检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ziyu Gong Chengcheng Mai Yihua Huang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Electronic Information/School of Artifical Intelligence Nanjing Normal University Nanjing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

The image-text retrieval task aims to retrieve relevant information from a given image or text. The main challenge is to unify multimodal representation and distinguish fine-grained differences across modalities, thereby finding similar contents and filtering irrelevant contents. However, existing methods mainly focus on unified semantic representation and concept alignment for multi-modalities, while the fine-grained differences across modalities have rarely been studied before, making it difficult to solve the information asymmetry problem. In this paper, we propose a novel asymmetry-sensitive contrastive learning method. By generating corresponding positive and negative samples for different asymmetry types, our method can simultaneously ensure fine-grained semantic differentiation and unified semantic representation between multi-modalities. Additionally, a hierarchical cross-modal fusion method is proposed, which integrates global and local-level features through a multimodal attention mechanism to achieve concept alignment. Extensive experiments performed on MSCOCO and Flickr30K, demonstrate the effectiveness and superiority of our proposed method.

关键词： Visualization Attention mechanisms Sensitivity Filtering Semantics Contrastive learning Optimization

来源：评论

学校读者我要写书评

暂无评论

Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services

Seed Feature Maps-based CNN Models for LEO Satellite Remote ...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Lu, Zhichao Ding, Chuntao Wang, Shangguang Cheng, Ran Juefei-Xu, Felix Boddeti, Vishnu Naresh Sun Yat-sen University School of Software Engineering Zhuhai China Beijing Jiaotong University School of Computer and Information Technology Beijing China Beijing University of Posts and Telecommunications Key Laboratory of Networking and Switching Technology Beijing China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China New York University New YorkNY United States Michigan State University Department of Computer Science and Engineering East LansingMI United States

ISBN: (纸本)9798350304855

Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interest from industry and academia. However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models. Existing approaches often require large floating-point operations (FLOPs) and substantial model parameter transmissions, presenting considerable challenges. To address these issues, this paper introduces a ground-station server-assisted framework. With the proposed framework, each layer of the CNN model contains only one learnable feature map (called the seed feature map) from which other feature maps are generated based on specific rules. The hyperparameters of these rules are randomly generated instead of being trained, thus enabling the generation of multiple feature maps from the seed feature map and significantly reducing FLOPs. Furthermore, since the random hyperparameters can be saved using a few random seeds, the ground station server assistance can be facilitated in updating the CNN model deployed on the LEO satellite. Experimental results on the ISPRS Vaihingen, ISPRS Potsdam, UAVid, and LoveDA datasets for semantic segmentation services demonstrate that the proposed framework outperforms existing state-of-the-art approaches. In particular, the SineFM-based model achieves a higher mIoU than the UNetFormer on the UAVid dataset, with 3.3 × fewer parameters and 2.2 × fewer FLOPs. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Resource Scheduling Method with Edge Channel Deployment for BPM 19

An Intelligent Resource Scheduling Method with Edge Channel ...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Liu, Bowen Dou, Wanchun Zhou, Xiaokang Zhang, Xuyun Qi, Lianyong Dai, Fei Chen, Chaochao Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Shiga University Faculty of Data Science Hikone Japan Macquarie University Department of Computing Sydney Australia College of Computer and Software Qingdao China Southwest Forestry University College of Big Data and Intelligent Engineering Kunming China Zhejiang University College of Computer Science and Technology Hangzhou China

ISBN: (纸本)9798350346558

Edge computing is a novel computing paradigm that offers kinds of resources at the network edge. In edge computing, terminal users are connected to edge servers via the wireless network and there are various channels in each wireless link. These wireless channels are limited resource while different channel has different cost and service ability. The dynamic changes of users' status make it harder to find an appropriate method to satisfy the BPM requirements of channel deployment. With this observation, it is a tricky challenge to make a trade-off between the system cost(rental price) and the service ability(number of users). In view of this challenge, an intelligent resource scheduling method, named EdgeIRS, is proposed in this paper. In the technical sense, the EdgeIRS method can accommodate most users at the edge with a minimum cost of deploying channel resources in an online way. Its performance is analyzed theoretically and the experiments verify the superiority of the method. © 2022 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

AsCL: An Asymmetry-sensitive Contrastive Learning Method for Image-Text Retrieval with Cross-Modal Fusion

arXiv

引用

arXiv 2024年

作者： Gong, Ziyu Mai, Chengcheng Huang, Yihua State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Electronic Information School of Artifical Intelligence Nanjing Normal University Nanjing China

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

AMSC: Adaptive Multi-channel Graph Convolutional Network-Enhanced Web Services Classification 23

AMSC: Adaptive Multi-channel Graph Convolutional Network-Enh...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Qing, Yueying Cao, Buqing Peng, Mi Zhang, Lulu Kang, Guosheng Liu, Jianxun Fletcher, Kenneth K. School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory of Service Computing and New Software Service Technology Xiangtan China University of Massachusetts Boston Department of Computer Science Boston United States

