检索结果-南通市图书馆

Hybrid first and second order attention Unet for building segmentation in remote sensing images

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第4期63卷 69-80页

作者： Nanjun HE Leyuan FANG Antonio PLAZA College of Electrical and Information Engineering Hunan University Hyperspectral Computing Laboratory Department of Technology of Computers and CommunicationsEscuela Politecnica University of Extremadura

Recently, building segmentation(BS) has drawn significant attention in remote sensing applications. Convolutional neural networks(CNNs) have become the mainstream analysis approach in this field owing to their powerful representative ability. However, owing to the variation in building appearance, designing an effective CNN architecture for BS still remains a challenging task. Most of CNN-based BS methods mainly focus on deep or wide network architectures, neglecting the correlation among intermediate *** address this problem, in this paper we propose a hybrid first and second order attention network(HFSA)that explores both the global mean and the inner-product among different channels to adaptively rescale intermediate features. As a result, the HFSA can not only make full use of first order feature statistics, but also incorporate the second order feature statistics, which leads to more representative feature. We conduct a series of comprehensive experiments on three widely used aerial building segmentation data sets and one satellite building segmentation data set. The experimental results show that our newly developed model achieves better segmentation performance over state-of-the-art models in terms of both quantitative and qualitative results.

关键词： building segmentation(BS) convolutional neural networks(CNNs) remote sensing high order pooling attention

Dual attention autoencoder for all-weather outdoor lighting estimation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第11期64卷 22-35页

作者： Piaopiao YU Jie GUO Longhai WU Cheng ZHOU Mengtian LI Chenchen WANG Yanwen GUO National Key Lab for Novel Software Technology Nanjing University Samsung Electronics (China)R&D Center Kuaishou Technology

Accurate outdoor illumination estimation is not easy due to extremely complicated sky appearance and the mutual interference of the sun and sky. In view of these challenges, we present a new deep approach for the estimation of all-weather outdoor illumination. The key to our approach is a novel dual attention autoencoder(DAA) with two independent branches to compress the sun and sky lighting information from an input HDR panorama, respectively. This enables more accurate lighting estimation as evidenced by our experiments since the mutual interference between the sun and sky can be precluded effectively. In DAA,we design the adaptive feature pyramid and the attention module to promote its accuracy in *** further develop a sun-sky predictor, a masked network, to learn the sun and sky lighting conditions from an Fo V-limited image. Comprehensive qualitative and quantitative experiments verify the effectiveness of our proposed approach and show its superiority over the state of the arts.

关键词： outdoor illumination adaptive feature pyramid attention autoencoder augmented reality

Multi-label Image Classification via Coarse-to-Fine attention

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第6期28卷 1118-1126页

作者： LYU Fan LI Linyan Victor S.Sheng FU Qiming HU Fuyuan School of Electronic and Information Engineering Suzhou University of Science and Technology College of Intelligence and Computing Tianjin University Suzhou Institute of Trade and Commerce Department of Computer Science Texas Tech University

Great efforts have been made by using deep neural networks to recognize multi-label *** multi-label image classification is very complicated,many studies seek to use the attention mechanism as a kind of guidance. Conventional attention-based methods always analyzed images directly and aggressively, which is difficult to well understand complicated scenes. We propose a global/local attention method that can recognize a multi-label image from coarse to fine by mimicking how human-beings observe images. Our global/local attention method first concentrates on the whole image, and then focuses on its local specific objects. We also propose a joint max-margin objective function, which enforces that the minimum score of positive labels should be larger than the maximum score of negative labels horizontally and vertically. This function further improve our multi-label image classification method. We evaluate the effectiveness of our method on two popular multi-label image datasets(i.e., Pascal VOC and MS-COCO). Our experimental results show that our method outperforms state-of-the-art methods.

关键词： Multi-label classification Convolutional neural network Recurrent neural network attention

An attention-Based Neural Framework for Uncertainty Identification on Social Media Texts

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2020年第1期25卷 117-126页

作者： Xu Han Binyang Li Zhuoran Wang International Science and Technology Cooperation Base of Electronic System Reliability and Mathematical Interdisciplinary Information Engineering CollegeCapital Normal UniversityBeijing 100048China. School of Information Science and Technology University of International RelationsBeijing 100091China Tricorn(Beijing)Technology Co.Ltd Beijing 100029China

