检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Du, Yong Zhan, Jiahui Li, Xinzhe Dong, Junyu Chen, Sheng Yang, Ming-Hsuan He, Shengfeng The School of Computer Science and Technology Ocean University of China Qingdao China The School of Computer Science and Technology Ocean University of China Shanghai Jiao Tong University China The School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom The University of California at Merced United States Yonsei University Korea Republic of Google United States The School of Computing and Information Systems Singapore Management University Singapore

In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and significant visual differences. The main idea behind our approach is leveraging the domain-neutral capabilities of CLIP as a bridging mechanism, while utilizing a separate module to extract abstract, domain-agnostic semantics from the embeddings of both the source and target realms. Fusing these abstract semantics with target-specific semantics results in a transformed embedding within the CLIP space. To bridge the gap between the disparate worlds of CLIP and StyleGAN, we introduce a new non-linear mapper, the CLIP2P mapper. Utilizing CLIP embeddings, this module is tailored to approximate the latent distribution in the StyleGAN’s latent space, effectively acting as a connector between these two spaces. The proposed UniTranslator is versatile and capable of performing various tasks, including style mixing, stylization, and translations, even in visually challenging scenarios across different visual domains. Notably, UniTranslator generates high-quality translations that showcase domain relevance, diversity, and improved image quality. UniTranslator surpasses the performance of existing general-purpose models and performs well against specialized models in representative tasks. The source code and trained models will be released to the public. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Performability analysis of FOGGIS model for geospatial web services 11

Performability analysis of FOGGIS model for geospatial web s...

引用

11th International Conference on Cloud computing, Data science and Engineering, Confluence 2021

作者： Panigrahi, Símil K. Barik, Rabindra Kumar Behera, Satyaban Barik, Lalbihari Patra, Sudhansu Shekhar School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Department of Information Science Electronics and Telecommunications G.M. University Sambalpur India Department of Information Systems Faculty of Computing and Information Technology Rabigh King Abdulaziz University Saudi Arabia School of Computer Applications KIIT Deemed to be University Bhubaneswar India

ISBN: (纸本)9780738131603

The Internet of Spatial Things (IoST), continuously generates a large volume of geospatial data from a large number of connected smart devices. Cloud computing is inefficient to respond to IoST because of latency concern. Fog computing allows geospatial data processing as well as geospatial storage close to IoST devices and addresses this concern. This fog computing-based GIS model i.e. FogGIS is assisting to the cloud for invoking various geospatial web services. In many scenarios the service requests arrive to the fog layer and waits in a queue due to the current workload of fog servers. When all the Virtual Machines (VMs) are congested (busy), the arrived tasks are queued in the fog buffer until the fog servers becomes available to process the service. This creates the possibilities of task reneging or dropping. Reneged or dropped tasks could be resubmitted if the tasks were not dropped due to security reasons. In this paper, it experiments the performance of the fog layer based on the task arrival and the buffer size of the system using M/M/c/N Queuing theory. It also offers numerical illustrations to demonstrate the application of task reneging and feedback on the parameters such as queuing delay, probability of immediate service as well as probability of task rejection. © 2021 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Disentangled Multimodal Representation Learning for Recommendation

arXiv

引用

arXiv 2022年

作者： Liu, Fan Chen, Huilin Cheng, Zhiyong Liu, Anan Nie, Liqiang Kankanhalli, Mohan School of Computing National University of Singapore Singapore The School of Computer Science and Engineering Tianjin University of Technology China The Shandong Artificial Intelligence Institute Qilu University of Technology Shandong Academy of Sciences China The School of Electrical and Information Engineering Tianjin University China Harbin Institute of Technology Shenzhen China

