检索结果-内蒙古大学图书馆

Multi-domain feature-enhanced attribute updater for generalized zero-shot learning

Neural Computing and Applications 2025年第14期37卷 8397-8414页

作者： Shi, Yuyan Jiang, Chenyi Song, Feifan Ye, Qiaolin Long, Yang Zhang, Haofeng School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China School of Information Science and Technology Nanjing Forestry University Jiangsu Nanjing210037 China Department of Computer Science Durham University DurhamDH1 3LE United Kingdom

The goal of generalized zero-shot learning (GZSL) is to transfer knowledge from seen classes to unseen classes. However, a significant challenge is the single-category attributes are often inadequate to capture the intra-class variability of diverse image samples. During training, the model tends to cluster samples of seen categories based solely on semantic descriptions, overlooking subtle yet important visual differences. To address these challenges, this paper introduces an instance-level attribute updating method, termed as multi-domain feature-enhanced attribute updater (MDAU), which establishes a one-to-one alignment between visual and semantic by obtaining multiple instance-level attributes that closely correspond to the natural intra-class distribution of the image, in contrast to the many-to-one alignment typically used in traditional GZSL approaches. Specifically, we initially compute feature weights for each individual image, and then, the visual information is incorporated as conditions to facilitate the personalized updating of class attributes. We evaluate our model on three benchmark datasets, the results show that our model can achieve the state-of-the-art performance and detailed analysis also illustrates the effectiveness of each proposed module. Code is available at https://***/S-Silvia/MDAU. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Strain-tuned electronic and valley-related properties in Janus monolayers of SWSiX_(2)(X=N,P,As)

引用

Chinese Physics B 2024年第9期33卷 487-492页

作者： Yunxi Qi Jun Zhao Hui Zeng New Energy Technology Engineering Laboratory of Jiangsu Province&School of Science Nanjing University of Posts and TelecommunicationsNanjing 210023China School of Microelectronics Nanjing University of Science and TechnologyNanjing 210094China

Exploring novel two-dimensional(2D)valleytronic materials has an essential impact on the design of spintronic and valleytronic *** first principles calculation results reveal that the Janus SWSiX_(2)(X=N,P,As)monolayer has excellent dynamical and thermal *** to strong spin–orbit coupling(SOC),the SWSiX_(2)monolayer exhibits a valence band spin splitting of up to 0.49 eV,making it promising 2D semiconductor for valleytronic *** opposite Berry curvatures and optical selection rules lead to the coexistence of valley and spin Hall effects in the SWSiX2 ***,the optical transition energies can be remarkably modulated by the in-plane *** tensile(compressive)in-plane strains can achieve spin flipping in the SWSiN2 monolayer,and induce both SWSiP_(2)and SWSiAs_(2)monolayers transit from semiconductor to *** research provides new 2D semiconductor candidates for designing high-performance valleytronic devices.

关键词： first-principles calculations two-dimensional valleytronic spintronic

来源：评论

学校读者我要写书评

暂无评论

Swarm intelligence:A survey of model classification and applications

引用

Chinese Journal of Aeronautics 2025年第3期38卷 163-182页

作者： Chao WANG Shuyuan ZHANG Tianhang MA Yuetong XIAO Michael Zhiqiang CHEN Lei WANG School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China School of Automation Nanjing University of Science and TechnologyNanjing 210094China

Swarm Intelligence (SI) is a collective behavior that emerges from interaction between individuals in a group. Typical SI includes fish schooling, ant foraging, bird migration, and so on. A great deal of models have been introduced to characterize the mechanism of SI. This article reviews several typical models and classifies them into four categories: self-driven particle models, with Boids model as the primary example;pheromone communication models, including the ant colony pheromone model which serves as the foundation for ant colony optimization;leadership decision models, utilizing the hierarchical dynamics model of pigeon flock as a prime instance;empirical research models, which employ the topological rule model of starling flock as a classic model. On this basis, each type of model is elaborated upon in terms of its typical model overview, applications, and model evaluation. More specifically, multi-agent swarm control, path optimization and obstacle avoidance, formation and consensus control, trajectory tracking in the dense crowd and social networks analysis are surveyed in the application of each category, respectively. Furthermore, the more precise and effective modeling techniques for leadership decision and empirical research models are described. Limitations and potential directions for further exploration in the study of SI are presented.

