检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chaohao Wen Xun Gong School of Computing and Artificial Intelligence SWJTU Chengdu China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China National Engineering Laboratory of Integrated Transportation Big Data Application Technology SWJTU Chengdu China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province SWJTU Chengdu China

Deep Neural Networks (DNN) have achieved extraordinary success in many visual recognition tasks. Visual Transformer (ViT), which is derived from Natural Language Processing (NLP), has achieved state-of-the-art (SOTA) results on many tasks due to its capability of capturing long-range dependencies in visual data. However, Existing ViT models are challenging to deploy on devices due to their massive computational consumption, huge memory overhead, and reliance on large datasets. In this work, we address these issues by replacing some computationally expensive and memory-intensive modules in ViT with standard Convolutional Neural Network (CNN) modules. Firstly, we propose an efficient Self-Attention module called SDG-Attention (SDGA) with linear space and time complexity, and an economical FeedForward Network (FFN) composed of group convolution and shuffle channel (SFFN). Then, we develop a lightweight CNN model with SDGA and SFFN, SDGFormer, which embraces several priors of ViT and is LayerNorm-Free. We evaluate SDGFormer on ImageNet-1K and Mini-ImageNet, and the SDGFormer-S achieves a comparable top-1 accuracy of 77.6% on ImageNet-1K with 9.1M parameters and 1.6 GFlops regimes. Moreover, our SDGFormer-T achieves SOTA performance on Mini-ImageNet with 83.3% accuracy, demonstrating good generalization on small datasets without extra data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental observation of parity-symmetry-protected phenomena in the quantum Rabi model with a trapped ion

arXiv

引用

arXiv 2025年

作者： Zhao, Xingyu Bin, Qian Hou, Waner Li, Yi Li, Yue Lin, Yiheng Lü, Xin-You Du, Jiangfeng CAS Key Laboratory of Microscale Magnetic Resonance School of Physical Sciences University of Science and Technology of China Hefei230026 China Anhui Province Key Laboratory of Scientific Instrument Development and Application University of Science and Technology of China Hefei230026 China Hefei National Laboratory University of Science and Technology of China Hefei230088 China College of Physics Sichuan University Chengdu610065 China School of Physics Institute for Quantum Science and Engineering Huazhong University of Science and Technology Wuhan Institute of Quantum Technology Wuhan430074 China Institute of Quantum Sensing School of Physics Zhejiang University Hangzhou310027 China

Symmetry is crucial for gaining insights into the fundamental properties of physical systems, bringing possibilities in studying exotic phenomena such as quantum phase transitions and ground state entanglement. Here, we experimentally simulate a highly controllable extended quantum Rabi model, capable of tuning into the ultra-strong or deep coupling regime, in a spin-motion-coupled trapped ion. We observe that the phonon driven by such a model with parity symmetry preserved (broken) would experience double (single) excitation in the ultra-strong coupling regime. Quantum phenomena such as strong ground state entanglement and quantum superposition in systems occur with parity symmetry, and these phenomena disappear following the symmetry breaking. We also find sensitive responses for the two-level system entropy and phonon Wigner function in the deep coupling regime, depending on the parameter across the symmetry transition point. This work offers the prospect of exploring symmetry-controlled quantum phenomena and their applications in high-precision quantum technologies. © 2025, CC BY.

关键词： Phonons

来源：评论

学校读者我要写书评

暂无评论

GDKansformer: A group-wise dynamic Kolmogorov–Arnold transformer with multi-view gated attention for pathological image diagnosis

引用

Expert Systems with applications 2025年 286卷

作者： Lu, Xiaoyan Gong, Xun Chen, Yuanyuan School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology and Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China Department of Pathology The Third People's Hospital of Chengdu Affiliated Hospital of Southwest Jiaotong University Chengdu610031 China

