检索结果-内蒙古大学图书馆

Hierarchical vectorization for facial images

Computational Visual Media 2024年第1期10卷 97-118页

作者： Qian Fu Linlin Liu Fei Hou Ying He School of Computer Science and Engineering Nanyang Technological University639798SingaporeSingapore Data61 Commonwealth Scientific and Industrial Research OrganisationSydney2015Australia Interdisciplinary Graduate School Nanyang Technological University and Alibaba Group639798SingaporeSingapore State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing100190China University of Chinese Academy of Sciences Beijing100049China

The explosive growth of social media means portrait editing and retouching are in high *** portraits are commonly captured and stored as raster images,editing raster images is non-trivial and requires the user to be highly *** at developing intuitive and easy-to-use portrait editing tools,we propose a novel vectorization method that can automatically convert raster images into a 3-tier hierarchical *** base layer consists of a set of sparse diffusion curves(DCs)which characterize salient geometric features and low-frequency colors,providing a means for semantic color transfer and facial expression *** middle level encodes specular highlights and shadows as large,editable Poisson regions(PRs)and allows the user to directly adjust illumination by tuning the strength and changing the shapes of *** top level contains two types of pixel-sized PRs for high-frequency residuals and fine details such as pimples and *** train a deep generative model that can produce high-frequency residuals *** to the inherent meaning in vector primitives,editing portraits becomes easy and *** particular,our method supports color transfer,facial expression editing,highlight and shadow editing,and automatic *** quantitatively evaluate the results,we extend the commonly used FLIP metric(which measures color and feature differences between two images)to consider *** new metric,illumination-sensitive FLIP,can effectively capture salient changes in color transfer results,and is more consistent with human perception than FLIP and other quality measures for portrait *** evaluate our method on the FFHQR dataset and show it to be effective for common portrait editing tasks,such as retouching,light editing,color transfer,and expression editing.

关键词： face editing vectorization Poisson editing color transfer illumination editing expression editing

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Resource Allocation in Wireless Communication Systems 9

Deep Reinforcement Learning for Resource Allocation in Wirel...

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Vivekanand, Chettiyar Vani Talele, Gokul Jaishanthi, B. Harihara Gopalan, S. Maheswari, K. Uma Maheswari, B. Rmk College of Engineering And Technology Department of Electronics And Communication Engineering Tamil Nadu Thiruvallur601206 India Iiit Banglore Department of Data Science India Tagore Engineering College Department of Computer Science And Engineering Tamil Nadu Chennai600 127 India Sri Ramakrishna Engineering College Department of Computer Science And Engineering Tamil Nadu Coimbatore641022 India Cmr Technical Campus Department of Computer Science And Engineering Hyderabad Telangana Kandlakoya501401 India St. Joseph's College of Engineering Omr Department of Computer Science And Engineering Tamil Nadu Chennai600119 India

ISBN: (纸本)9798350365092

In wireless communication systems, deep reinforcement learning (DRL) methods are used to find the best way to use resources so that the system works at its best. When it comes to cellular networks, the old ways of doing things aren't working well enough to meet the growing need for efficient use of limited resources. The reason for this is that demand is rising very quickly. With this , the authors hope to come up with a new way to use DRL's features to distribute resources in real-time based on how the network is performing. That's what thisis all about. Also, deep neural networks are built into the system. This lets it learn how to adapt and improve strategies for allocating resources, which eventually makes the system work better overall. For the purpose of finding out if DRL is both possible and useful in handling the difficulties that come with wireless contact, this is being done. Changing traffic loads, the state of the route, and the needs of the users are just a few of the other things that are taken into account. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Assessing a Personalized, Hybrid, and Generic Approach for Glucose Prediction in Type 1 Diabetes

Assessing a Personalized, Hybrid, and Generic Approach for G...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Bosoni, Pietro Jensen, Morten Hasselstrom Bellazzi, Riccardo Cichosz, Simon Lebech University of Pavia Department of Electrical Computer and Biomedical Engineering Pavia Italy Aalborg University Data Science Department of Health Science and Technology Aalborg Denmark Aalborg University Department of Health Science and Technology Aalborg Denmark