关键词： Swarm intelligence Ant colony optimization Self-driven particle models Pheromone communication models Leadership decision models Empirical research models

来源：评论

学校读者我要写书评

暂无评论

Understanding and Detecting Inefficient Image Displaying Issues in Android Apps

引用

Journal of computer science & technology 2024年第2期39卷 434-459页

作者：李文杰马骏蒋炎岩许畅马晓星 State Key Laboratory of Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China

Mobile applications(apps for short)often need to display ***,inefficient image displaying(IID)issues are pervasive in mobile apps,and can severely impact app performance and user *** paper first establishes a descriptive framework for the image displaying procedures of IID *** on the descriptive framework,we conduct an empirical study of 216 real-world IID issues collected from 243 popular open-source Android apps to validate the presence and severity of IID issues,and then shed light on these issues’characteristics to support research on effective issue *** the findings of this study,we propose a static IID issue detection tool TAPIR and evaluate it with 243 real-world Android ***,49 and 64 previously-unknown IID issues in two different versions of 16 apps reported by TAPIR are manually confirmed as true positives,respectively,and 16 previously-unknown IID issues reported by TAPIR have been confirmed by developers and 13 have been ***,we further evaluate the performance impact of these detected IID issues and the performance improvement if they are *** results demonstrate that the IID issues detected by TAPIR indeed cause significant performance degradation,which further show the effectiveness and efficiency of TAPIR.

关键词： Android application(app) inefficient image displaying(IID) performance empirical study static analysis

来源：评论

学校读者我要写书评

暂无评论

A Rearrangement and Restore-Based Mixer Model for Target-Oriented Multimodal Sentiment Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 3109-3119页

作者： Jia, Li Ma, Tinghuai Rong, Huan Sheng, Victor S. Huang, Xuejian Xie, Xintong Nanjing University of Information Science and Technology School of Computer Science Nanjing Jiangsu210044 China Nanjing University of Information Science and Technology School of Computer and Software Nanjing Jiangsu210044 China Jiangsu Ocean University School of Computer Engineering Lianyungang Jiangsu222005 China Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing Jiangsu210044 China Texas Tech University Department of Computer Science LubbockTX79409 United States

With the development of fine-grained multimodal sentiment analysis tasks, target-oriented multimodal sentiment (TMSC) analysis has received more attention, which aims to classify the sentiment of target with the help of textual and associated image features. Existing methods focus on exploring fine-grained image features and incorporate transformer-based complex fusion strategies, while ignoring the heavy computational burden. Recently, some lightweight multilayer perceptrons (MLP)-based methods have been successfully applied to multimodal sentiment classification tasks. In this article, we propose an effective rearrangement and restore mixer model (RR-Mixer) for TMSC, which dedicates the interaction of image, text, and targets along the modal-axis, sequential-axis, and feature channel-axis through rearrangement and restore operations. Specifically, we take vision transformer (ViT) and robustly optimized BERT (RoBERTa) pretrained models to extract image and textual features, respectively. Further, we adopt cosine similarity to select the most semantically relevant image features. Then, an RR-Mixer module is designed for mixed multimodal features, with the core technology consisting of rolling, grouping rearrangement and restore operations. Moreover, we introduce MLP Unit to learn the information of different modalities for intermodal interaction. The results show that our model achieves superior performance on two benchmark multimodal datasets, TWITTER-15 and TWITTER-17, with a significant improvement of 4.66% and 1.26% in terms of macro-F1. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Federated Learning Incentive Mechanism for Dynamic Client Participation:Unbiased Deep Learning Models

引用

computers, Materials & Continua 2025年第4期83卷 619-634页

作者： Jianfeng Lu Tao Huang Yuanai Xie Shuqin Cao Bing Li School of Computer Science and Technology Wuhan University of Science and TechnologyWuhan430065China College of Computer Science South-Central Minzu UniversityWuhan430074China School of Computer Science and Technology Zhejiang Normal UniversityJinhua321004China