Uncertainty identification is an important semantic processing task. It is crucial to the quality of information in terms of factuality in many applications, such as topic detection and question answering. Factuality has become a premier concern especially in social media, in which texts are written informally. However, existing approaches that rely on lexical cues suffer greatly from the casual or word-of-mouth peculiarity of social media, in which the cue phrases are often expressed in substandard form or even omitted from sentences. To tackle these problems, this paper proposes an attention-based Neural Framework for Uncertainty identification on social media texts, named ANFU. ANFU incorporates attention-based Long Short-Term Memory(LSTM) networks to represent the semantics of words and Convolutional Neural Networks(CNNs) to capture the most important semantics. Experiments were conducted on four datasets, including 2 English benchmark datasets used in the CoNLL-2010 task of uncertainty identification and 2 Chinese datasets of Weibo and Chinese news texts. Experimental results showed that our proposed ANFU approach outperformed the-state-of-the-art on all the datasets in terms of F1 measure. More importantly, 41.37% and 13.10% improvements were achieved over the baselines on English and Chinese social media datasets, respectively, showing the particular effectiveness of ANFU on social media texts.

关键词： uncertainty identification attention neural networks social media

Adversarial Heterogeneous Network Embedding with Metapath attention Mechanism

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2019年第6期34卷 1217-1229页

作者： Chun-Yang Ruan Ye Wang Jiangang Ma Yanchun Zhang Xin-Tian Chen Shanghai Key Laboratory of Data Science School of Computer ScienceFudan UniversityShanghai 200433China Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Computer Science National University of Defense TechnologyChangsha 410073China School of Science Engineering and Information TechnologyFederation University AustraliaMelbourne 3000Australia College of Engineering and Science Victoria UniversityMelbourne 3000Australia

Heterogeneous information network (HIN)-structured data provide an effective model for practical purposes in real world. Network embedding is fundamental for supporting the network-based analysis and prediction tasks. Methods of network embedding that are currently popular normally fail to effectively preserve the semantics of HIN. In this study, we propose AGA2Vec, a generative adversarial model for HIN embedding that uses attention mechanisms and meta-paths. To capture the semantic information from multi-typed entities and relations in HIN, we develop a weighted meta-path strategy to preserve the proximity of HIN. We then use an autoencoder and a generative adversarial model to obtain robust representations of HIN. The results of experiments on several real-world datasets show that the proposed approach outperforms state-of-the-art approaches for HIN embedding.

关键词： heterogeneous information network network embedding attention mechanism generative adversarial network

A novel visual attention method for target detection from SAR images

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2019年第8期32卷 1946-1958页

作者： Fei GAO Aidong LIU Kai LIU Erfu YANG Amir HUSSAIN School of Electronic and Information Engineering Beihang UniversityBeijing 100083China Space Mechatronic Systems Technology Laboratory Department of DesignManufacture and Engineering ManagementUniversity of StrathclydeGlasgow G1 1XJUK Cognitive Big Data and Cyber-Informatics(CogBID)Laboratory School of ComputingEdinburgh Napier UniversityEdinburgh EH10 5DTScotlandUK

Synthetic Aperture Radar(SAR) imaging systems have been widely used in civil and military fields due to their all-weather and all-day abilities and various other advantages. However, due to image data exponentially increasing, there is a need for novel automatic target detection and recognition technologies. In recent years, the visual attention mechanism in the visual system has helped humans effectively deal with complex visual signals. In particular, biologically inspired top-down attention models have garnered much attention recently. This paper presents a visual attention model for SAR target detection, comprising a bottom-up stage and top-down *** the bottom-up step, the Itti model is improved based on the difference between SAR and optical images. The top-down step fully utilizes prior information to further detect targets. Extensive detection experiments carried out on the benchmark Moving and Stationary Target Acquisition and Recognition(MSTAR) dataset show that, compared with typical visual models and other popular detection methods, our model has increased ability and robustness for SAR target detection, under a range of Signal to Clutter Ratio(SCR) conditions and scenes. In addition, results obtained using only the bottom-up stage are inferior to those of the proposed method, further demonstrating the effectiveness and rationality of a top-down strategy. In summary, our proposed visual attention method can be considered a potential benchmark resource for the SAR research community.

