检索结果-内蒙古大学图书馆

Polynomial stacked-attention network for nationality classification

Frontiers of Computer Science 2022年第4期16卷 215-217页

作者： Kunyan Li Jie Zhang Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing100190China University of Chinese Academy of Sciences Beijing100049China

1Introduction In recent years,nationality and region inference has atracted more and_more *** anthropological researches indicate that human faces are influenced by genes,and other external factors,e.g-,geographical environment[1].This relevance provides possible solutions for geographical area inference by ***,it remains a challenging task due to the tiny differences on faces for various countries,which is even hard for human beings to tell.

关键词： Polynomial s. network

来源：评论

学校读者我要写书评

暂无评论

Representation of Semantic Word Embeddings Based on SLDA and Word2vec Model

引用

Chinese Journal of Electronics 2023年第3期32卷 647-654页

作者： TANG Huanling ZHU Hui WEI Hongmin ZHENG Han MAO Xueli LU Mingyu GUO Jin School of Computer Science and Technology Shandong Technology and Business University Co-innovation Center of Shandong Colleges and Universities: Future Intelligent Computing Key Laboratory of Intelligent Information Processing in Universities of Shandong Shandong Technology and Business University School of Information and Electronic Engineering Shandong Technology and Business University Information Science and Technology College Dalian Maritime University School of Computer and Information Technology Liaoning Normal University

To solve the problem of semantic loss in text representation, this paper proposes a new embedding method of word representation in semantic space called wt2svec based on supervised latent Dirichlet allocation(SLDA) and Word2vec. It generates the global topic embedding word vector utilizing SLDA which can discover the global semantic information through the latent topics on the whole document set. It gets the local semantic embedding word vector based on the Word2vec. The new semantic word vector is obtained by combining the global semantic information with the local semantic information. Additionally, the document semantic vector named doc2svec is generated. The experimental results on different datasets show that wt2svec model can obviously promote the accuracy of the semantic similarity of words,and improve the performance of text categorization compared with Word2vec.

关键词： Semantics Text categorization Resource management Task analysis

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Privacy Preservation Method for Attributed Social Network Based on Negative Representation of information

引用

Computer Modeling in Engineering & Sciences 2024年第7期140卷 1045-1075页

作者： Hao Jiang Yuerong Liao Dongdong Zhao Wenjian Luo Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei230601China Chongqing Research Institute School of Computer Science and Artificial IntelligenceWuhan University of TechnologyWuhan430070China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and TechnologyHarbin Institute of TechnologyShenzhen518055China

Due to the presence of a large amount of personal sensitive information in social networks,privacy preservation issues in social networks have attracted the attention of many *** by the self-nonself discrimination paradigmin the biological immune system,the negative representation of information indicates features such as simplicity and efficiency,which is very suitable for preserving social network ***,we suggest a method to preserve the topology privacy and node attribute privacy of attribute social networks,called ***,a negative survey-based method is developed to disturb the relationship between nodes in the social network so that the topology structure can be kept ***,a negative database-based method is proposed to hide node attributes,so that the privacy of node attributes can be preserved while supporting the similarity estimation between different node attributes,which is crucial to the analysis of social *** evaluate the performance of the AttNetNRI,empirical studies have been conducted on various attribute social networks and compared with several state-of-the-art methods tailored to preserve the privacy of social *** experimental results show the superiority of the developed method in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topology disturbing and attribute hiding *** experimental results show the superiority of the developed methods in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topological interference and attribute-hiding components.

关键词： Attributed social network topology privacy node attribute privacy negative representation of information negative survey negative database

来源：评论

学校读者我要写书评

暂无评论

A SAR Target Recognition Strategy Guided by Electromagnetic Scattering Feature 2

A SAR Target Recognition Strategy Guided by Electromagnetic ...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Yin, Yifei Chen, Liang Liu, Lujiao Meng, Yufan Chen, Fan Shi, Hao National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Chinese Academy of Sciences Aerospace Information Research Institute Beijing China

