检索结果-内蒙古大学图书馆

Scene text recognition with context-aware autonomous bidirectional iterative models

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8605-8616页

作者： Zhao, Xiaoqing Xu, Miaomiao Li, Yanbing Huang, Hao Silamu, Wushour College of Computer Science and Technology Xinjiang University Urumqi China

This research focuses on Scene Text Recognition (STR), a crucial component in various applications of artificial intelligence such as image retrieval, office automation, and intelligent traffic systems. Recent studies have shown that semantic-aware approaches significantly improve the performance of STR tasks, with context-aware STR methods becoming mainstream. Among these, the fusion of visual and language models has shown remarkable effectiveness. We propose a novel method (PABINet) that incorporates three key components: a Visual-Language Decoder, a Language Model, and a Fusion Model. First, during training, the Visual-Language Decoder masks the original labels in the Transformer decoder using permutation masks, with each mask being unique. This enhances word memorization and learning through contextual semantic information, resulting in robust semantic knowledge. During the inference stage, the Visual-Language Decoder employs autonomous Autoregressive model (AR) inference to generate results. Subsequently, the Language Model scrutinizes and corrects the output of the Visual-Language Encoder using a cloze mask approach, achieving context-aware, autonomous, bidirectional inference. Finally, the Fusion Model concatenates and refines the outputs of both models through iterative *** results demonstrate that our PABINet performs exceptionally well when handling various quality images. When trained with synthetic data, PABINet achieves a new STR benchmark (average accuracy of 92.41%), and when trained with real data, it establishes new state-of-the-art results (average accuracy of 96.28%). © 2024 – IOS Press. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Robust Deep One-Class Classification Time Series Anomaly Detection

引用

computers, Materials & Continua 2025年第6期83卷 5181-5197页

作者： Zhengdao Yang Xuewei Wang Yuling Chen Hui Dou Haiwei Sang State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550000China College of Computer Science and Technology Weifang University of Science and TechnologyWeifang261000China School of Mathematics and Big Data Guizhou Education UniversityGuiyang550018China

Anomaly detection(AD)in time series data is widely applied across various industries for monitoring and security applications,emerging as a key research focus within the field of deep *** many methods based on different normality assumptions performwell in specific scenarios,they often neglected the overall normality *** feature extraction methods incorporate pre-training processes but they may not be suitable for time series anomaly detection,leading to decreased ***,real-world time series samples are rarely free from noise,making them susceptible to outliers,which further impacts detection *** address these challenges,we propose a novel anomaly detection method called Robust One-Class Classification Detection(ROC).This approach utilizes an autoencoder(AE)to learn features while constraining the context vectors fromthe AE within a sufficiently small hypersphere,akin to One-Class Classification(OC)*** simultaneously optimizing two hypothetical objective functions,ROC captures various aspects of *** categorize the input raw time series into clean and outlier sequences,reducing the impact of outliers on compressed feature *** results on public datasets indicate that our approach outperforms existing baselinemethods and substantially improves model robustness.

关键词： Time series anomaly detection self-supervised learning robustness

来源：评论

学校读者我要写书评

暂无评论

Pyridine-regulated Sb@InSbS_(3)ultrafine nanoplates as high-capacity and long-cycle anodes for sodium-ion batteries

引用

Rare Metals 2024年第5期43卷 2080-2092页

作者： Jia-Ying Ren Xiang-Lin Yu Chang-Miao Chen Xin-Yu Hu Ting Yang Ming Zhang College of Materials Science and Engineering and College of Science Central South University of Forestry and TechnologyChangsha 410004China College of Semiconductors(College of Integrated Circuits) Changsha Semiconductor Technology and Application Innovation Research InstituteHunan UniversityChangsha 410082China