Many multimodal recommender systems have been proposed to exploit the rich side information associated with users or items (e.g., user reviews and item images) for learning better user and item representations to improve the recommendation performance. Studies from psychology show that users have individual differences in the utilization of various modalities for organizing information. Therefore, for a certain factor of an item (such as appearance or quality), the features of different modalities are of varying importance to a user. However, existing methods ignore the fact that different modalities contribute differently towards a user's preference on various factors of an item. In light of this, in this paper, we propose a novel Disentangled Multimodal Representation Learning (DMRL) recommendation model, which can capture users' attention to different modalities on each factor in user preference modeling. In particular, we employ a disentangled representation technique to ensure the features of different factors in each modality are independent of each other. A multimodal attention mechanism is then designed to capture users' modality preference for each factor. Based on the estimated weights obtained by the attention mechanism, we make recommendations by combining the preference scores of a user's preferences to each factor of the target item over different modalities. Extensive evaluation on five real-world datasets demonstrate the superiority of our method compared with existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Interpretation Based on Deep Learning and Speech Synthesis

Simultaneous Interpretation Based on Deep Learning and Speec...

引用

Frontiers technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Wenzhuo Geng Hong Wang Yanqi Nie Xian Zou Hanlin Yang Teoh Teik Toe Faculty of Computing Harbin Institute of Technology Harbin China School of Information Science and Engineering Harbin Institute of Technology Harbin China School of Computer Central China Normal University Wuhan China ITOM/NBS Nanyang Technological University Singapore

Simultaneous interpretation is a scarce skill which has only been performed by well-trained interpreters so far. The fast development and wide application of artificial intelligence stimulate us to think about its computer implementation. In this paper, we design and implement a system, in which original speech can be converted into translated speech through three steps: speech recognition, text translation and speech synthesis. We apply the newly-developed HiFi-GAN vocoder for speech synthesis, which provides a faster speed and better quality than previous vocoders. And we add the speaker's voice elements as a factor in the synthesis to make the synthesized speech much similar to the original speaker. As is demonstrated by an English to Chinese speech interpretation experiment, our purposed system outperforms a currently widely-used translation system, showing an exciting prospect for computer implementation of simultaneous interpretation.

关键词： Deep learning Technological innovation Costs Vocoders Web and internet services Hidden Markov models Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Hybrid BiGRU-CNN Model for Load Forecasting in Smart Grids with High Renewable Energy Integration

引用

IET Generation, Transmission and Distribution 2025年第1期19卷

作者： Ullah, Kaleem Shakir, Daniyal Abid, Usama Alahmari, Saad Aslam, Sheraz Ullah, Zahid US-Pakistan Centre for Advanced Studies in Energy University of Engineering and Technology Peshawar Peshawar Pakistan Sr. Business Analyst S&P Global Islamabad Islamabad Pakistan Department of Computer Science and Information Technology School of Computing Engineering and Mathematical Sciences La Trobe University MelbourneVIC Australia Department of Computer Science Applied College Northern Border University Arar Saudi Arabia Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus Department of Computer Science CTL eurocolege Limassol Cyprus Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano Lombardia Italy

Integrating renewable energy sources into smart grids increases supply and demand management because renewable energy sources are intermittent and variable. To overcome this type of challenge, short-term load forecasting (STLF) is essential for managing energy, demand-side flexibility, and the stability of smart grids with renewable energy integration. This paper presents a new model called BiGRU-CNN to improve the operation of STLF in smart grids. The BiGRU-CNN model integrates bidirectional gated recurrent units (BiGRUs) to model temporal dependencies and convolutional neural networks (CNNs) to extract spatial patterns from energy consumption data. The newly developed BiGRU captures past and future contexts through bidirectional processing, and the CNN component extracts high-level features to enhance the accuracy of load demand prediction. The BiGRU-CNN model is compared with two other hybrid models, CNN-LSTM and CNN-GRU, on real-world data from American electric power (AEP) and ISONE datasets. Simulation results show that the proposed BiGRU-CNN outperforms other models, with single-step forecasting yielding root mean square error (RMSE) of 121.43 (AEP) and 123.57 (ISONE), mean absolute error (MAE) of 90.95 (AEP) and 62.97 (ISONE), and mean absolute percentage error (MAPE) of 0.61% (AEP) and 0.41% (ISONE). For multi-step forecasting, the model yields RMSE of 680.02 (AEP) and 581.12 (ISONE), MAE of 481.12 (AEP) and 411.20 (ISONE), and MAPE of 3.27% (AEP) and 2.91% (ISONE). The results show that the BiGRU-CNN model can generate accurate and reliable STLF, which is useful in managing massive renewable energy-integrated smart grids. © 2025 The Author(s). IET Generation, Transmission & Distribution published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and technology.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Crane Cloud: a resilient multi-cloud service layer for resource constrained settings

