检索结果-南通市图书馆

Computational Visual Media 2022年第3期8卷 331-368页

作者： Meng-Hao Guo Tian-Xing Xu Jiang-Jiang Liu Zheng-Ning Liu Peng-Tao Jiang Tai-Jiang Mu Song-Hai Zhang Ralph R.Martin Ming-Ming Cheng Shi-Min Hu BNRist Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China TKLNDST College of Computer ScienceNankai UniversityTianjin 300350China School of Computer Science and Informatics Cardiff UniversityCardiffUK

Humans can naturally and effectively find salient regions in complex *** by this observation,attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual *** an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input *** mechanisms have achieved great success in many visual tasks,including image classification,object detection,semantic segmentation,video understanding,image generation,3D vision,multimodal tasks,and self-supervised *** this survey,we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach,such as channel attention,spatial attention,temporal attention,and branch attention;a related repository https://***/MenghaoG uo/Awesome-Vision-attentions is dedicated to collecting related *** also suggest future directions for attention mechanism research.

关键词： attention transformer computer vision deep learning salience

Sports match prediction model for training and exercise using attention-based LSTM network

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Digital Communications and Networks 2022年第4期8卷 508-515页

作者： Qiyun Zhang Xuyun Zhang Hongsheng Hu Caizhong Li Yinping Lin Rui Ma Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyShouguang262700China Department of Computing Macquarie UniversitySydneyAustralia Faculty of Engineering University of AucklandNew Zealand No.1 Middle School of Pidu Chengdu Chengdu611730China e General Education Department Shandong First Medical University(Shandong Academy of Medical Sciences)TaianChina

Sports matches are very popular all over the *** prediction of a sports match is helpful to grasp the team's state in time and adjust the strategy in the process of the ***'s a challenging effort to predict a sports ***,a method is proposed to predict the result of the next match by using teams'historical match *** combined the Long Short-Term Memory(LSTM)model with the attention mechanism and put forward an ASLSTM model for predicting match ***,to ensure the timeliness of the prediction,we add the time sliding window to make the prediction have better *** the football match as an example,we carried out a case study and proposed the feasibility of this method.

关键词： Sports Prediction Long short-term memory attention Sliding window

Light field super-resolution using complementary-view feature attention

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 843-858页

作者： Wei Zhang Wei Ke Da Yang Hao Sheng Zhang Xiong Faculty of Applied Sciences Macao Polytechnic UniversityMacao SAR 999078China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191Chinaand Beihang Hangzhou Innovation Institute YuhangXixi Octagon CityYuhang DistrictHangzhou 310023China

Light field(LF)cameras record multiple perspectives by a sparse sampling of real scenes,and these perspectives provide complementary *** information is beneficial to LF super-resolution(LFSR).Compared with traditional single-image super-resolution,LF can exploit parallax structure and perspective correlation among different LF ***,the performance of existing methods are limited as they fail to deeply explore the complementary information across LF *** this paper,we propose a novel network,called the light field complementary-view feature attention network(LF-CFANet),to improve LFSR by dynamically learning the complementary information in LF ***,we design a residual complementary-view spatial and channel attention module(RCSCAM)to effectively interact with complementary information between complementary ***,RCSCAM captures the relationships between different channels,and it is able to generate informative features for reconstructing LF images while ignoring redundant ***,a maximum-difference information supplementary branch(MDISB)is used to supplement information from the maximum-difference angular positions based on the geometric structure of LF *** branch also can guide the process of *** results on both synthetic and real-world datasets demonstrate the superiority of our *** proposed LF-CFANet has a more advanced reconstruction performance that displays faithful details with higher SR accuracy than state-of-the-art methods.

关键词： light field(LF) super-resolution(SR) attention

Visual attention network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 733-752页

作者： Meng-Hao Guo Cheng-Ze Lu Zheng-Ning Liu Ming-Ming Cheng Shi-Min Hu Department of Computer Science Tsinghua UniversityBeijingChina Nankai University TianjinChina Fitten Tech BeijingChina