ISBN: (纸本)9798350386226

This study investigates the potential of using generic, hybrid, and personalized neural network models for glucose prediction in individuals with Type 1 Diabetes (T1D). data from 194 participants in the Wireless Innovations for Seniors with Diabetes Mellitus (WISDM) study, totaling over 46 million minutes of Continuous Glucose Monitoring (CGM), were used to develop and evaluate the models. A baseline reference model, Last Observation Carried Forward (LOCF), was also included for comparison. Models were trained using data from 70% of the participants and tested on the remaining 30%, with prediction horizons (PH) set at 30 and 60 minutes. At the 30-minute PH, the generic model achieved a Root Mean Square Error (RMSE) of 19.6 mg/dL and a Mean Absolute Relative Difference (MARD) of 9.2%. These results were slightly worse than those of the hybrid and personalized models, which yielded RMSEs of 19.4 mg/dL and 19.5 mg/dL, respectively, and MARDs of 9.6% for both. However, the differences were not statistically significant. At the 60-minute PH, the generic model showed the best performance, with an RMSE of 34.9 mg/dL and MARD of 16.2%. The hybrid and personalized models exhibited slightly higher RMSEs (35.3 mg/dL and 35.5 mg/dL, respectively) and MARDs (17.8% and 18.1%, respectively). These findings suggest that both generic and individualized models can provide satisfactory glucose forecasting results based solely on CGM data. Nonetheless, the potential benefits of individualized approaches deserve further investigation, particularly when substantial training data are available. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

DivLog: Log Parsing with Prompt Enhanced In-Context Learning 24

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

引用

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Xu, Junjielong Yang, Ruichun Huo, Yintong Zhang, Chengyu He, Pinjia The Chinese University of Hong Kong Dept. of Computer Science & Engineering Hong Kong Eth Zurich Switzerland School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China

ISBN: (纸本)9798400702174

Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing super-vised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose Di-vLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

HyCoT: A Transformer-Based Autoencoder for Hyperspectral Image Compression 14

HyCoT: A Transformer-Based Autoencoder for Hyperspectral Ima...

引用

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Fuchs, Martin Hermann Paul Rasti, Behnood Demir, Begum Technische Universität Faculty of Electrical Engineering and Computer Science Berlin Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany

ISBN: (纸本)9798331513139

The development of learning-based hyperspectral image (HSI) compression models has recently attracted significant interest. Existing models predominantly utilize convolutional filters, which capture only local dependencies. Furthermore, they often incur high training costs and exhibit substantial computational complexity. To address these limitations, in this paper we propose Hyperspectral Compression Trans-former (HyCoT) that is a transformer-based autoencoder for pixelwise HSI compression. Additionally, we apply a simple yet effective training set reduction approach to accelerate the training process. Experimental results on the HySpecNet-11k dataset demonstrate that HyCoT surpasses the state of the art across various compression ratios by over 1 dB of PSNR with significantly reduced computational require-ments. Our code and pre-trained weights are publicly avail-able at https://***/rsim/hycot. © 2024 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

OFDM with Generalized Cascade Index Modulation for Secure Communications

引用

China Communications 2024年第10期21卷 210-225页

作者： Hu Zeng Jin Xiaopin Yao Yudong Chen Fangjiong Wan Dehuan Liu Yun College of Information Science and Technology Zhongkai University of Agriculture and EngineeringGuangzhou 510225China College of Information Engineering China Jiliang UniversityHangzhou 310018China Department Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ 07030USA School of Electronic and Information Engineering South China University of TechnologyGuangzhou 510641China Center for Data Science and Artificial Intelligence Guangdong University of FinanceGuangzhou 510521China

Cascade index modulation(CIM) is a recently proposed improvement of orthogonal frequency division multiplexing with index modulation(OFDM-IM) and achieves better error *** CIM, at least two different IM operations construct a super IM operation or achieve new functionality. First, we propose a OFDM with generalized CIM(OFDM-GCIM) scheme to achieve a joint IM of subcarrier selection and multiple-mode(MM)permutations by using a multilevel digital ***, two schemes, called double CIM(D-CIM) and multiple-layer CIM(M-CIM), are proposed for secure communication, which combine new IM operation for disrupting the original order of bits and symbols with conventional OFDM-IM, to protect the legitimate users from eavesdropping in the wireless communications. A subcarrier-wise maximum likelihood(ML) detector and a low complexity log-likelihood ratio(LLR) detector are proposed for the legitimate users. A tight upper bound on the bit error rate(BER) of the proposed OFDM-GCIM, D-CIM and MCIM at the legitimate users are derived in closed form by employing the ML criteria detection. computer simulations and numerical results show that the proposed OFDM-GCIM achieves superior error performance than OFDM-IM, and the error performance at the eavesdroppers demonstrates the security of D-CIM and M-CIM.