Research Square

引用

Research Square 2021年

作者： Bainomugisha, Engineer Mwotil, Alex Department of Computer Science School of Computing and Informatics Technology College of Computing and Information Sciences Makerere University Kampala Uganda

Whereas the main cloud providers have set up cloud services on stable infrastructure, developers and users situated in low-resource settings access cloud services and platforms using low-end computing devices that often connect to the Internet via slow mobile connections. These settings require custom software abstraction layers that consider such bandwidth constraints and intermittent connections as a rule rather than the exception. In this paper, we identify key challenges for developing for and accessing cloud services in resource constrained settings, namely, (1) Frequent Internet partitions and bandwidth constraints, (2) Data jurisdiction restrictions, (3) Vendor lock-in, and (4) Poor quality of service. To address these challenges, we propose a set of design considerations and properties for a resilient multi-cloud service layer, that includes: (1) Containerisation and orchestration of applications, (2) Service scheduling and replication, (3) Portability and multi-cloud migration, (4) Resilience to network partitions and bandwidth constraints, (5) Automated service discovery and load balancing, (6) Localised image registry, and (7) Support for platform monitoring and management. We present a prototype validation case study, Crane Cloud, an open source multi-cloud service abstraction layer built on-top of Kubernetes that is designed with inherent support for resilience to network partitions, microservice orchestration (deployment, scaling and management of containerized applications)a localized image registry, support for migration of services between private and public clouds to avoid vendor lock-in issues and platform monitoring. We evaluate the performance and user experience of Crane Cloud by implementing and deploying a computational and bandwidth intensive machine learning system shows lower response time compared when hosted on other public clouds. © 2021, CC BY.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

VFedMH: Vertical Federated Learning for Training Multiple Heterogeneous Models

arXiv

引用

arXiv 2023年

作者： Wang, Shuo Gai, Keke Yu, Jing Zhu, Liehuang Choo, Kim-Kwang Raymond Xiao, Bin School of Cyberspace Science and Technology Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing Zhejiang China Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Information Systems and Cyber Security University of Texas at San Antonio San AntonioTX78249 United States Department of Computing The Hong Kong Polytechnic University Hong Kong

Vertical federated learning (VFL) has garnered significant attention as it allows clients to train machine learning models collaboratively without sharing local data, which protects the client's local private data. However, existing VFL methods face challenges when dealing with heterogeneous local models among participants, which affects optimization convergence and generalization. To address this challenge, this paper proposes a novel approach called Vertical federated learning for training multiple Heterogeneous models (VFedMH). VFedMH focuses on aggregating the local embeddings of each participant's knowledge during forward propagation. To protect the participants' local embedding values, we propose an embedding protection method based on lightweight blinding factors. In particular, participants obtain local embedding using local heterogeneous models. Then the passive party, who owns only features of the sample, injects the blinding factor into the local embedding and sends it to the active party. The active party aggregates local embeddings to obtain global knowledge embeddings and sends them to passive parties. The passive parties then utilize the global embeddings to propagate forward on their local heterogeneous networks. However, the passive party does not own the sample labels, so the local model gradient cannot be calculated locally. To overcome this limitation, the active party assists the passive party in computing its local heterogeneous model gradients. Then, each participant trains their local model using the heterogeneous model gradients. The objective is to minimize the loss value of their respective local heterogeneous models. Additionally, the paper provides a theoretical analysis of VFedMH's convergence performance and privacy analysis. Extensive experiments are conducted to demonstrate that VFedMH can simultaneously train multiple heterogeneous models with heterogeneous optimization and outperform some recent methods in model performance. Copyri

