检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Yang Liu, Mengyuan Huang, Shudong Lv, Jiancheng College of Computer Science Sichuan University Chengdu610065 China Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education Chengdu China State Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School Shenzhen China

learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain textual information from multiple different views, which makes it difficult to compute the similarity between these two modalities accurately and efficiently. In this paper, we propose a novel framework called Asymmetric Visual Semantic Embedding (AVSE) to dynamically select features from various regions of images tailored to different textual inputs for similarity calculation. To capture information from different views in the image, we design a radial bias sampling module to sample image patches and obtain image features from various views, Furthermore, AVSE introduces a novel module for efficient computation of visual semantic similarity between asymmetric image and text embeddings. Central to this module is the presumption of foundational semantic units within the embeddings, denoted as "meta-semantic embeddings." It segments all embeddings into meta-semantic embeddings with the same dimension and calculates visual semantic similarity by finding the optimal match of meta-semantic embeddings of two modalities. Our proposed AVSE model is extensively evaluated on the large-scale MS-COCO and Flickr30K datasets, demonstrating its superiority over recent state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Practical Evaluation of Presodiation Techniques for High Energy Sodium-Based Batteries

引用

ACS Nano 2025年 2025 May 1页

作者： Lin, Kui Liu, Ming Qin, Xianying Zheng, Guorui Liang, Junwei Li, Baohua Jiang, Chunhai Fujian Provincial Key Laboratory of Functional Materials and Applications Institute of Advanced Energy Materials School of Materials Science and Engineering Xiamen University of Technology Xiamen 361024 China Shenzhen Key Laboratory on Power Battery Safety Research and Shenzhen Geim Graphene Center Tsinghua Shenzhen International Graduate School Shenzhen 518055 China Shenzhen Graphene Innovation Center Co. Ltd. Shenzhen 518055 China

Low-cost rechargeable sodium-based batteries are regarded as ideal alternatives to replace or complement current lithium-ion batteries in large-scale energy storage applications. Unfortunately, the commercial implementation of sodium-based batteries is restricted by their unsatisfied energy density, severe initial capacity decay, and discontented cycle life. Presodiation techniques including anode pretreatment and cathode additives are widely suggested to alleviate the above problems by providing an extra sodium resource to compensate for the initial capacity loss. However, none of them have been applied at the industrial level due to poor kinetics and severe gas evolution. Hence, in this timely review, we reclassify the presodiation techniques based on their operating locations and charge compensation mechanisms, which could provide intuitive perspectives for practical assessment. key evaluation factors including kinetic performance, gas evolution behavior, environmental stability, and cost are proposed and systematically analyzed. The corresponding optimization strategies and potential applications are provided, followed by the scientific and technical challenges and suggestions for future industrialization. We believe this review will promote the industrial development of presodiation techniques in the future. © 2025 American Chemical Society.

关键词： cost environmental stability gas evolution high energy density initial capacity decay kinetics practical evaluation presodiation sodium batteries

来源：评论

学校读者我要写书评

暂无评论

Multiscale Convolutional Transformer with Diverse-aware Feature learning for Motor Imagery EEG Decoding

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hang, Wenlong Wang, Junliang Liang, Shuang Lei, Baiying Wang, Qiong Li, Guanglin Chen, Badong Qin, Jing Nanjing Tech University College of Computer Nanjing211816 China Nanjing Tech University Information Engineering Nanjing211816 China Nanjing University of Posts and Telecommunications School of Internet of Things Nanjing210023 China Shenzhen University School of Biomedical Engineering Shenzhen518060 China Guangdong Provincial Key Laboratory of Computer Vision Shenzhen518055 China Virtual Reality Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Shenzhen Institute of Advanced Technology Shenzhen518055 China Chinese Academy of Sciences Shenzhen518055 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China Hong Kong Polytechnic University School of Nursing Hung Hom Hong Kong