ISBN: (纸本)9781665494571

With the development of Service Oriented Architecture (SOA), the number of Web services on the Internet is also growing rapidly. Classifying Web services accurately and efficiently is helpful to improve the quality of services discovery and promote the efficiency of service composition. However, existing deep learning-based Web services classification methods, such as graph convolutional networks (GCNs), are incapable of adaptively learning the correlation between service topology structure and service node features concurrently, resulting in unsatisfactory classification performance. To address this problem, this paper proposes an adaptive multi-channel GCN-enhanced Web services classification method. In this method, we first extract specific and shared embedding, in the Web API node isomorphic network, from the node features, topology, and combination of Web service nodes. Then, an attention mechanism is used to learn the importance weight of each embedding. By doing this, we adaptively integrate these weights to ensure the consistency and difference of each learned embedding. Finally, experimental results on real datasets from Programmable Web show that compared with LINE, Node2vec, Deep-walk, GCN, and GAT, the method proposed in this paper has an average improvement in accuracy of 19.81%, 19.35%, 19.16%, 11.56%, and 7.75% respectively. © 2021 IEEE.

关键词： Correlation Adaptive systems Network topology Smart cities Quality of service Feature extraction Topology

来源：评论

学校读者我要写书评

暂无评论

EEG-based Emotion Recognition using Graph Attention Network with Dual-Branch Attention Module 46

EEG-based Emotion Recognition using Graph Attention Network ...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Li, Cheng Pun, Sio Hang Li, Jia Wen Chen, Fei University of Macau State Key Laboratory of Analog and Mixed-Signal Vlsi China Southern University of Science and Technology Department of Electrical and Electronic Engineering Shenzhen China Guangdong Polytechnic Normal University School of Computer Science Guangzhou China

ISBN: (纸本)9798350371499

EEG reveals human brain activities for emotion and becomes an important aspect of affective computing. In this study, we developed a novel approach, namely DAM-GAT, which incorporated a dual-branch attention module (DAM) into a graph attention network (GAT) for EEG-based emotion recognition. This method used the GAT to capture the local features of emotional EEG signals. To enhance the important EEG features for emotion recognition, the proposed method also included a DAM that calculated weights considering both channel and frequency information. Additionally, the relationship between EEG channels was determined using the phase-locking value (PLV) connectivity of corresponding EEG signals. Based on the SEED datasets, the proposed approach provided an accuracy of up to 94.63% for emotion recognition, demonstrating its impressive performance compared with other existing methods. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

state and tendency: an empirical study of deep learning question&answer topics on Stack Overflow

引用

science China(Information sciences) 2021年第11期64卷 131-153页

作者： Henghui ZHAO Yanhui LI Fanwei LIU Xiaoyuan XIE Lin CHEN State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science Wuhan University

Deep learning has developed rapidly in recent years, attracting the attention of numerous researchers. Since a wide range of topics are covered in this field, we are wondering what topics researchers have concerned about. However, after investigation, we find that very few researchers have paid attention to this demand. In this paper, we conduct a large-scale study to analyze the questions faced by deep learning developers. We use Stack Overflow, one of the largest question&answer sites, as our data source, and extract32969 posts about deep learning as our studied dataset. After filtering, augmenting and pre-processing the post datasets from Stack Overflow, we use the latent Dirichlet allocation(LDA) topic model to summarize30 topics based on their text content. In addition, we measure the difficulty and popularity of each topic,compare the different issues faced by different deep learning frameworks, and analyze the development trend of each topic. Our main results are as follows:(1) developers ask a broad spectrum of questions about deep-learning, ranging from Data Shape to Object Detection;(2) Gradient Propagation is the most popular among all the topics and(3) Object Detection is the most difficult;(4) issues of Package Installation, Code Understanding and Method Introduction are common in the current different deep learning frameworks;(5) there are three trends in these topics, e.g., a significant rising trend is found in the number of discussion on Data Shape. Finally, based on our research findings, we make some targeted and valuable suggestions for developers, researchers, educators, and framework providers of deep learning.