Sb-based materials exhibit considerable potential for sodium-ion storage owing to their high theoretica ***,the bulk properties of Sb-based materials always result in poor cycling and rate *** overcome these issues,pyridine-regulated Sb@InSbS_(3)ultrafine nanoplates loaded on reduced graphene oxides(Sb@InSbS_(3)@rGO)were designed and *** the synthesis process,pyridine was initially adopted to coordinate with In^(3+),and uniformly dispersed In_(2)S_(3)ultrafine nanoplates on reduced graphene oxide were generated after ***,partial In^(3+)was exchanged with Sb^(3+),and Sb@InSbS_(3)@rGO was obtained by using the subsequent annealing *** unique structure of Sb@InSbS_(3)@rGO effectively shortened the transfer path of sodium ions and electrons and provided a high *** the anode in sodium-ion batteries,the Sb@InSbS_(3)@rGO electrode demonstrated a significantly higher reversible capacity better stability(445 m Ah·g^(-1)at 0.1 A·g^(-1)after 200 cycles and 212 mAh·g^(-1)at 2 A·g^(-1)after 1200 cycles),and superior rate(210 mAh·g^(-1)at 6.4 A·g^(-1))than the electrode without pyridine(355 mAh·g-1at 0.1 A·g-1after 55 cycles and 109 mAh·g^(-1)at 2 A·g^(-1)after 770 cycles)Furthermore,full cells were assembled by using the Sb@InSbS_(3)@rGO as anode and Na_(3)V_(2)(PO_(4))_(3)as cathode which demonstrated good cycling and rate performances and exhibited promising application *** results indicate that adjusting the microstructure of electrode materials through coordination balance is A·good strategy for obtaining high-capacity,high-rate,and longcycle sodium storage performances.

关键词： Sodium-ion battery Sb-based anode material Pyridine coordination Reduced size nanostructure Half/full cell

来源：评论

学校读者我要写书评

暂无评论

RCCA-SM9: securing SM9 on corrupted machines

引用

science China(Information sciences) 2024年第11期67卷 106-120页

作者： Rongmao CHEN Jinrong CHEN Xinyi HUANG Yi WANG College of Computer National University of Defense Technology Artificial Intelligence Thrust Information Hub Hong Kong University of Science and Technology (Guangzhou)

The SM9 identity-based encryption(IBE) scheme is a cryptographic standard used in China, and has been incorporated into the ISO/IEC standard in 2021. This work primarily proposes a countermeasure to secure the SM9 IBE scheme if its implementation is tampered with or deviated from the standard *** attacks, known as subversion attacks, are feasible and powerful in real-world cryptographic application scenarios. Our goal is to design a subversion-resilient variant of the SM9 IBE scheme, primarily using the cryptographic reverse firewall(CRF) proposed by Mironov and Stephens-Davidowitz at EUROCRYPT 2015.A CRF can sanitize cryptographic transcripts to eliminate covert channels, necessitating that the underlying primitive be rerandomizable. Unfortunately, the rerandomizability of the SM9 IBE scheme is disabled for ensuring security against chosen ciphertext attack(CCA). Hence, we shift our focus to a relaxed version of CCA security called RCCA security, offering security guarantees comparable to CCA security while allowing for ciphertext rerandomization. For this purpose, we design an efficient and RCCA-secure variant of the SM9 IBE scheme with provable security that can integrate with CRFs to achieve subversion resilience.

关键词： SM9 subversion resilience subversion attack cryptographic reverse firewall RCCA

来源：评论

学校读者我要写书评

暂无评论

Maximizing Overall Service Profit:Multi-Edge Service Pricing as a Stochastic Game Model

引用

Tsinghua science and technology 2024年第6期29卷 1872-1889页

作者： Shengye Pang Xinkui Zhao Jiayin Luo Jintao Chen Fan Wang Jianwei Yin College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China School of Software Technology Zhejiang UniversityNingbo 315048China

The diversified development of the service ecosystem,particularly the rapid growth of services like cloud and edge computing,has propelled the flourishing expansion of the service trading ***,in the absence of appropriate pricing guidance,service providers often devise pricing strategies solely based on their own interests,potentially hindering the maximization of overall market *** challenge is even more severe in edge computing scenarios,as different edge service providers are dispersed across various regions and influenced by multiple factors,making it challenging to establish a unified pricing *** paper introduces a multi-participant stochastic game model to formalize the pricing problem of multiple edge ***,an incentive mechanism based on Pareto improvement is proposed to drive the game towards Pareto optimal direction,achieving optimal ***,an enhanced PSO algorithm was proposed by adaptively optimizing inertia factor across three *** optimization significantly improved the efficiency of solving the game model and analyzed equilibrium states under various evolutionary *** results demonstrate that the proposed pricing incentive mechanism promotes more effective and rational pricing allocations,while also demonstrating the effectiveness of our algorithm in resolving game problems.

