检索结果-内蒙古大学图书馆

Multi-scale feature fusion for facial expression recognition

Neural Computing and Applications 2025年 1-22页

作者： Guo, Jiatao Peng, Junjie Huang, Yansong Chen, Gan Cai, Zesu Tan, Shuhua School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China School of Computer Science and Technology Harbin Institute of Technology Harbin China National Engineering Laboratory for Logistics Information Technology YTO Express Co. Ltd. Shanghai China

As an important computer vision task that can be used in many areas, facial expression recognition (FER) has been widely studied which much progress has been obtained especially when deep learning (DL) approaches have been introduced in FER. However, existing methods are restricted to extracting localized information or utilizing attention mechanism to focus on the region most relevant to the emotion, possibly resulting in errors in facial expression interpretation. Moreover, the inconsistency of image sizes in the wild FER datasets further increases the difficulty of the FER task. To address these issues, we propose a multi-scale feature fusion (MSFF) for FER. Specifically, our method first extracts features from facial images using multi-scale feature extraction to obtain rich multi-dimensional information. Meanwhile, extensive feature extraction at different scales is achieved by expanding the receptive field of the model, which provides the basis for more detailed analysis of facial expressions. Eventually, features at different scales are fused to enhance their synergistic effect. Subsequently, the adaptive extraction of comprehensive and valuable information from the fused features is performed, optimizing the performance of expression recognition. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on in-the-wild datasets. It is promising for FER in realistic and complex scenarios. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Transformation of Normalization Standard of Smith Chart for Microwave Networks With Multiple Impedance Transmission Lines

引用

IEEE Microwave and Wireless Technology Letters 2025年第4期35卷 384-387页

作者： Yi, Zixuan Hu, Peipei Yang, Xue-Xia Li, Meiling Zeng, Dan Shanghai Institute for Advanced Communication and Data Science Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai University Shanghai200444 China

The Smith chart is a graphical approach for solving impedance matching problems in the microwave circuit design, which provides visualized traces, but it is not applicable to address impedance discontinuities graphically, especially for multiple-impedance transmission lines (TLs) within microwave networks. In this letter, a novel transformation of normalization standard (TNS) method is proposed, which is applied to the Smith chart to solve the aforementioned problem. Then, TNS traces are derived and applied to the classical Smith chart, obtaining an improved Smith chart. In addition, the TNS idea is applied to the microwave circuit design examples. The proposed TNS method provides a convenient visualized way for the design of microwave circuits with multi-impedance TLs. © 2023 IEEE.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Fabrication-Tolerant High-Speed 5-Bit Silicon Optical True Time Delay Line in the O-Band

引用

Journal of Lightwave Technology 2025年第9期43卷 4358-4366页

作者： Ni, Ziheng Lu, Liangjun Wang, Yixuan Liu, Yuanbin Chen, Jianping Zhou, Linjie Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Institute for Advanced Communication and Data Science Department of Electronic Engineering Shanghai Key Lab of Navigation and Location Services Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China

Fast reconfiguration time on the order of nanoseconds is crucial for microwave photonic beamformers, particularly in 5G/6G wireless communication systems. Most previously reported integrated optical true time delay lines (OTTDLs) exhibit a slow response time of tens of microseconds. In this study, we demonstrate an O-band high-speed 5-bit silicon OTTDL based on fabrication-tolerant electro-optic push-pull optical switches, which exhibit lower phase deviation and reduced insertion loss compared to conventional designs. The rising and falling times are 9 ns and 11 ns for the electro-optic switching, respectively. The insertion loss and crosstalk of our fabrication-tolerant high-speed switch element are 0.66 dB (0.74 dB) and −25.09 dB (−27.41 dB) at the bar (cross) state, respectively, at the wavelength of 1310 nm. For the 5-bit OTTDL, the initial phase variation is only ∼0.10π, which is one-sixth of that observed in the conventional design. Additionally, our proposed OTTDL features a low fiber-to-fiber insertion loss of 8.72 dB and a delay tuning range of 0-313.9 ps. The high-performance, fabrication-tolerant OTTDLs hold significant promise for future applications in fast beamforming. © 1983-2012 IEEE.

关键词： Fiber to the x

来源：评论

学校读者我要写书评

暂无评论

Accelerating the Thermal Response of a III-V/Si3N4 Hybrid External Cavity Laser with Electronic-Photonic Co-Design

引用

Journal of Lightwave Technology 2025年第10期43卷 4871-4880页

作者： Han, Keyi Lu, Liangjun Guo, Yuyao Li, Xinhang Xu, Weihan Chen, Jianpin Zhou, Linjie Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks The Shanghai Institute for Advanced Communication and Data Science Shanghai Key Lab of Navigation and Location Services Department of Electronic Engineering Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China

We propose an electronic-photonic (EP) co-designed scheme to enhance the modulation speed of thermo-optic (TO) phase shifters. We establish a small signal analysis model to optimize the TO phase shifter by compensating its thermal-response-limited low-pass behavior with an electric high-pass equalization circuit, thus expanding the modulation bandwidth. To prove its potential, we demonstrate an EP-converged frequency-modulated continuous-wave (FMCW) laser comprising an InP/Si3N4 hybrid integrated external cavity laser (ECL) driving with an electric equalization circuit. The small signal bandwidth of the TO phase shifter inside the laser cavity is enhanced from 10 kHz to 360 kHz with the equalization circuit. By driving the TO phase shifter, we generate an FMCW signal with a chirp bandwidth of 943 MHz at a repetition rate of 100 kHz. The residual nonlinearity of the frequency chirp is reduced to 0.72% thanks to the pre-distortion technique, enabling a ranging precision of 8.1 cm over a 20 m distance. © 2025 IEEE.