Electroencephalogram (EEG)-based motor imagery (MI) brain-computer interfaces (BCIs) have significant potential in improving motor function for neurorehabilitation. Despite recent advancements, learning diversified EEG features across different frequency ranges remains a significant challenge, as the homogenization of feature representations often limits the generalization capabilities of EEG decoding models for BCIs. In this paper, we propose a novel multiscale convolutional transformer framework for EEG decoding that integrates multiscale convolution, transformer, and diverse-aware feature learning scheme (MCTD) to tackle the above challenge. Specifically, we first capture multiple frequency features using dynamic one-dimensional temporal convolution with different kernel lengths. Subsequently, we incorporate convolutional layers and transformers with a contrastive learning scheme to extract discriminative local and global EEG features within a single frequency range. To mitigate the homogenization of features extracted from different frequency ranges, we propose a novel decorrelation regularization. It enables multiscale convolutional transformers produce less correlated features with each other, thereby enhancing the overall expressiveness of EEG decoding model. The performance of MCTD is evaluated on four public MI-based EEG datasets, including the BCI competition III 3a and IV 2a, the BNCI 2015- 001, and the OpenBMI. For the average Kappa/Accuracy scores, MCTD obtains improvements of 3.58%/2.68%, 3.09%/2.20%, 2.33%/1.54%, and 4.44%/2.22%, over the state-of-the-art method on four EEG datasets, respectively. Experimental results demonstrate that our method exhibits superior performance. © 2016 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

DAT: Dual-branch Adapter-Tuning for Few-shot Recognition

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Junxi Wu, Guangxing Li, Hongxiang Chen, Jiankang Zhang, Wentao Zheng, Weishi Wang, Ruixuan Sun Yat-sen Univerisity College of Computer Science and Engineering Guangzhou510275 China Peking University School of Electronic and Computer Engineering Shenzhen518055 China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou510275 China Sun Yat-sen Univerisity School of Computer Science and Engineering Guangzhou510275 China Peng Cheng Laboratory Shenzhen518066 China

Parameter-Efficient Fine-Tuning methods based on vision-language models (such as CLIP) for few-shot learning have recently received considerable attention. However, previous works only fine-tune either the image or text branch, breaking the alignment of the original two branches, meanwhile fine-tuning both branches of the CLIP would inevitably introduce more trainable parameters and likely cause more severe over-fitting due to the limited training data. In this study, we propose a novel Dual-branch Adapter-Tuning framework (DAT), which collaboratively trains the visual adapter and textual adapter added to the two branches of the original CLIP with multiple consistency constraints. By effectively utilizing the semantically detailed class-specific prompts and outputs of the original CLIP to guide the fine-tuning of both branches, our method gains exceptional adaptation ability to the downstream few-shot learning tasks and alleviates the over-fitting issue, meanwhile maximally preserving the generalization ability of the original CLIP model. Our proposed framework has achieved superior performance on diverse datasets under various few-shot learning settings compared to the existing approaches. The source code is available at https://***/SandyXi/DAT. © 1991-2012 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

A novel energy functional minimization model for speckle noise removal

引用

Optoelectronics Letters 2019年第5期15卷 386-390页

作者： CHEN Bo ZOU Jin-bin CHEN Wen-sheng ZHANG Meng-yun Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and Statistics Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

In this paper, a novel energy functional minimization model is proposed for ultrasound images denoising. A controllable regularized term and the variational method are employed in the process of speckle noise. This model not only improves the plasticity of the model, but also improves the effect and efficiency of noise removal. The new model has different diffusion performance in different regions. At the same time, the diffusion performance is related to the parameters introduced by the proposed model. Numerical simulation results show that different parameters have different denoising effects, and the proposed model for speckle noise removal is superior to traditional models.