关键词： service pricing game theory incentive mechanism Pareto improvement equilibrium solution

来源：评论

学校读者我要写书评

暂无评论

Improved quantum(t,n)threshold group signature

引用

Chinese Physics B 2023年第9期32卷 184-191页

作者：张耀东刘锋左海新 College of Computer Science and Technology Shandong Technology and Business UniversityYantai 264005China College of Mathematic and Information Science Shandong Technology and Business UniversityYantai 264005China

Threshold signature is an important branch of the digital signature scheme,which can distribute signature rights and avoid the abuse of signature *** the continuous development of quantum computation and quantum information,quantum threshold signatures are gradually becoming more ***,a quantum(t,n)threshold group signature scheme was analyzed that uses techniques such as quantum-controlled-not operation and quantum ***,this scheme cannot resist forgery attack and does not conform to the design of a threshold signature in the signing *** on the original scheme,we propose an improved quantum(t,n)threshold signature scheme using quantum(t,n)threshold secret sharing *** analysis proves that the improved scheme can resist forgery attack and collusion attack,and it is *** the same time,this scheme reduces the level of trust in the arbitrator during the signature phase.

关键词： quantum(t n)threshold signature quantum(t n)threshold secret sharing forgery attack collusion attack

来源：评论

学校读者我要写书评

暂无评论

A Sentence Retrieval Generation Network Guided Video Captioning

引用

computers, Materials & Continua 2023年第6期75卷 5675-5696页

作者： Ou Ye Mimi Wang Zhenhua Yu Yan Fu Shun Yi Jun Deng College of Computer Science and Technology Xi’an University of Science and TechnologyXi’an710054China College of Safety and Engineering Xi’an University of Science and TechnologyXi’an710054China

Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input *** contents of video captioning are limited since few studies employed external corpus information to guide the generation of video captioning,which is not conducive to the accurate descrip-tion and understanding of video *** address this issue,a novel video captioning method guided by a sentence retrieval generation network(ED-SRG)is proposed in this ***,a ResNeXt network model,an efficient convolutional network for online video understanding(ECO)model,and a long short-term memory(LSTM)network model are integrated to construct an encoder-decoder,which is utilized to extract the 2D features,3D features,and object features of video data *** features are decoded to generate textual sentences that conform to video content for sentence ***,a sentence-transformer network model is employed to retrieve different sentences in an external corpus that are semantically similar to the above textual *** candidate sentences are screened out through similarity ***,a novel GPT-2 network model is constructed based on GPT-2 network *** model introduces a designed random selector to randomly select predicted words with a high probability in the corpus,which is used to guide and generate textual sentences that are more in line with human natural language *** proposed method in this paper is compared with several existing works by *** results show that the indicators BLEU-4,CIDEr,ROUGE_L,and METEOR are improved by 3.1%,1.3%,0.3%,and 1.5%on a public dataset MSVD and 1.3%,0.5%,0.2%,1.9%on a public dataset MSR-VTT *** can be seen that the proposed method in this paper can generate video captioning with richer semantics than several state-of-the-art approaches.

关键词： Video captioning encoder-decoder sentence retrieval external corpus RS GPT-2 network model

来源：评论

学校读者我要写书评

暂无评论

FedQT: A Federated Learning Model Compression Algorithm Based on Quicksort and Top Avg Pruning

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第1期9卷 225-238页

作者： Zhang, Jin-Quan Xu, Hui-Xin Ma, Yun-Shen Ni, Li-Na College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

With the advent of the fourth industrial revolution, data ushered in explosive growth. Federated learning can protect users’ privacy and raw data from being known by third parties. Its client data is only trained locally and will not be uploaded to the server. However, the need to continuously transmit between the server and the client in federated learning increases communication overhead and communication delay, and the consumption of resources is very large. In order to improve the communication efficiency of the federation, we proposed an FedQT federated learning model compression algorithm based on pruning and quantization. Firstly, the fast sorting is used to preprocess the trained parameters. Secondly, the middle part of the processed parameters is averaged to obtain the pruning threshold avg(ω). Then, according to the obtained new threshold standard, the model performs Top Avg pruning based on median comparison. Finally, the k − means algorithm is used to cluster the parameters for further compression. In the simulation experiment, FedQT is compared with uncompressed and other compression algorithms, and the time complexity is analyzed. It is proved that FedQT can compress the trained model parameters to improve its communication efficiency while reducing the time overhead. The model can be compressed by more than one thousand times, and the model accuracy can be maintained above 97%, which is enough to prove that FedQT algorithm has good performance in the compression framework of federated learning. © 2024.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Reconstructing interfacial manganese deposition for durable aqueous zinc-manganese batteries

