检索结果-内蒙古大学图书馆

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Li, Fangfang Shan, Youran Duan, Junwen Mao, Xingliang Huang, MinLie School of Computer Science and Engineering Central South University China Institute of Big Data and Internet Innovation Hunan University of Technology and Business China Beijing National Research Center for Information Science and Technology Tsinghua University China

Chinese spelling check (CSC) detects and corrects spelling errors in Chinese texts. Previous approaches have combined character-level phonetic and graphic information, ignoring the importance of segment-level information. According to our pilot study, spelling errors are always associated with incorrect word segmentation. When appropriate word boundaries are provided, CSC performance is greatly enhanced. Based on these findings, we present WSpeller, a CSC model that takes into account word segmentation. A fundamental component of WSpeller is a W-MLM, which is trained by predicting visually and phonetically similar words. Through modification of the embedding layer's input, word segmentation information can be incorporated. Additionally, a robust module is trained to assist the W-MLM-based correction module by predicting the correct word segmentations from sentences containing spelling errors. We evaluate WSpeller on the widely used benchmark datasets SIGHAN13, SIGHAN14, and SIGHAN15. Our model is superior to state-of-the-art baselines on SIGHAN13 and SIGHAN15 and maintains equal performance on SIGHAN14. © 2022 Association for Computational Linguistics.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-magnetic resonance imaging system:In the era of 6G and artificial intelligence

引用

Magnetic Resonance Letters 2025年第1期5卷 52-63页

作者： Yirong Zhou Yanhuang Wu Yuhan Su Jing Li Jianyu Cai Yongfu You Jianjun Zhou Di Guo Xiaobo Qu Department of Electronic Science Intelligent Medical Imaging R&D CenterFujian Provincial Key Laboratory of Plasma and Magnetic ResonanceNational Institute for Data Science in Health and MedicineXiamen UniversityXiamen361104China Department of Electronic Science Key Laboratory of Digital Fujian on IoT CommunicationXiamen UniversityXiamen361104China Shanghai Electric Group Co. LtdShanghai200002China China Telecom Group Quanzhou362018China China Mobile Group Xiamen361009China Department of Radiology Zhongshan Hospital(Xiamen)Fudan UniversityXiamen Municipal Clinical Research Center for Medical ImagingFujian Province Key Clinical Specialty Construction Project(Medical Imaging Department)Xiamen Key Laboratory of Clinical Transformation of Imaging Big Data and Artificial IntelligenceXiamen361006China School of Computer and Information Engineering Xiamen University of TechnologyXiamen361024China

Magnetic resonance imaging(MRI)plays an important role in medical diagnosis,generating petabytes of image data annually in large *** voluminous data stream requires a significant amount of network bandwidth and extensive storage ***,local data processing demands substantial manpower and hardware *** isolation across different healthcare institutions hinders crossinstitutional collaboration in clinics and *** this work,we anticipate an innovative MRI system and its four generations that integrate emerging distributed cloud computing,6G bandwidth,edge computing,federated learning,and blockchain *** system is called Cloud-MRI,aiming at solving the problems of MRI data storage security,transmission speed,artificial intelligence(AI)algorithm maintenance,hardware upgrading,and collaborative *** workflow commences with the transformation of k-space raw data into the standardized Imaging Society for Magnetic Resonance in Medicine Raw data(ISMRMRD)***,the data are uploaded to the cloud or edge nodes for fast image reconstruction,neural network training,and automatic ***,the outcomes are seamlessly transmitted to clinics or research institutes for diagnosis and other *** Cloud-MRI system will save the raw imaging data,reduce the risk of data loss,facilitate inter-institutional medical collaboration,and finally improve diagnostic accuracy and work efficiency.

关键词： Magnetic resonance imaging Cloud computing 6G bandwidth Artificial intelligence Edge computing Federated learning Blockchain

来源：评论

学校读者我要写书评

暂无评论

Image Denoising Method Based on Channel Compression and Split-Attention Mechanism

Image Denoising Method Based on Channel Compression and Spli...