关键词： Pulse repetition rate

来源：评论

学校读者我要写书评

暂无评论

Recticoil for Efficient Compact Inductive Power Transfer

引用

IEEE Transactions on Power Electronics 2025年第7期40卷 10154-10164页

作者： Yi, Zixuan Qin, Yuanyuan Yang, Xue-Xia Shao, Yaoxia Zeng, Dan Li, Meiling Shanghai University School of Communication and Information Engineering Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science Shanghai200444 China Hangzhou City University School of Information and Electrical Engineering Hangzhou310015 China

The MHz inductive power transfer (IPT) system has broad application prospects due to its high safety, longer transmission distance, and better tolerance for misalignment. However, the increase in frequency will lead to an increased loss of lumped components, such as inductors and capacitors, in peripheral circuits, thereby reducing efficiency. This is currently the bottleneck problem encountered by MHz IPT. To address this key challenge, researchers have tried to remove the lumped components in the peripheral circuit while ensuring the functions of the IPT system. One successful and beneficial attempt is the self-resonant coil, which replaces traditional lumped resonant capacitors with distributed capacitors formed by coil turn-to-turn capacitance, ensuring compensation for leakage inductance and eliminating reactive power. This innovative integration makes efficiency and integration greatly improved. In this article, the novel coil named Recticoil, on which the rectification function is integrated further, is proposed for efficient compact IPT. Recticoil can directly output dc power without additional compensation and rectification circuits. By analyzing a toroidal coil where two separate conductors generate a voltage differential, and incorporating two diodes, resulting in a dc output. Subsequently, the self-resonant coil replaces the toroidal coil to form Recticoil, and the equivalent circuits of Recticoil are given and analyzed. In addition, the analysis and test method of rectification efficiency is given. The experimental results show that the Recticoil achieves a rectification efficiency as high as 97.25% at 6.78 MHz, outperforming both the bridge rectifier and the Class E rectifier. Additionally, the compact construction of Recticoil eliminates the volume of traditional rectifiers. All of these advantages of Recticoil render it a promising candidate for applications in wearables and miniaturized devices. © 1986-2012 IEEE.

关键词： Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

Explore Statistical Properties of Undirected Unweighted Networks from Ensemble Models 27th

Explore Statistical Properties of Undirected Unweighted Netw...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Xunda Wu, Xing Wang, Jianjia School of Computer Engineering and Science Shanghai University Shanghai China Engineering and Science Shanghai Institute for Advanced Communication and Data Science School of Computer Shanghai University Shanghai China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou China

ISBN: (纸本)9783031783975

Complex network theory has been widely demonstrated as a powerful tool in modeling and characterizing various complex systems. In the past, complex network theory has focused on the behaviors as well as the characteristics of the network nodes and edges. However, with the continuous evolution of society, traditional graph theory faces challenges due to the emergence of extermely large network structures. Recently, complex network method based statistics has attracted much attention. The new approach effectively manages very large networks and uncovers their intrinsic properties. In this paper, we present a complex network analysis model for undirected, unweighted networks based on a statistical analysis approach. This model is inspired by the ensemble model in thermostatistical physics. Based on the established mathematical model, we derive physical measures that reflect the intrinsic properties of the network, including Entropy, Free Energy, Temperature, and so on. In the experimental part, we first explored the mathematical characterization of these metrics. Then, we observed the performance of various network categories under the same metric. Finally, we applied these measures to the field of graph classification. Extensive experiments demonstrate the effectiveness and superiority of the proposed method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

RGB-D Rail Surface Defect Inspection Driven by Conditional Diffusion Architecture and Frequency Knowledge

引用

IEEE Sensors Journal 2025年第10期25卷 18334-18343页

作者： He, Zhihao Li, Gongyang Liu, Zhi Shanghai University School of Communication and Information Engineering Shanghai200444 China Anhui Province Key Laboratory of Machine Vision Detection and Perception Wuhu241000 China Wenzhou Institute of Shanghai University Wenzhou325000 China Shanghai University Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai200444 China

RGB-D Rail Surface Defect Inspection (RSDI) is a critical measure for ensuring transportation safety. It improves inspection accuracy by using depth maps, but the issue of poor-quality depth maps in rail defect datasets is often overlooked. Additionally, the similarity between the foreground and background has always been a persistent challenge in RGB-D RSDI. In this article, we propose a novel network, termed DiffRSDI to overcome these challenges in RGB-D RSDI, which treats RGB-D RSDI as a mask generation task using a conditional diffusion architecture. Specifically, DiffRSDI consists of two key components: Cross-modal Cyclic Enhancement (CCE) module and Frequency-aware Alternate Fusion (FAF) module. CCE module is based on the cyclic enhancement approach, and aims to eliminate interference from poor-quality depth maps and aggregate cross-modal features. FAF module overcomes the similarity between the foreground and background in the frequency-domain, and achieves cross-scale fusion in the fused features. Comprehensive experiments conducted on the NEU RSDDS-AUG dataset confirm that our method achieves superior performance in comparison to 14 related methods. The DiffRSDI code and results are available at https://***/zeroyi37/DiffRSDI. © 2001-2012 IEEE.