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection

arXiv

引用

arXiv 2023年

作者： He, Junwei Xu, Qianqian Jiang, Yangbangyan Wang, Zitai Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the Anomaly Overfitting and Homophily Trap problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate Anomaly Overfitting. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Stable Attribute Group Editing for Reliable Few-shot Image Generation

arXiv

引用

arXiv 2023年

作者： Ding, Guanqi Han, Xinzhe Wang, Shuhui Wu, Shuzhe Jin, Xin Tu, Dandan Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China Huawei Cloud EI Innovation Lab China

Few-shot image generation aims to generate data of an unseen category based on only a few samples. Apart from basic content generation, a bunch of downstream applications hopefully benefit from this task, such as low-data detection and few-shot classification. To achieve this goal, the generated images should guarantee category retention for classification beyond the visual quality and diversity. In our preliminary work, we present an "editing-based" framework Attribute Group Editing (AGE) for reliable few-shot image generation, which largely improves the performance compared with existing methods that require re-training a GAN with limited data. Nevertheless, AGE's performance on downstream classification is not as satisfactory as expected. This paper investigates the class inconsistency problem and proposes Stable Attribute Group Editing (SAGE) for more stable class-relevant image generation. Different from AGE which directly edits from a one-shot image, SAGE takes use of all given few-shot images and estimates a class center embedding based on the category-relevant attribute dictionary. Meanwhile, according to the projection weights on the category-relevant attribute dictionary, we can select category-irrelevant attributes from the similar seen categories. Consequently, SAGE injects the whole distribution of the novel class into StyleGAN's latent space, thus largely remains the category retention and stability of the generated images. Going one step further, we find that class inconsistency is a common problem in GAN-generated images for downstream classification. Even though the generated images look photo-realistic and requires no category-relevant editing, they are usually of limited help for downstream classification. We systematically discuss this issue from both the generative model and classification model perspectives, and propose to boost the downstream classification performance of SAGE by enhancing the pixel and frequency components. Extensive experime

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Spatial-Temporal Representation Method for EEG Emotion Recognition

An Efficient Spatial-Temporal Representation Method for EEG ...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Weining Weng Yang Gu Yiqiang Chen Guoqiang Wang Nianfeng Shi Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China The Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China School of Computer and Information Engineering Luoyang Institute of Science and Technology Luoyang China

Affective computing based on electroencephalogram (EEG) has been widely studied due to the high correlation between the brain and emotions. Neurological research shows that emotions are generated by the interaction of neural circuits separated in different brain regions. Recently, many deep learning methods have been demonstrated to recognize different emotions. However, these methods extract features at the data level, ignoring the brain’s neural mechanisms of emotion generation, which may result in the features’ weak ability to express emotion. To solve this problem and extract more discriminant features according to the neural mechanism of emotion generation, this article proposes an attention based spatial-temporal representation method (ASTR) for emotion recognition. The ASTR method constructs spatial-temporal representations of emotion from neural circuits’ activity in different brain regions. In the model, the cascade attention quantifies the multi-granularity correlation and information exchange pattern between brain regions as the spatial features, which measure neural circuits’ activation and information interaction in different brain regions. The one-way transformer introduces temporal order in spatial features, calculates temporal variation features from the long-term activity of neural circuits and generates the emotion representation. The representation incorporates spatial-temporal features of neural circuits’ activity during emotion generation, which is highly related to emotion. We conducted experiments on SEED and DEAP datasets. The experimental results show that the emotion recognition accuracy of our model is about 3.0% higher than that of the SOTA algorithms, reaching more than 98%. The results also visualize the emotion generation process, revealing how the brain works under different emotions.

关键词：

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：