引用

Computer engineering and intelligent Control (ICCEIC) International Conference on

作者： Hao Sun Xiaoyan Qiao Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion School of Computer Science and Technology Shandong Technology and Business University Technology and Evaluation Shandong Engineering Research Center Yantai Shandong

ISBN: (数字)9798331507992

ISBN: (纸本)9798331508005

In the image restoration task, how to make full use of spatial and channel feature information to improve the reconstruction quality of the model without significantly increasing the computational complexity is an important research issue. To address this challenge, this paper proposes a CS module (Channel Compression and Split-Attention) specifically for optimizing image denoising tasks. The module first compresses the features through a preliminary convolution operation, then introduces the split attention convolution mechanism to split the features by channel and dynamically weight them, thereby enhancing the model's adaptive attention to different feature channels and improving feature expression capabilities. Through experiments on multiple image denoising datasets, the results show that the CS module significantly improves the image reconstruction quality, especially in terms of peak signal-to-noise ratio (PSNR). At the same time, the introduction of the CS module does not lead to a significant increase in computational complexity, maintaining a high computational efficiency, which verifies the practicality and superiority of the module in image denoising tasks.

关键词： Image coding PSNR Convolution Computational modeling Refining Image restoration Computational efficiency Computational complexity Image reconstruction Image denoising

来源：评论

学校读者我要写书评

暂无评论

Intensity Confusion Matters: An Intensity-Distance Guided Loss For Bronchus Segmentation

Intensity Confusion Matters: An Intensity-Distance Guided Lo...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Haifan Gong Wenhao Huang Huan Zhang Yu Wang Xiang Wan Hong Shen Guanbin Li Haofeng Li Shenzhen Research Institute of Big Data China School of Science and Engineering The Chinese University of Hong Kong (Shenzhen) China InferVision China School of Computer Science and Engineering Sun Yat-sen University China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Automatic segmentation of the bronchial tree from CT imaging is important, as it provides structural information for disease diagnosis. Despite the merits of previous automatic bronchus segmentation methods, they have paied less attention to the issue we term as Intensity Confusion, wherein the intensity values of certain background voxels approach those of the foreground voxels within bronchi. Conversely, the intensity values of some foreground voxels are nearly identical to those of background voxels. This proximity in intensity values introduces significant challenges to neural network methodologies. To address the issue, we introduce a novel Intensity-Distance Guided loss function, which assigns adaptive weights to different image voxels for mining hard samples that cause the intensity confusion. The proposed loss estimates the voxel-level hardness of samples, on the basis of the following intensity and distance priors. We regard a voxel as a hard sample if it is in: (1) the background and has an intensity value close to the bronchus region; (2) the bronchus region and is of higher intensity than most voxels inside the bronchus; (3) the background region and at a short distance from the bronchus. Extensive experiments not only show the superiority of our method compared with the state-of-the-art methods, but also verify that tackling the intensity confusion issue helps to significantly improve bronchus segmentation. Project page: https://***/lhaof/ICM.

关键词： Image segmentation Image resolution Accuracy Computed tomography Neural networks Focusing Benchmark testing

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

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

引用

International Conference on Software engineering (ICSE)

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

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

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.

关键词： Training Measurement Analytical models Semantics Feature extraction Tuning Software engineering

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Application of Convolutional Neural Network in Livestock Target Detection of IoT Images

Application of Convolutional Neural Network in Livestock Tar...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Maohong Tian Feiyang Zhao Nengmei Chen Dequan Zhang Jie Li Hualin Li School of Big Data and Artificial Intelligence Chongqing Institute of Engineering Shu Yi Xin Credit Management Co. LTD Chongqing China School of Big Data and Artificial Intelligence Chongqing Institute of Engineering Intelligent Application of Financial Big Data Chongqing Colleges and Universities Engineering Research Center Chongqing China Chongqing Da Tong Experimental School Chongqing China Shu Yi Xin Credit Management Co. LTD Chongqing China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