Pathological image diagnosis is a fundamental and critical component of precision medicine, playing a pivotal role in clinical decision-making. However, due to the high heterogeneity of pathological images, existing models still face the challenges of insufficient feature representation, poor interpretability, and high computational costs. To address these issues, we propose a novel pathological image diagnosis model called GDKansformer, which integrates the Group-wise Dynamic Kolmogorov–Arnold Network with a Vision Transformer (ViT) architecture. Specifically, this model employs adaptive dynamic fitting and group-wise computation strategies to seamlessly embed an improved Kolmogorov–Arnold Network (KAN) into ViTs, thereby boosting pathological representation and interpretability. The proposed group-wise computation strategy effectively mitigates the distribution overfitting caused by the KAN structure and significantly reduces the computational costs. Furthermore, a Multi-view Gated Attention (MVGA) block comprising pixel-level non-local neighborhoods and adaptive local perception is designed to eliminate redundant non-feature information and enhance contextual interactions, thereby improving the feature discrimination of the model for high heterogeneity data distributions. Experimental results demonstrate that GDKansformer achieves high accuracy with lower parameters, highlighting the significant potential in facilitating pathological diagnosis. © 2025

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Active Integrated Antenna Based on Minimum Noise Matching

Active Integrated Antenna Based on Minimum Noise Matching

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Jin-Cheng Tang Qiang-Ming Cai Yuan Zhang Xin Cao Longjian Zhou Yuyu Zhu Bo Pu Jun Fan School of Information Engineering Southwest University of Science and Technology Mianyang China Robot Technology Used for Special Environment Key Laboratory of Sichuan Province Mianyang Sichuan China Tianfu Institute of Research and Innovation Southwest University of Science and Technology (SWUST-TIRI) AVIC Chengdu Aircraft Industrial (Group) Co. Led Chengdu China DeTooLIC Technology Co. Ltd Ningbo Zhejiang China

In this paper, in order to discard the impedance matching circuit and reduce the antenna overall size, a directional antenna integrated a low noise amplifier (LNA) with ATF-54143 transistor is designed. Two 50ohm matching networks between the antenna and the LNA can be eliminated, and the insertion loss and the space occupation of RF front-end system have also been reduced. The simulated results show that this directional antenna with input impedance of 23.1-j15.4 ohm rather than 50 ohm at 2.45GHz and has a great radiation performance. The noise figure of the integrated antenna decreases by 0.1 at 2.45GHz, in comparison with the traditional cascade circuit by designing 50ohm matching networks. It provides a useful guiding method for the design of active antennas.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Colorimetric and Fluorometric Dual-Signal Determination of Organics and Baijiu Based on Nanozymes with Peroxidase-Like Activity

SSRN

引用

SSRN 2023年

作者： Qiao, Cailin Wang, Xinrou Gao, Yuwei Li, Jiawei Zhao, Jinsong Luo, Huibo Zhang, Suyi Huo, Danqun Hou, Changjun Key Laboratory for Biorheological Science and Technology of Ministry of Education Bioengineering College of Chongqing University Chongqing400044 China Liquor Making Biology Technology Application of Key Laboratory of Sichuan Province College of Bioengineering Sichuan University of Science and Engineering 188 University Town Yi bin644000 China National Engineering Research Center of Solid-State Brewing Luzhou Laojiao Group Co. Ltd. Luzhou646000 China Sichuan Liquor Group Co. Ltd. Chengdu610000 China

Nanozyme has attracted wide interest in biosensing owing to its excellent advantages. However, nanozymes have been scarcely applied in Baijiu quality inspection. Herein, a colorimetric and fluorometric dual-signal determination mediate by nanozyme-H2O2-TMB system was developed for organics and Baijiu determination. Since the diversity peroxidase-like activity of nanozymes, their ability to catalyze H2O2 to produce ·OH is diversity, resulting in different degrees of oxidized TMB generation. When analytes added to the system, specific changes of RGB (red, green, blue) values and the fluorescence emission peaks around 420 nm were obtained. Based on this, the system was employed to identify 21 organics qualitatively and quantitatively by colorimetric method with a rapid response ( © 2023, The Authors. All rights reserved.