The proliferation of deep learning(DL)has amplified the demand for processing large and complex datasets for tasks such as modeling,classification,and ***,traditional DL methods compromise client privacy by collecting sensitive data,underscoring the necessity for privacy-preserving solutions like Federated Learning(FL).FL effectively addresses escalating privacy concerns by facilitating collaborative model training without necessitating the sharing of raw *** that FL clients autonomously manage training data,encouraging client engagement is pivotal for successful model *** overcome challenges like unreliable communication and budget constraints,we present ENTIRE,a contract-based dynamic participation incentive mechanism for *** ensures impartial model training by tailoring participation levels and payments to accommodate diverse client *** approach involves several key ***,we examine how random client participation impacts FL convergence in non-convex scenarios,establishing the correlation between client participation levels and model ***,we reframe model performance optimization as an optimal contract design challenge to guide the distribution of rewards among clients with varying participation *** balancing budget considerations with model effectiveness,we craft optimal contracts for different budgetary constraints,prompting clients to disclose their participation preferences and select suitable contracts for contributing to model ***,we conduct a comprehensive experimental evaluation of ENTIRE using three real *** results demonstrate a significant 12.9%enhancement in model performance,validating its adherence to anticipated economic properties.

关键词： Federated learning deep learning non-IID data dynamic client participation non-convex optimization contract

来源：评论

学校读者我要写书评

暂无评论

More Accurate Constraints for Self-Supervised Learning in Remote Sensing Images based Object Detection

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12303-12314页

作者： Zheng, Shangdong Wu, Zebin Xu, Yang Liu, Qian Wei, Zhihui Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense China Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China

Self-supervised learning (SSL) automatically generates internal labels by exploring the potential auxiliary task of the network itself, and trains the same model through these annotations to learn the latent representation of the data, which greatly improves the accuracy of object detection in remote sensing images (RSIs). However, most existing methods suffer from guaranteeing the quality of the generated SSL pseudo annotations, and the constructed auxiliary tasks are not detectionoriented, which is difficult to enhance the feature representations that are beneficial for object detection. In this paper, we focus on generating more accurate constraints by excavating the intercorrelation between fully and weakly-supervised learning to improve the performance of object detection in RSIs. Initially, weakly-supervised learning (WSL) assigns the pseudo instancelevel annotations for the high-scoring positive bags to model the detector, which can be regarded as a weakened version of the region proposal network (RPN). Fortunately, RPN can be constrained by the ground truth of bounding boxes in fullysupervised learning (FSL), and the high-quality supervisions it provides are unavailable in any WSL methods. Moreover, we construct a proposal generation module (PGM), which further filters the unreliable bounding boxes, predicted by RPN, to supplement high-quality constraints into the ground truth and SS generated candidate boxes to supervise the optimization of WSL branch. By constructing an interactive learning paradigm of WSL and FSL, the former has more accurate constraints to learn an efficient auxiliary task, while the latter enjoys a richer representation form of data provided by WSL, which is undoubtedly a win-win process. Finally, we cascade the losses of WSL and FSL to further explore the intrinsic correlation between them by sharing the same feature extraction network. Experimental comparisons on DOTA and DIOR datasets demonstrate that our method achieves superior per

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Tracing monoclinic distortion in NCM532 cathode materials by in situ high-energy synchrotron X-ray diffraction

引用

Progress in Natural science:Materials International 2024年第2期34卷 274-279页

作者： Min Dong Qingya Sun Zhihua Wang Zixin Rui Zhe Zhang He Zhu Si Lan Herbert Gleiter Institute of Nanoscience School of Materials Science and Engineering Nanjing University of Science and Technology School of Mechanical Engineering Nanjing University of Science and Technology School of Materials Science and Engineering Henan University of Technology Center for Neutron Scattering City University of Hong Kong Shenzhen Research Institute