关键词： topic model deep learning Stack Overflow question&answer

来源：评论

学校读者我要写书评

暂无评论

A novel Method for Precipitation Nowcasting Based on ST-LSTM

引用

computers, Materials & Continua 2022年第9期72卷 4867-4877页

作者： Wei Fang Liang Shen Victor S.Sheng Qiongying Xue School of Computer&Software Engineering Research Center of Digital ForensicsMinistry of EducationNanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory of Severe Weather Chinese Academy of Meteorological SciencesBeijing100081China Department of Computer Texas Tech UniversityLubbockTX79409USA

Precipitation nowcasting is of great significance for severe convective weather *** echo extrapolation is a commonly used precipitation nowcasting ***,the traditional radar echo extrapolation methods are encountered with the dilemma of low prediction accuracy and extrapolation *** reason is that those methods cannot retain important long-term information and fail to capture short-term motion information from the long-range data *** order to solve the above problems,we select the spatiotemporal long short-term memory(ST-LSTM)as the recurrent unit of the model and integrate the 3D convolution operation in it to strengthen the model’s ability to capture short-term motion information which plays a vital role in the prediction of radar echo motion *** the purpose of enhancing the model’s ability to retain long-term important information,we also introduce the channel attention mechanism to achieve this *** the experiment,the training and testing datasets are constructed using radar data of Shanghai,we compare our model with three benchmark models under the reflectance thresholds of 15 and *** results demonstrate that the proposed model outperforms the three benchmark models in radar echo extrapolation task,which obtains a higher accuracy rate and improves the clarity of the extrapolated image.

关键词： Precipitation nowcasting radar echo extrapolation ST-LSTM attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation by Fusing key Information of Text

引用

computers, Materials & Continua 2023年第2期74卷 2803-2815页

作者： Shijie Hu Xiaoyu Li Jiayu Bai Hang Lei Weizhong Qian Sunqiang Hu Cong Zhang Akpatsa Samuel Kofi Qian Qiu Yong Zhou Shan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China Science and Technology on Altitude Simulation Laboratory Sichuan Gas Turbine Establishment Aero Engine Corporation of ChinaMianyang621000China School of Power and Energy Northwestern Polytechnical UniversityXi’an710072China School of Computer Science Southwest Petroleum UniversityChengdu610500China Department of Chemistry Physics and Atmospheric SciencesJackson State UniversityJacksonMS 39217USA

When the Transformer proposed by Google in 2017,it was first used for machine translation tasks and achieved the state of the art at that *** the current neural machine translation model can generate high quality translation results,there are still mistranslations and omissions in the translation of key information of long *** the other hand,the most important part in traditional translation tasks is the translation of key *** the translation results,as long as the key information is translated accurately and completely,even if other parts of the results are translated incorrect,the final translation results’quality can still be *** order to solve the problem of mistranslation and missed translation effectively,and improve the accuracy and completeness of long sentence translation in machine translation,this paper proposes a key information fused neural machine translation model based on *** model proposed in this paper extracts the keywords of the source language text separately as the input of the *** the same encoding as the source language text,it is fused with the output of the source language text encoded by the encoder,then the key information is processed and input into the *** incorporating keyword information from the source language sentence,the model’s performance in the task of translating long sentences is very *** order to verify the effectiveness of the method of fusion of key information proposed in this paper,a series of experiments were carried out on the verification *** experimental results show that the Bilingual Evaluation Understudy(BLEU)score of the model proposed in this paper on theWorkshop on Machine Translation(WMT)2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test *** experimental results show the advantages of the model proposed in this paper.

关键词： key information transformer fusion neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Contrastive Learning with Second Order Sampling for Collaborative Filtering

Hyperbolic Contrastive Learning with Second Order Sampling f...

引用

IEEE International Conference on Web Services (ICWS)

作者： Longchuan Tu Shunmei Meng Lianyong Qi Xiaolong Xu Xuyun Zhang School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Lab. for Novel Software Technology Nanjing University China College of Computer Science and Technology China University of Petroleum(East China) China School of Computer and Software Nanjing University of Information Science and Technology China School of Computing Macquarie University Australia

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

Recently, hyperbolic spaces have proven beneficial for service recommendation due to their exponentially growing spatial properties conforming to power-law distributed user-item networks. Among them, the combination of hyperbolic space with graph convolution has achieved great success. However, hyperbolic convolutional models still perform multi-layer convolution in tangent space (Euclidean space), leading to the still inevitable problem of over-smoothing arising from multi-layer convolution. In addition, most of these models randomly draw negative samples from items that users have not interacted with, so that some of the samples obtained may not be well suited for model optimization. To tackle the above challenges, we propose a new Hyperbolic GCN model based on Contrastive Learning and Second-order Reachable sampling for collaborative filtering (HG-CLSR), which improve high quality of representations by exploring the distribution of users and items in hyperbolic space. Specifically, We first introduce a root alignment approach to encourage embeddings to align with the tangent space, thereby reducing distortions during the embedding mapping process in space. Then, we perform contrastive learning in hyperbolic space to motivate the spatial distribution of nodes to better fit the hyperbolic space. Moreover, we sample in the user’s second-order reachable item set, which ensures that the negative sample is more similar to the positive sample, so that the negative node can provide better information for guiding model optimization. Extensive experiments on three real-world datasets demonstrate that the HG-CLSR is significantly superior compared to existing hyperbolic models.

关键词： Degradation Graphical models Convolution Web services Collaborative filtering Design methodology Contrastive learning Distortion Optimization Distribution functions

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：