed to optimize the d z 2 -orbital occupancy of active Au atoms for realizing highly selective H 2 O 2 evolution on core-shell NiS@Au cocatalysts.

cn (code pays fourni par la source)