Layered LiNixCoyMnzO2（NCM） cathode materials have emerged as the best choice for high-energy-density lithium-ion batteries for powering electric *** significant research efforts,the understanding of complex structural dynamics during lithium（de-） intercalation still remains a subject of debate,especially in scenarios where morphology and composition *** this study,we carried out in situ high-energy synchrotron X-ray diffraction experiments on commercial NCM523cathode materials in both single crystal and polycrystalline forms to probe the structural changes during charging and discharging in *** findings reveal that both single crystal and polycrystalline materials exhibit typical H1-H2-H3 phase ***,in polycrystalline NCM532,a monoclinic intermediate phase emerges between the H1 and H2 *** this process,symmetry reduces from R-3m to C2/m,which is attributed to a shear distortion along the ab *** contrast,for single crystal materials,the H1 phase directly transforms into the H2 phase without the monoclinic *** observed monoclinic distortion significantly impacts structural stability and material cycling *** study provides new insight into the structural dynamics in NCM532 cathode materials,particularly concerning morphology-dependent behaviors,which could deepen our understanding of the relationship between NCM material structures and their performance.

关键词： Single crystals

来源：评论

学校读者我要写书评

暂无评论

A pure quantum secret sharing scheme based on GHZ basis measurement and quantum entanglement exchange

引用

Chinese Physics B 2025年第3期34卷 95-102页

作者： Bai Liu Jun Zhang Shupin Qiu Mingwu Zhang School of Computer Science Hubei University of TechnologyWuhan 430068China

At present,most quantum secret sharing(QSS)protocols are more or less designed with the incorporation of classical secret sharing *** the increasing maturity of quantum technology,QSS protocols based on pure quantum mechanics are becoming more *** secret sharing schemes cannot achieve absolute security,and their involvement can compromise the security of QSS *** paper proposes a QSS scheme based on Greenberger-Horn-Zeilinger(GHZ)basis measurement and quantum entanglement *** this protocol,the secret sender stores the secret information using Pauli *** obtain their shares by measuring the product state ***,participants complete the secret reconstruction through quantum entanglement exchange and other related quantum *** addition,the particles held by participants in the protocol do not contain any secret *** participant's particles are in a state of maximum entanglement,and no participant can deduce the particle information of other participants through their own *** the same time,the protocol is based on pure quantum mechanics and does not involve classical schemes,which avoids the problem of reduced security of the *** analysis indicates that the protocol is not vulnerable to retransmission interception and collusion ***,it is capable of detecting and terminating the protocol promptly when facing with attacks from dishonest participants.

关键词： quantum secret sharing projection measurement quantum entanglement exchange threshold

来源：评论

学校读者我要写书评

暂无评论

Multiple-event-triggered adaptive fuzzy output-feedback control for MIMO uncertain nonlinear systems

引用

science China(Technological sciences) 2025年第2期68卷 216-226页

作者： Shuai SUI Yu YANG Shaocheng TONG C.L.Philip CHEN School of Science Liaoning University of TechnologyJinzhou 121001China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China

The article addresses the output-feedback control issue for a class of multi-input multi-output(MIMO)uncertain nonlinear systems with multiple event-triggered mechanisms(ETM).Compared to previous event-triggering studies,this paper aims to trigger both the output and filtered *** nonlinear dynamics are approximated using fuzzy logic systems(FLSs).Then,a novel kind of state observer has been designed to deal with unmeasurable state problems using the triggered output *** sampled estimated state,the triggered output signal,and the filtered signal are utilized to propose an event-triggering mechanism that consists of sensor-to-observer(SO)and observer-to-controller(OC).An event-triggered output feedback control approach is given inside backstepping control,whereby the filter may be employed to circumvent the issue of the virtual control function not being differentiable at the trigger *** is testified that,according to the Lyapunov stability analysis scheme,all closed-loop signals and the system output are ultimately uniformly constrained by our control ***,the simulation examples are performed to confirm the theoretical findings.

关键词： event-triggered control(ETC) dynamic surface control(DSC) output-feedback control fuzzy adaptive control

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：