关键词： Learning strategy Synthetic Aperture Radar(SAR) images Target detection Top-down Visual attention mechanism

Code attention: translating source code to comments by exploiting the code constructs

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第3期13卷 565-578页

作者： Wenhao ZHENG Hongyu ZHOU Ming LI Jianxin WU National Key Laboratory for Novel Software Technology Nanjing University Nanjing 210023 China

Appropriate comments of code snippets provide insight for code functionality, which are helpful for program comprehension. However, due to the great cost of authoring with the comments, many code projects do not contain adequate comments. Automatic comment generation techniques have been proposed to generate comments from pieces of code in order to alleviate the human efforts in annotating the code. Most existing approaches attempt to exploit certain correlations (usually manually given) between code and generated comments, which could be easily violated if coding patterns change and hence the performance of comment generation declines. In addition, recent approaches ignore exploiting the code constructs and leveraging the code snippets like plain text. Furthermore, previous datasets are also too small to validate the methods and show their advantage. In this paper, we propose a new attention mechanism called Codeattention to translate code to comments, which is able to utilize the code constructs, such as critical statements, symbols and keywords. By focusing on these specific points, Codeattention could understand the semantic meanings of code better than previous methods. To verify our approach in wider coding patterns, we build a large dataset from open projects in GitHub. Experimental results in this large dataset demonstrate that the proposed method has better performance over existing approaches in both objective and subjective evaluation. We also perform ablation studies to determine effects of different parts in Codeattention.

关键词： software mining machine learning code comment generation recurrent neural network attention mechanism

attention network function of insomniacs improved by manual acupuncture: Evidence from attention Network Task

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Acupuncture-Moxibustion 2019年第2期29卷 91-96页

作者：赵非一许红洪钰芳赵英侠燕海霞马恰怡明星胡菁徐燕上海杉达学院护理系上海中医药大学附属市中医医院上海中医药大学基础医学院上海天山中医医院

Objective:To investigate if manual acupuncture can improve the primary insomnia-induced impairments of attention network function and its ***:Totally 64 eligible participants were enrolled in a randomized controlled trial,with 32 cases allocated to the treatment group and 32 cases allocated to the control group,*** participants in the treatment group received real-acupuncture therapy[acupuncture at 'Five Spirits Acupoints' including Shéntíng(神庭 GV 24),Běnshén(本神 GB 13),Sìshéncōng(四神聪 EX-HN 1),Shéndào(神道 GV11)and Shénmén(神门 HT 7)]whereas participants in control group received sham-acupuncture therapy with Streitberger placebo-needle and same *** were offered every two days and three times a week for total 8 *** Pittsburgh sleep quality index(PSQI)and attention Network Task(ANT)were employed to assess the changes of sleep quality and attention network function at pretreatment and post-treatment,***,adverse effects were monitored and ***:(1)After 8-week treatment,the total score of PSQI in the treatment group decreased from14.22±3.46 to 8.19±3.34(P<0.001),and the total score of PSQI in the control group decreased from12.84±3.90 to 11.41±3.90(P<0.05).The decrease in the treatment group was more significant than that in the control group(P<0.001).(2)After treatment,the alerting efficiency of both groups increased,the treatment group increased from 40.44±5.62 to 56.44±5.37(P<0.001),and the control group increased from 39.50±6.39 to 40.06±6.14(P<0.05).The increase in the treatment group was more significant than that in the control group(P<0.001).The total reaction time of both groups decreased,the treatment group decreased from 574.94±10.1 to 548.34±15.05(P<0.001),and the control group decreased from578.25±13.26 to 576.78±12.15(P<0.05).The decrease in the treatment group was more significant than that in the control group(P<0.001).(3)No obvious change in orienting efficiency was observed in

关键词： Insomnia attention network function Acupuncture

attention deficit hyperactivity disorder and comorbidity: A review of literature

在线全文

学校读者我要写书评

暂无评论

World Journal of Clinical Cases 2019年第17期7卷 2420-2426页

作者： Sundar Gnanavel Pawan Sharma Pulkit Kaushal Sharafat Hussain Child Mental Health Services TeesEsk and Wear Valleys NHS Foundation TrustDurham DH1 4LWUnited Kingdom Department of Psychiatry Patan Academy of Health SciencesPatan 44700Nepal Northumberland Tyne and Wear NHS foundation TrustNewcastle NE3 3XTUnited Kingdom

attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder with onset in early *** is a clinically heterogenous condition with comorbidity posing a distinct challenge to diagnosing and managing these children and *** review aims to provide an overview of comorbidity with ADHD including other neurodevelopmental disorders,learning disorders,externalising and internalising *** in screening for,diagnosing and managing comorbidity with ADHD are ***,methodological challenges and future directions in research in this interesting field are highlighted.

关键词： attention deficit hyperactivity disorder Comorbidity Review