关键词： Railroad accidents

来源：评论

学校读者我要写书评

暂无评论

Quantifying Racial Segregation Through Continuous-Time Quantum Walks 27th

Quantifying Racial Segregation Through Continuous-Time Quant...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Jiang, Yutong Wu, Xing Wang, Jianjia School of Computer Engineering and Science Shanghai University Shanghai China Engineering and Science Shanghai Institute for Advanced Communication and Data Science School of Computer Shanghai University Shanghai China Xi’an Jiaotong-Liverpool University Suzhou215123 China

ISBN: (纸本)9783031781919

With the development of cities, racial segregation is one of the reasons for social inequality on a large scale, it is also a major factor affecting economic development. However, racial segregation has received comparatively limited attention in research. In the paper, we propose a segregation index independent of any parameters( titled Quantum Walk Convergence Time), which calculates the convergence time statistics for accessing different racial categories through quantum walks on complex networks constructed from urban systems. The magnitude of the time statistics represents the degree of racial segregation. The results generated by our method can also be applied to other social factors, including family situation, income level, and education level. We evaluate our method using large-scale real datasets, including statistics from the U.S. Census Bureau and the Office for National Statistics in the UK. The results demonstrate the close correlation between our method and the degree of racial segregation, showing advantages over traditional random walk methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Chirp-free hundred-picosecond pulse fiber laser based on carbon nanotubes mode-locker

引用

Optics Express 2025年第7期33卷 14850-14857页

作者： Li, Weixi Jiang, Kailin Dai, Lilong Huang, Qianqian Zou, Meng Luo, Siyu Chen, Siyu Song, Yingxiong Liu, Yunqi Yan, Zhijun Mou, Chengbo Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute for Advanced Communication and Data Science Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai University Shanghai200444 China School of Optical and Electronic Information National Engineering Laboratory for Next Generation Internet Access System Huazhong University of Science and Technology Wuhan430074 China

We demonstrate a narrow bandwidth passively erbium-doped mode-locked fiber laser based on single-wall carbon nanotubes (SWCNTs). The center wavelength is 1546.61 nm. The strong filtering effect and low saturable absorber (SA) modulation depth provide advantages for a long pulse duration of 323 ps. An overall spectral bandwidth of 1.3 GHz (0.01 nm) is measured by the optical heterodyne method, representing the narrowest spectral width based on SWCNT under a single filter structure. The obtained spectral width is very close to the transform-limited bandwidth of 8 pm, indicating that the pulse is chirp-free. Meanwhile, the generation of beat signals reveals the strong coherence between pulses. The repetition frequency of the laser is 7.8 MHz, and the number of longitudinal mode locks is only 166, which is the minimum number of longitudinal mode-locking in passively mode-locked laser based on material SA. At the same time, numerical simulations further support our experimental results and reveal the pulse evolution, providing evidence that SA and filter are the key factors in the generation of chirp-free long pulse. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Saturable absorbers

来源：评论

学校读者我要写书评

暂无评论

Dispersive wave control in soliton fiber lasers via online high-order dispersion engineering

引用

Optics Letters 2025年第8期50卷 2788-2791页

作者： Sun, Suwan Zha, Zimin Bai, Jiamin Shi, Zhiming Chu, Yongyuan Li, Zilong Huang, Qianqian Mou, Chengbo Guo, Hairun Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China School of Engineering and Materials Science Queen Mary University of London Mile end Bethnal Green LondonE1 4NS United Kingdom

Ultrafast fiber lasers generating temporal solitary pulses have found important applications in numerous fields. Circulating within the laser cavity, such solitons would feature dispersive wave generation due to the perturbation of cavity parameters. While Kelly sidebands have been widely recognized as dispersive waves in fiber lasers due to an intrinsic periodic loss perturbation, optical Cherenkov radiation-an alternative dispersive wave regime that is enabled by highorder dispersion-has been less explored. In this Letter, we demonstrate a broad control of dispersive waves in an ultrafast fiber laser via online dispersion engineering, which enables precise tuning of both the Cherenkov radiation and Kelly sidebands and enables a transition in between via manipulation of third- and fourth-order dispersion (TOD and FOD). Furthermore, we identify a retrieval method for tracing cavity high-order dispersion from frequencies of dispersive waves, which has been traditionally challenging. Our findings would not only help gain in-depth understanding of cavity soliton dynamics but may also contribute to advanced design of ultrafast lasers. © 2025 Optica Publishing Group.

关键词： Dispersion (waves)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：