关键词： cascade index modulation low-complexity detector maximum likelihood OFDM physical layer security

来源：评论

学校读者我要写书评

暂无评论

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining 42

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pi...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shi, Shaohuai Pan, Xinglin Chu, Xiaowen Li, Bo Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Hong Kong Baptist University Department of Computer Science Hong Kong Data Science and Analytics Thrust Hong Kong The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Large models have attracted much attention in the AI area. The sparsely activated mixture-of-experts (MoE) technique pushes the model size to a trillion-level with a sub-linear increase of computations as an MoE layer can be equipped with many separate experts, but only one or two experts need to be trained for each input data. However, the feature of dynamically activating experts of MoE introduces extensive communications in distributed training. In this work, we propose PipeMoE to adaptively pipeline the communications and computations in MoE to maximally hide the communication time. Specifically, we first identify the root reason why a higher pipeline degree does not always achieve better performance in training MoE models. Then we formulate an optimization problem that aims to minimize the training iteration time. To solve this problem, we build performance models for computation and communication tasks in MoE and develop an optimal solution to determine the pipeline degree such that the iteration time is minimal. We conduct extensive experiments with 174 typical MoE layers and two real-world NLP models on a 64-GPU cluster. Experimental results show that our PipeMoE almost always chooses the best pipeline degree and outperforms state-of-the-art MoE training systems by 5%-77% in training time. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

data-Augmented Few-Shot Object Detection for Efficient Identification of Invasive Weed Seedlings 1

Data-Augmented Few-Shot Object Detection for Efficient Ident...

引用

1st IEEE International Conference on Advances in data-Driven Analytics and Intelligent Systems, ADACIS 2023

作者： Alli, Smaran Baidya, Sabur Carnegie Mellon University Department of Data Science PA United States University of Louisville Department of Computer Science and Engineering KY United States

ISBN: (纸本)9798350344158

Invasive weeds have continued to ravage crops across the world and with their population starkly rising, intelligent technologies need to be incorporated to mitigate the spread of these weeds. This research aims at employing Deep Learning models on invasive weed seedlings images in order to be able to detect them in images before they have grown. Due to the lack of images available on weed seedlings, more images were collected of weed seedlings, which were then combined with the limited available pre-existing images found in the Aarhus dataset. However, due to the dataset being still comparably small, a Few-Shot Object Detector (FSOD) is employed for better object detection performance. This FSOD was created through transfer learning with the universal COCO dataset. We also investigate data augmentation techniques by varying different attributes of images. We compare our proposed data-augmented FSOD with a 16-layer CNN-based object detector and also with the models without any augmentation. With experimental results, we show that the FSOD model achieves a higher mean Average Precision (mAP50) than the 16-layer CNN for both augmented (0.839 to 0.834) and non-augmented data (0.814 to 0.808). The FSOD detector also runs faster than the CNN model, and thus can be useful in real-time autonomous detection of the weed seedling and hence, in mitigating spreading of these invasive weeds. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

mVulPreter: A Multi-Granularity Vulnerability Detection System With Interpretations

引用

IEEE Transactions on Dependable and Secure Computing 2022年 1-12页

作者： Zou, Deqing Hu, Yutao Li, Wenke Wu, Yueming Zhao, Haojun Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Computer Science and Engineering Nanyang Technological University Singapore National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Due to the powerful automatic feature extraction, deep learning-based vulnerability detection methods have evolved significantly in recent years. However, almost all current work focuses on detecting vulnerabilities at a single granularity (i.e., slice-level or function-level). In practice, slice-level vulnerability detection is fine-grained but may contain incomplete vulnerability details. Function-level vulnerability detection includes full vulnerability semantics but may contain vulnerability-unrelated statements. Meanwhile, they pay more attention to predicting whether the source code is vulnerable and cannot pinpoint which statements are more likely to be vulnerable. In this paper, we design mVulPreter, a multi-granularity vulnerability detector that can provide interpretations of detection results. Specifically, we propose a novel technique to effectively blend the advantages of function-level and slice-level vulnerability detection models and output the detection results' interpretation only by the model itself. We evaluate mVulPreter on a dataset containing 5,310 vulnerable functions and 7,601 non-vulnerable functions. The experimental results indicate that mVulPreter outperforms existing state-of-the-art vulnerability detection approaches (i.e., Checkmarx, FlawFinder, RATS, TokenCNN, StatementLSTM, SySeVR, and Devign). IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Plausible Heterogeneous Graph k-Anonymization for Social Networks

引用

Tsinghua science and Technology 2022年第6期27卷 912-924页

作者： Kaiyang Li Ling Tian Xu Zheng Bei Hui School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu 610000China

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector *** embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data *** social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual’s privacy and ***,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social *** be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network *** this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph *** experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

关键词： social network graph embedding privacy preservation adversarial learning

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：