关键词： Ascorbic acid

来源：评论

学校读者我要写书评

暂无评论

A Novel Colorimetric and Fluorometric Dual-Signal Determination of Organics and Baijiu Based on Nanozymes with Peroxidase-Like Activity

SSRN

引用

SSRN 2023年

作者： Hou, Changjun Qiao, Cailin Wang, Xinrou Gao, Yuwei Li, Jiawei Zhao, Jinsong Luo, Huibo Zhang, Suyi Huo, Danqun Key Laboratory for Biorheological Science and Technology of Ministry of Education Bioengineering College of Chongqing University Chongqing400044 China Liquor Making Biology Technology Application of Key Laboratory of Sichuan Province College of Bioengineering Sichuan University of Science and Engineering 188 University Town Yibin644000 China National Engineering Research Center of Solid-State Brewing Luzhou Laojiao Group Co. Ltd. Luzhou646000 China Sichuan Liquor Group Co. Ltd. Chengdu610000 China

Nanozymes are a kind of nanomaterial with intrinsic enzymatic properties, and have the advantages of diverse functions, adjustable catalytic activity, high stability, and easy large-scale production, so they have attracted wide interest in biosensing. However, nanozymes have been scarcely applied in Baijiu quality inspection. Herein, a colorimetric and fluorometric dual-signal determination mediated by nanozyme-H2O2-TMB system was developed for organics and Baijiu. Since the diverse peroxidase-like activity of nanozymes, their ability to catalyze H2O2 to produce ·OH is diverse, resulting in different degrees of oxidized TMB generation. Based on this, 21 organics were identified qualitatively and quantitatively by colorimetric method with a rapid response ( © 2023, The Authors. All rights reserved.

关键词： Catalyst activity

来源：评论

学校读者我要写书评

暂无评论

A Composite 3D-2D Visual Surface Defects Inspection Method for Steel Bar Intelligent Manufacturing 4

A Composite 3D-2D Visual Surface Defects Inspection Method f...

引用

4th Annual International Conference on Data Science and Business Analytics, ICDSBA 2020

作者： Xu, Feng Wang, Jinqiang Liu, Guihua Wang, Kangjia Southwest University of Science and Technology Robot Technology Used for Special Environment Key Laboratory of Sichuan Province Mianyang China Zhejiang University of Technology Hangzhou China

ISBN: (纸本)9781728181646

A composite 3D-2D visual surface defects inspection scheme based on combining active 3D visual inspection with 2D image texture extraction is presented for steel bar intelligent manufacturing. The active 3D visual inspection method is used to detect the surface defects with poor contrast;the 2D image texture extraction method is used to detect the surface defects with tiny width. The variable defects can be identified through fusion of the acquired 3D and 2D information of steel bar. The fundamental derivation of composite 3D-2D visual inspection is given. The experimental results validate and demonstrate the feasibility of the proposed approach. © 2020 IEEE.

关键词： Image texture

来源：评论

学校读者我要写书评

暂无评论

A Novel Colorimetric and Fluorometric Dual-Signal Determination of Organics and Baijiu Based on Nanozymes with Peroxidase-Like Activity

SSRN

引用

SSRN 2023年

作者： Qiao, Cailin Wang, Xinrou Gao, Yuwei Li, Jiawei Zhao, Jinsong Luo, Huibo Zhang, Suyi Huo, Danqun Hou, Changjun Key Laboratory for Biorheological Science and Technology of Ministry of Education Bioengineering College of Chongqing University Chongqing400044 China Liquor Making Biology Technology and Application of Key Laboratory of Sichuan Province College of Bioengineering Sichuan University of Science and Engineering 188 University Town Yibin644000 China National Engineering Research Center of Solid-State Brewing Luzhou Laojiao Group Co. Ltd. Luzhou646000 China Sichuan Liquor Group Co. Ltd. Chengdu610000 China