引用

National science Review 2023年第10期10卷 139-150页

作者： Yida Hu Zhexuan Liu Lanyan Li Shan Guo Xuefang Xie Zhigao Luo Guozhao Fang Shuquan Liang School of Materials Science and Engineering Key Laboratory of Electronic Packaging and Advanced Functional Materials of Hunan ProvinceCentral South University School of Science Hunan University of Technology and Business College of Physical Science and Technology Xinjiang University College of Chemistry Xiangtan University

Low-cost,high-satety,and broad-prospect aqueous zinc-manganese batteries（ZMBs） are limited by complex interracial *** solid-liquid interfacial state of the cathode dominates the Mn dissolution/deposition process of aqueous ZMBs,especially the important influence on the mass and charge transfer behavior of Zn2+and Mn2+.We proposed a quasi-eutectic electrolyte（QEE） that would stabilize the reversible behavior of interracial deposition and favorable interracial reaction kinetic of manganese-based cathodes in a long cycle process by optimizing mass and charge *** emphasize that the initial interfacial reaction energy barrier is not the main factor affecting cycling performance,and the good reaction kinetics induced by interfacial deposition during the cycling process is more conducive to the stable cycling of the battery,which has been confirmed by theoretical analysis,quartz crystal microbalance with dissipation monitoring,depth etching X-ray photon-electron spectroscopy,*** a result,the QEE electrolyte maintained a stable specific capacity of 250 mAh g-1at 0.5 A g-1after 350 cycles in zinc-manganese *** energy density retention rate of the ZMB with QEE increased by 174%compared to that of conventional aqueous ***,the multi-stacked soft-pack battery with a cathodic mass load of 54.4 mg maintained a stable specific capacity of 200 mAh g-1for 100 cycles,demonstrating its commercial *** work proves the feasibility of adapting lean-water QEE to the stable aqueous ZMBs.

关键词： quasi-eutectic electrolyte aqueous zinc −manganese batteries solid −liquid interfacial state mass transfer charge transfer

来源：评论

学校读者我要写书评

暂无评论

CMDCF: an effective cross-modal dense cooperative fusion network for RGB-D SOD

引用

Neural Computing and Applications 2024年第23期36卷 14361-14378页

作者： Jia, XingZhao Zhao, WenXiu Wang, YuMei DongYe, ChangLei Peng, YanJun College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

The success of vision transformer demonstrates that the transformer structure is also suitable for various vision tasks, including high-level classification tasks and low-level dense prediction tasks. Salient object detection (SOD) is a pixel-level dense prediction task that simulates the most salient objects in human visual recognition scenarios. In recent years, depth images have been widely used for salient object detection. Compared with RGB SOD, the key point of RGB-D SOD is the effective fusion of depth information. As RGB-D SOD requires extracting depth features and fusing cross-modal information, additional computation is involved. However, except for lightweight models, most RGB-D SOD methods tend to obtain better prediction maps by consuming more computational resources. We propose a cross-modal dense cooperative fusion net, which provides state-of-the-art performance with less computation and parameters. We take advantage of the ability of the transformer structure to model long sequence dependencies to extract saliency features from RGB images. Since there is less information in the depth image than in the RGB image, it is not necessary to use the same structure in the depth stream. For the sake of reducing parameters and computation, we consider the asymmetric architecture. It is enough to meet our needs that deep features extracted by lightweight MobileV2Net. Our decoder can perform dense cooperative fusion of cross-modal information while decoding features. It can both effectively fuse cross-modal information and save computation. Comprehensive experiments on multiple benchmark datasets for RGB-D SOD show that compared with SOTA methods, our method performs much better with less computation and parameters. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Object detection

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：