ISBN: (纸本)9798331515669

SAR target Automatic Target Recognition (ATR) is indispensable in SAR image interpretation. Recently, deep learning technology has been widely used in SAR target recognition tasks. Most networks achieve incremental improvements in target recognition by modifying their structures to extract visual features of targets. However, due to the unique imaging mechanism, relying solely on visual features often leads to the loss of target information. In contrast, the ASC model, which captures the electromagnetic scattering characteristics of the target, plays a crucial role in target recognition tasks. Unfortunately, traditional parameter estimation methods for extracting the ASC model are computationally expensive and time-consuming, making them impractical for real-world applications. To address these issues, we propose a novel target recognition method based on electromagnetic scattering features in this paper. First, a lightweight network-based feature extraction module is designed. Then, the target ASC image is used as the ground truth for guidance, with image intensity and target structure serving as the loss functions during training. Finally, an ASC model-guided feature fusion network is designed, utilizing the fused features for target recognition. On the MSTAR dataset, a visual assessment experiment demonstrated that the proposed feature extraction module effectively extracts electromagnetic scattering features under various operating conditions. Subsequently, in downstream classification tasks, the inclusion of the proposed module resulted in improved accuracy compared to other networks. Additionally, a visualization analysis of the classification network showed that, under the guidance of electromagnetic scattering features, the network achieved good interpretability. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Temporal Modeling for Multi-object Tracking in Satellite Video 2

Multi-frame Temporal Modeling for Multi-object Tracking in S...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Chai, Bingqian Qiao, Tingting Xie, Baorong Wang, Jue Liu, Wenchao Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Shanghai Aerospace Electronic Technology Institute Shanghai China

ISBN: (纸本)9798331515669

With the advancement of remote sensing technology, video satellites have played an increasingly important role in both military and civilian domains, and they are widely used in areas such as military guidance, intelligent transportation, and disaster response. Multi-object tracking (MOT) in satellite video is a crucial research topic in these fields and has made certain progress. However, due to the difficulty of tracking objects in complex scene and low resolution, current MOT methods face issues of low accuracy in satellite video. In this work, we propose a joint-detection-and-tracking method called multi-frame temporal MOT (MFT-MOT). Firstly, a heatmap guided multi-frame temporal modeling method is introduced to extract features with temporal semantic information while suppressing background noise. Then, we utilize a weights-shared encoder-decoder network to facilitate interaction of temporal and spatial information and capture inter-frame object motion tracks at low resolution. Experiments on SAT-MTB dataset shows the effectiveness of our method. © 2024 IEEE.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

PFedKD: Personalized Federated Learning via Knowledge Distillation using Unlabeled Pseudo Data for Internet of Things

引用

IEEE Internet of Things Journal 2025年第11期12卷 16314-16324页

作者： Li, Hanxi Chen, Guorong Wang, Bin Chen, Zheng Zhu, Yongsheng Hu, Fuqiang Dai, Jiao Wang, Wei Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation 3 Shangyuancun Beijing China China Railway Information Technology Group Corporation Limited Institute of Computing Technologies Beijing10081 China

With the rapid advancement of wearable devices and IoT technologies, sensor data generated by edge devices has surged. This data is crucial for advancing IoT applications, including health status monitoring, abnormal behavior detection, and environmental monitoring. However, traditional centralized learning requires uploading data to a central server, raising security and privacy concerns and hindering data application. Federated learning (FL) offers a solution by enabling collaborative model training on IoT devices without transferring data from the local device. In practice, edge devices generate data that is often highly heterogeneous, making it challenging for the global FL model to capture local data distributions accurately, leading to significant performance degradation. Additionally, imbalanced edge device resources and limited bandwidth can cause data transmission delays or interruptions, impacting application feasibility. To address these issues, we propose PFedKD, a novel personalized FL algorithm based on knowledge distillation, aimed at enhancing the model's generalization ability and reducing communication overhead in heterogeneous IoT data environments. PFedKD constructs a public dataset using unlabeled pseudo data to extract knowledge from each client, training personalized models that fit local data distributions. This method controls dataset size while enhancing performance. During communication, only logits and class prototypes are transmitted, ensuring high communication efficiency. Sharpness Aware Minimization is introduced in local model training to optimize generalization. Additionally, we design a weight distribution mechanism based on client sample quality evaluation that optimizes knowledge aggregation and model personalization. Extensive experiments demonstrate that PFedKD significantly outperforms state-of-the-art baselines in both learning performance and communication efficiency. © 2025 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

A Dual-Branch Network Based on ViT and Mamba for Semantic Segmentation of Remote Sensing Image 2

A Dual-Branch Network Based on ViT and Mamba for Semantic Se...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： An, Ke Wang, Ying Chen, Liang Wang, Yupie Beijing Institute of Technology National Key Laboratory for Space-Born Intelligent Information Processing Beijing China Shanghai Academy of Spaceflight Technology Shanghai China