While originally designed for natural language processing tasks,the self-attention mechanism has recently taken various computer vision areas by ***,the 2D nature of images brings three challenges for applying self-attention in computer vision:(1)treating images as 1D sequences neglects their 2D structures;(2)the quadratic complexity is too expensive for high-resolution images;(3)it only captures spatial adaptability but ignores channel *** this paper,we propose a novel linear attention named large kernel attention(LKA)to enable self-adaptive and long-range correlations in self-attention while avoiding its ***,we present a neural network based on LKA,namely Visual attention Network(VAN).While extremely simple,VAN achieves comparable results with similar size convolutional neural networks(CNNs)and vision transformers(ViTs)in various tasks,including image classification,object detection,semantic segmentation,panoptic segmentation,pose estimation,*** example,VAN-B6 achieves 87.8%accuracy on ImageNet benchmark,and sets new state-of-the-art performance(58.2%PQ)for panoptic ***,VAN-B2 surpasses Swin-T 4%mloU(50.1%vs.46.1%)for semantic segmentation on ADE20K benchmark,2.6%AP(48.8%vs.46.2%)for object detection on COCO *** provides a novel method and a simple yet strong baseline for the *** code is available at https://***/Visual-attention-Network.

关键词： vision backbone deep learning ConvNets attention

NGAT:attention in breadth and depth exploration for semi-supervised graph representation learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2022年第3期23卷 409-421页

作者： Jianke HU Yin ZHANG College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

Recently,graph neural networks(GNNs)have achieved remarkable performance in representation learning on graph-structured ***,as the number of network layers increases,GNNs based on the neighborhood aggregation strategy deteriorate due to the problem of oversmoothing,which is the major bottleneck for applying GNNs to real-world *** efforts have been made to improve the process of feature information aggregation from directly connected nodes,i.e.,breadth ***,these models perform the best only in the case of three or fewer layers,and the performance drops rapidly for deep *** alleviate oversmoothing,we propose a nested graph attention network(NGAT),which can work in a semi-supervised *** addition to breadth exploration,a k-layer NGAT uses a layer-wise aggregation strategy guided by the attention mechanism to selectively leverage feature information from the k;-order neighborhood,i.e.,depth *** with a 10-layer or deeper architecture,NGAT can balance the need for preserving the locality(including root node features and the local structure)and aggregating the information from a large *** a number of experiments on standard node classification tasks,NGAT outperforms other novel models and achieves state-of-the-art performance.

关键词： Graph learning Semi-supervised learning Node classification attention

A Novel SE-CNN attention Architecture for sEMG-Based Hand Gesture Recognition

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2023年第1期134卷 157-177页

作者： Zhengyuan Xu Junxiao Yu Wentao Xiang Songsheng Zhu Mubashir Hussain Bin Liu Jianqing Li Key Laboratory of Clinical and Medical Engineering School of Biomedical Engineering and InformaticsNanjing Medical UniversityNanjing211166China Department of Medical Engineering Wannan Medical CollegeWuhu241002China Postdoctoral Innovation Practice Shenzhen PolytechnicShenzhen518055China

In this article,to reduce the complexity and improve the generalization ability of current gesture recognition systems,we propose a novel SE-CNN attention architecture for sEMG-based hand gesture *** proposed algorithm introduces a temporal squeeze-and-excite block into a simple CNN architecture and then utilizes it to recalibrate the weights of the feature outputs from the convolutional *** enhancing important features while suppressing useless ones,the model realizes gesture recognition *** last procedure of the proposed algorithm is utilizing a simple attention mechanism to enhance the learned representations of sEMG signals to performmulti-channel sEMG-based gesture recognition *** evaluate the effectiveness and accuracy of the proposed algorithm,we conduct experiments involving multi-gesture datasets Ninapro DB4 and Ninapro DB5 for both inter-session validation and subject-wise *** a series of comparisons with the previous models,the proposed algorithm effectively increases the robustness with improved gesture recognition performance and generalization ability.

关键词： Hand gesture recognition sEMG CNN temporal squeeze-and-excite attention

One Dimensional Conv-BiLSTM Network with attention Mechanism for IoT Intrusion Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第12期77卷 3765-3781页

作者： Bauyrzhan Omarov Zhuldyz Sailaukyzy Alfiya Bigaliyeva Adilzhan Kereyev Lyazat Naizabayeva Aigul Dautbayeva Department of Information Systems Al-Farabi Kazakh National UniversityAlmatyKazakhstan Department of Information Technology and Security Abylkas Saginov Karaganda Technical UniversityKaragandaKazakhstan Department of Computer Science and Information Technology K.Zhubanov Aktobe Regional UniversityAktobeKazakhstan Department of Information Systems International Information Technology UniversityAlmatyKazakhstan Department of Computer Science Korkyt Ata Kyzylorda State UniversityKyzylordaKazakhstan