关键词： functional minimization model speckle noise removal ultrasound images denoising

来源：评论

学校读者我要写书评

暂无评论

Contextual-aware terrain segmentation network for navigable areas with triple aggregation

引用

Expert Systems with applications 2025年 287卷

作者： Wei Li Muxin Liao Wenbin Zou Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University 518060 Guangdong shenzhen China College of Electronics and Information Engineering Shenzhen University 518060 Guangdong shenzhen China School of Computer Science and Engineering Jiangxi Agricultural University 330045 Jiangxi Nanchang China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University 518060 Guangdong shenzhen China

Robust terrain feature representation is beneficial for accurately identifying navigable areas in autonomous vehicle systems, especially in complex and unstructured wild terrain environments. However, existing methods struggle to achieve stable and precise feature representation due to their inability to capture sufficient terrain features. To address these issues, we propose the Contextual-Aware Terrain Segmentation Network (CTSNet) with triple aggregation to effectively capture terrain features for safe navigable area segmentation. CTSNet comprises three essential modules: the Global Channel Sparsification Module (GCSM), the Fusion-wise Calibration Module (FCM), and the Attention Channel Entropy Module (ACEM). First, GCSM selectively globalizes channels through Top-K sparsification, enabling the aggregation of rich global contextual cues that guide feature fusion. Second, FCM refines multi-scale feature aggregation by addressing inconsistent feature representations across scales. It explores the spatial-semantic relationships between features of different sizes and enhances feature interaction via channel-wise calibration, ensuring more coherent integration of both fine-grained and global information. Finally, ACEM aggregates meaningful channel features through normalization and information entropy, ensuring that only the most relevant features contribute to the final segmentation output. Through triple aggregation in global semantic, multi-scale feature, and channel entropy, CTSNet obtains satisfactory and contextual-aware terrain features. Extensive experiments on multiple wild terrain datasets demonstrate that CTSNet outperforms state-of-the-art methods in identifying navigable areas. The code will be available at https://***/lv881314/CTSNet .

关键词：

来源：评论

学校读者我要写书评

暂无评论

ON LOCAL CONTROLLABILITY FOR COMPRESSIBLE NAVIER-STOKES EQUATIONS WITH DENSITY DEPENDENT VISCOSITIES

引用

Acta Mathematica Scientia 2023年第2期43卷 675-685页

作者：连祥凯陶强姚正安 College of Mathematics Sun Yat-sen UniversityGuangzhou 510275China College of Mathematics and Statistics Shenzhen UniversityShenzhen 518060China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen UniversityShenzhen 518060China

In this paper,we study the controllability of compressible Navier-Stokes equations with density dependent *** when the shear viscosityμis a positive constant and the bulk viscosityλis a function of the density,it is proven that the system is exactly locally controllable to a constant target trajectory by using boundary control functions.

关键词： compressible Navier-Stokes equations controllability density dependent vis-cosities

来源：评论

学校读者我要写书评

暂无评论

Reaction Kinetics Regulation Suppressed Carrier Recombination Loss for High-Efficient Solution-Based Antimony Selenosulfide Photovoltaic Devices

引用

advanced Energy Materials 2025年

作者： Fu, Boyang Xiong, Jun Jv, Tianhua Chen, Shuo Liang, Tianquan Ma, Hongli Zhang, Xianghua Pan, Daocheng Zou, Bingsuo Liang, Guangxing Ren, Donglou State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures MOE Key Laboratory of New Processing Technology for Nonferrous Metals and Materials and School of Resources Environment and Materials Guangxi University Nanning 530004 China Institute of Thin Film Physics and Applications Shenzhen Key Laboratory of Advanced Thin Films and Applications Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province State Key Laboratory of Radio Frequency Heterogeneous Integration College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen 518060 China ISCR (Institut des Sciences Chimiques de Rennes)-CNRS UMR 6226 Univ. Rennes Rennes F-35000 France

Carrier recombination loss within the emerging antimony selenosulfide (Sb2(S,Se)3) photovoltaic devices is a critical factor limiting the photovoltaic performance. Herein, a reaction kinetics regulation strategy is re... 详细信息