Nanozyme has attracted wide interest in biosensing owing to its excellent advantages. However, nanozymes have been scarcely applied in Baijiu quality inspection. Herein, a colorimetric and fluorometric dual-signal determination mediated by nanozyme-H2O2-TMB system was developed for organics and Baijiu determination. Since the diverse peroxidase-like activity of nanozymes, their ability to catalyze H2O2 to produce ·OH is diverse, resulting in different degrees of oxidized TMB generation. When analytes were added to the system, specific changes in RGB (red, green, blue) values and the fluorescence emission peaks around 420 nm were obtained. Based on this, the system was employed to identify 21 organics qualitatively and quantitatively by colorimetric method with a rapid response ( © 2023, The Authors. All rights reserved.

关键词： Ascorbic acid

来源：评论

学校读者我要写书评

暂无评论

Intra-Person Camera Adversarial for Intra-Camera Supervised Person Re-Identification

Intra-Person Camera Adversarial for Intra-Camera Supervised ...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Ruochen Tang Xun Gong School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu China

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Re-identification (ReID) of individuals across different cameras is a challenging task due to the high-quality large-scale datasets required for the model. Intra-camera supervised (ICS) person re-identification has been proposed to address the high cost of annotating large-scale datasets, but reducing the gap between camera domains remains a major challenge. Current approaches use intra- and inter-camera learning with contrastive learning performed separately in both phases. However, the effect of features from the same person under different cameras on the model during inter-camera learning, and the fine-grained characteristic where the same person can be classified into multiple classes based on the camera labels, still require further research. To address this issue, we propose a Camera-Based Contrastive Learning (CBCL) method that moves features away from their respective cameras and closer to other cameras to reduce domain gaps. We also introduce an Intra-Person Camera Adversarial (IPCA) loss that effectively utilizes fine-grained characteristics of person re-identification and improve IPCA by introducing camera labels to obtain IPCA_2 which achieves better model recognition performance than IPCA alone. Extensive experiments on multiple datasets demonstrate that our method outperforms existing methods and is comparable to fully-supervised methods.

关键词： Costs Scalability Face recognition Contrastive learning Gesture recognition Cameras Robustness

来源：评论

学校读者我要写书评

暂无评论

Symplectic Wigner Distribution in the Linear Canonical Transform Domain: Theory and application

arXiv

引用

arXiv 2025年

作者： He, Yangfan Zhang, Zhichao School of Communication and Artificial Intelligence School of Integrated Circuits Nanjing Institute of Technology Nanjing211167 China School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing210044 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Computational Science Application of Hainan Province Hainan Normal University Haikou571158 China Key Laboratory of Numerical Simulation of Sichuan Provincial Universities School of Mathematics and Information Sciences Neijiang Normal University Neijiang641000 China

This paper devotes to combine the chirp basis function transformation and symplectic coordinates transformation to yield a novel Wigner distribution (WD) associated with the linear canonical transform (LCT), named as the symplectic WD in the LCT domain (SWDL). It incorporates the merits of the symplectic WD (SWD) and the WD in the LCT domain (WDL), achieving stronger capability in the linear frequency-modulated (LFM) signal frequency rate feature extraction while maintaining the same level of computational complexity. Some essential properties of the SWDL are derived, including marginal distributions, energy conservations, unique reconstruction, Moyal formula, complex conjugate symmetry, time reversal symmetry, scaling property, time translation property, frequency modulation property, and time translation and frequency modulation property. Heisenberg’s uncertainty principles of the SWDL are formulated, giving rise to three kinds of lower bounds attainable respectively by Gaussian enveloped complex exponential signal, Gaussian signal and Gaussian enveloped chirp signal. The optimal symplectic matrices corresponding to the highest time-frequency resolution are generated by solving the lower bound optimization (minimization) problem. The time-frequency resolution of the SWDL is compared with those of the SWD and WDL to demonstrate its superiority in LFM signals time-frequency energy concentration. A synthesis example is also carried out to verify the feasibility and reliability of the theoretical analysis. Copyright © 2025, The Authors. All rights reserved.

关键词： Wigner-Ville distribution

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：