ISBN: (纸本)9798331515669

Semantic segmentation of remote sensing images has significant applications across various scenarios. The prevailing frameworks include Convolutional Neural Network (CNN) and Transformer. However, CNN is limited by the receptive field of convolutions, while the Transformer is constrained by computational complexity, which restricts attention calculations to local windows and fails to effectively address long-range dependency modeling. The efficient Mamba architecture, characterized by linear complexity, offers a promising solution to these challenges. Inspired by Mamba, we propose a dual-branch network based on ViT and Mamba. The Vision Transformer (ViT) branch incorporates the Swin Transformer to model spatial details while maintaining computational complexity within acceptable bounds. Complementarily, the Mamba branch efficiently captures global context and long-range dependencies. Additionally, to suppress noise and conflicting information arising from the fusion of features from different frameworks, we design the Cross-Model Fusion Module (CMFM) and the Cross-Model Relevance Loss (CMRLoss) to achieve semantic consistency in the fusion process. The comprehensive experimental findings on the commonly utilized GaoFen-2 and iSAID datasets clearly illustrate the advantages of our proposed approach compared to the leading methods in the field. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Conditional selection with CNN augmented transformer for multimodal affective analysis

引用

CAAI Transactions on Intelligence technology 2024年第4期9卷 917-931页

作者： Jianwen Wang Shiping Wang Shunxin Xiao Renjie Lin Mianxiong Dong Wenzhong Guo College of Computer and Data Science Fuzhou UniversityFuzhouChina College of Computer and Cyber Security Fujian Normal UniversityFuzhouChina Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhouChina Digital Fujian Institute of Big Data Security Technology Fujian Normal UniversityFuzhouChina Department of Sciences and Informatics Muroran Institute of TechnologyMuroranJapan

Attention mechanism has been a successful method for multimodal affective analysis in recent years. Despite the advances, several significant challenges remain in fusing language and its nonverbal context information. One is to generate sparse attention coefficients associated with acoustic and visual modalities, which helps locate critical emotional se-mantics. The other is fusing complementary cross‐modal representation to construct optimal salient feature combinations of multiple modalities. A Conditional Transformer Fusion Network is proposed to handle these problems. Firstly, the authors equip the transformer module with CNN layers to enhance the detection of subtle signal patterns in nonverbal sequences. Secondly, sentiment words are utilised as context conditions to guide the computation of cross‐modal attention. As a result, the located nonverbal fea-tures are not only salient but also complementary to sentiment words directly. Experi-mental results show that the authors’ method achieves state‐of‐the‐art performance on several multimodal affective analysis datasets.

关键词： affective computing data fusion information fusion multimodal approaches

来源：评论

学校读者我要写书评

暂无评论

Power Minimization for the IRS-Aided SWIPT Secure Communication System with Imperfect Cascaded Channel

引用

Journal of Communications and information Networks 2023年第2期8卷 133-140页

作者： Chunlong He Shuqiong Xu Gongbin Qian Xingquan Li Chiya Zhang Guangdong Key Laboratory of Intelligent Information Processing Shenzhen UniversityShenzhen 518060China School of Microelectronics Shenzhen Institute of Information TechnologyShenzhen 518000China School of Electronic and Information Engineering Harbin Institute of TechnologyShenzhen 518055China National Mobile Communications Research Laboratory Southeast UniversityNanjing 210096China Peng Cheng Laboratory(PCL) Shenzhen 5180523China

intelligent reflecting surface(IRS)-assisted simultaneous wireless information and power transfer(SWIPT)is a promising technology for prolonging the lifetime of the users and improving system ***,it is challenging to obtain the perfect channel state information(CSI)at the base station(BS)due to the lack of radio frequency(RF)chains at the IRS,which becomes even harder when eavesdroppers(Eves)*** this paper,we study the power issues in the IRS-aided SWIPT system under the imperfect CSI of BS-IRS-Eves *** aim to minimize the transmitting power at the BS by jointly designing transmit beamforming and reflective beamforming with subject to the rate outage probability constraints of the Eves,the energy harvesting constraints of the energy receivers(ERs),and the minimum rate constraints of the information receivers(IRs).We use Bernstein-type inequality to solve the rate outage probability ***,the formulated nonconvex problem can be efficiently tackled by employing alternating optimization(AO)combined with semidefinite relaxation(SDR)and penalty convex-concave procedure(CCP).Numerical results demonstrate the effectiveness of the proposed scheme.

关键词： IRS SWIPT secure communication AO

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：