Carrier recombination loss within the emerging antimony selenosulfide (Sb₂(S,Se)₃) photovoltaic devices is a critical factor limiting the photovoltaic performance. Herein, a reaction kinetics regulation strategy is reported to simultaneously passivate deep-level intrinsic defect and inhibit the oxide impurities in Sb₂(S,Se)₃ absorber with the help of sodium borohydride (SB). The SB, on one hand due to the alkaline feature, can significantly promote the decomposition of selenourea and Sb₂Se₃ formation, eliminating the deep-level Sb_S1 defects and reducing the V_S defects, and on the other hand, owing to the reducing property, can restore SbO⁺ ions to Sb³⁺, thus inhibiting the Sb₂O₃ formation and improving heterogeneous nucleation with preferable [hk1] orientation. These collective influences have remarkably suppressed carrier recombination loss and strengthened carrier collection with optimal band alignment. Consequently, high-efficient Sb₂(S,Se)₃ photovoltaic devices with an efficiency of 10.62% (0.0684 cm²) are gained, which is comparable to the latest-recorded value of 10.7% (0.0389 cm²). This work provides a feasible reaction kinetics regulation method for suppressing carrier recombination loss of Sb-based chalcogenide materials and supplies precious instruction for preparing high-performance optoelectronic devices. © 2025 Wiley-VCH GmbH.

关键词： alkaline reducing agent deep-level defects oxide impurities reaction kinetics solar cells

来源：评论

学校读者我要写书评

暂无评论

Optical and electrical properties of InGaZnON thin films

引用

Chinese Physics B 2020年第1期29卷 475-481页

作者： Jian Ke Yao Fan Ye Ping Fan Shenzhen Key Laboratory of Advanced Thin Films and Applications College of Physics and EnergyShenzhen UniversityShenzhen 518060China

The substrate temperature(Ts)and N2 partial pressure(PN2)dependent optical and electrical properties of sputtered InGaZnON thin films are *** the increased Ts and PN2,the thin film becomes more crystallized and *** Hall mobility,free carrier concentration(Ne),and electrical conductivity increase with the lowered interfacial potential barrier during crystal *** photoluminescence(PL)intensity decreases with the increased *** band gap(Eg)narrows and the linear refractive index(n1)increases with the increasing concentration of N in the thin *** Stokes shift between the PL peak and absorption edge decreases with *** n1,dispersion energy,average oscillator wavelength,and oscillator length strength all increase with *** single oscillator energy decreases with *** nonlinear refractive index and third order optical susceptibility increase with *** Seebeck coefficient,electron effective mass,mean free path,scattering time,and plasma energy are all Ne dependent.

关键词： InGaZnON thin films linear and nonlinear optical properties Seebeck coefficient electron effective mass

来源：评论

学校读者我要写书评

暂无评论

A prediction approach based on long short-term memory networks for dynamic multiobjective optimization

引用

Expert Systems with applications 2025年 283卷

作者： Xu, Biao Rang, Gejie Xie, Ruijie Li, Wenji Gong, Dunwei Fan, Zhun Yang, Shengxiang He, Jie College of Engineering Shantou University Shantou515063 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou543002 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266100 China Shenzhen institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518110 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Dynamic multiobjective optimization problems (DMOPs) present significant challenges to conventional evolutionary optimization methods because of the continuous changes in their Pareto-optimal sets (PSs) and fronts (PFs). Prediction-driven approaches have demonstrated potential in rapidly adapting to these changes. However, many existing methods depend on linear models to forecast the evolving PSs, which may be restrictive. To counteract this limitation, this research presents a novel dynamic multiobjective evolutionary optimization algorithm that incorporates predictions from long short-term memory (LSTM) networks. Initially, in our methodology, the PS for each problem is segmented into multiple clusters, and the centroid of each cluster is identified. These cluster centroids, representing the PSs across various environmental conditions, are then transformed into a series of time series data. The LSTM network models are subsequently trained on this time series data as input samples. Utilizing these refined models, the centroids of the evolving PSs are predicted with improved precision. Moreover, to enhance the performance of the algorithm, an innovative population-generation strategy is also introduced that guarantees a well-converged and diverse starting population. Our proposed algorithm undergoes rigorous testing using benchmark functions, and the outcomes validate its proficiency in tackling DMOPs, showing superior performance compared to existing state-of-the-art algorithms. © 2025 Elsevier Ltd

关键词： Multiobjective optimization

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：