In the face of escalating intricacy and heterogeneity within Internet of Things(IoT)network landscapes,the imperative for adept intrusion detection techniques has never been more *** paper delineates a pioneering deep learning-based intrusion detection model:the One Dimensional Convolutional Neural Networks(1D-CNN)and Bidirectional Long Short-Term Memory(BiLSTM)Network(Conv-BiLSTM)augmented with an attention *** primary objective of this research is to engineer a sophisticated model proficient in discerning the nuanced patterns and temporal dependencies quintessential to IoT network traffic data,thereby facilitating the precise categorization of a myriad of intrusion ***:The proposed model amal-gamates the potent attributes of 1D convolutional neural networks,bidirectional long short-term memory layers,and attention mechanisms to bolster the efficacy and resilience of IoT intrusion detection systems.A rigorous assessment was executed employing an expansive dataset that mirrors the convolutions and multifariousness characteristic of genuine IoT network settings,encompassing various network traffic paradigms and intrusion ***:The empirical evidence underscores the paramountcy of the One Dimensional Conv-BiLSTM Network with attention Mechanism,which exhibits a marked superiority over conventional machine learning ***,the model registers an exemplary AUC-ROC metric of 0.995,underscoring its precision in typifying a spectrum of intrusions within IoT ***:The presented One Dimensional Conv-BiLSTM Network armed with an attention Mechanism stands out as a robust and trustworthy vanguard against IoT network *** prowess in discerning intricate traffic patterns and inherent temporal dependencies transcends that of traditional machine learning *** commendable diagnostic accuracy manifested in this study advocates for its tangible *** investigation indubitably a

关键词： Intrusion detection attention deep learning IoT CNN BiLSTM

A BiLSTM cardinality estimator in complex database systems based on attention mechanism

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2022年第3期7卷 537-546页

作者： Qiang Zhou Guoping Yang Haiquan Song Jin Guo Yadong Zhang Shengjie Wei Lulu Qu Louis Alberto Gutierrez Shaojie Qiao School of Information Science and Technology Southwest Jiaotong UniversityChengduChina School of Software Engineering Chengdu University of Information TechnologyChengduChina School of Energy Power and Mechanical Engineering North China Electric Power UniversityBaodingChina Digital Media Art Key Laboratory of Sichuan ProvinceSichuan Conservatory of MusicChengduChina Department of Computer Science Rensselaer Polytechnic InstituteNew YorkNew YorkUSA

An excellent cardinality estimation can make the query optimiser produce a good execution *** there are some studies on cardinality estimation,the prediction results of existing cardinality estimators are inaccurate and the query efficiency cannot be guaranteed as *** particular,they are difficult to accurately obtain the complex relationships between multiple tables in complex database *** dealing with complex queries,the existing cardinality estimators cannot achieve good *** this study,a novel cardinality estimator is *** uses the core techniques with the BiLSTM network structure and adds the attention ***,the columns involved in the query statements in the training set are sampled and compressed into ***,the Word2vec model is used to embed the word vectors about the query ***,the BiLSTM network and attention mechanism are employed to deal with word *** proposed model takes into consideration not only the correlation between tables but also the processing of complex *** experiments and the evaluation of BiLSTM-attention Cardinality Estimator(BACE)on the IMDB datasets are *** results show that the deep learning model can significantly improve the quality of cardinality estimation,which is a vital role in query optimisation for complex databases.

关键词： attention BiLSTM cardinality estimation complex database systems query optimiser Word2vec

Neural Machine Translation Models with attention-Based Dropout Layer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第5期75卷 2981-3009页

作者： Huma Israr Safdar Abbas Khan Muhammad Ali Tahir Muhammad Khuram Shahzad Muneer Ahmad Jasni Mohamad Zain School of Electrical Engineering and Computer Science(SEECS) National University of Science and TechnologyIslamabadPakistan Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversiti Teknologi MARA40450Shah AlamSelangorMalaysia

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of *** model has obtained state-of-the-art performance for several language ***,there has been little work exploring useful architectures for Urdu-to-English machine *** conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and *** results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen *** trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,*** a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more *** attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear ***,we considered refining the attention-based models by defining an additional attention-based dropout *** dropout fixes alignment errors and minimizes translation errors at the word *** empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation *** ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as *** empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

关键词： Natural language processing neural machine translation word embedding attention perplexity selective dropout regularization Urdu Persian Arabic BLEU