The national rural revitalization strategy has advanced, and new requirements for modern internet-of-things (IoT)-based farm supervision tools have been proposed. This study proposes a “you-only-look-once” (YOLO) v5 convolutional neural network to optimize the candidate frame's center point algorithm. Five YOLOv5 models are used to identify and classify captive pigs. According to the experimental results, the K-median algorithm has a better effect than using the K-means algorithm, and its average intersection over union is approximately 1-2% higher. In our scenario, the commercial application value of the YOLOv5s model is higher, and the corresponding performance results of F1-score, mAP0.5, mAP0.5:0.95, FPS, and R 2 are 92.21%, 95.18%, 64.85%, 75 FPS, and 85.54%, respectively.

关键词： YOLO Seminars Image recognition Target recognition Approximation algorithms Agriculture Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Prediction of sepsis within 24 hours at the triage stage in emergency departments using machine learning

引用

World Journal of Emergency Medicine 2024年第5期15卷 379-385页

作者： Jingyuan Xie Jiandong Gao Mutian Yang Ting Zhang Yecheng Liu Yutong Chen Zetong Liu Qimin Mei Zhimao Li Huadong Zhu Ji Wu Department of Electronic Engineering Tsinghua UniversityBeijing 100084China Center for Big Data and Clinical Research Institute for Precision MedicineTsinghua UniversityBeijing 100084China Institute of Medical Technology Peking University Health Science CenterBeijing 100091China Emergency Department State Key Laboratory of Complex Severe and Rare DiseasesPeking Union Medical College HospitalChinese Academy of Medical Science and Peking Union Medical CollegeBeijing 100005China Department of Health Care Peking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100005China

BACKGROUND:Sepsis is one of the main causes of mortality in intensive care units(ICUs).Early prediction is critical for reducing *** approximately 36%of sepsis occur within 24 h after emergency department(ED)admission in Medical Information Mart for Intensive Care(MIMIC-IV),a prediction system for the ED triage stage would be *** methods such as the quick Sequential Organ Failure Assessment(qSOFA)are more suitable for screening than for prediction in the ED,and we aimed to fi nd a light-weight,convenient prediction method through machine ***:We accessed the MIMIC-IV for sepsis patient data in the *** dataset comprised demographic information,vital signs,and synthetic *** Gradient Boosting(XGBoost)was used to predict the risk of developing sepsis within 24 h after ED ***,SHapley Additive exPlanations(SHAP)was employed to provide a comprehensive interpretation of the model's *** percent of the patients were randomly selected as the testing set,while the remaining patients were used for training with 10-fold ***:For 10-fold cross-validation on 14,957 samples,we reached an accuracy of 84.1%±0.3%and an area under the receiver operating characteristic(ROC)curve of 0.92±*** model achieved similar performance on the testing set of 1,662 *** values showed that the fi ve most important features were acuity,arrival transportation,age,shock index,and respiratory ***:Machine learning models such as XGBoost may be used for sepsis prediction using only a small amount of data conveniently collected in the ED triage *** may help reduce workload in the ED and warn medical workers against the risk of sepsis in advance.

关键词： Sepsis Machine learning Emergency department Triage Informatics

来源：评论

学校读者我要写书评

暂无评论

Formal Specification and Verification of API Security Based on Design by Contract

Formal Specification and Verification of API Security Based ...

引用

IEEE International Conference on Power, intelligent Computing and Systems (ICPICS)

作者： Qing Tang Zetong Zhou Zhaoxiong Bu Li Ma Yong Zhong Guangdong Chankong Big Data Technology Co. Ltd. Foshan China School of Management Guangdong University of Technology Foshan China School of Electronic and Information Engineering Foshan University Foshan China School of Electronic and Information Engineering Foshan University Zhixin Urban Big Data Technology Research Institute Foshan China Foshan Data Science Association School of Electronic and Information Engineering Foshan University Zhixin Urban Big Data Technology Research Institute Foshan China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

The exploitation and hijacking of API vulnerabilities are becoming increasingly prominent issues in software supply chain security. This paper proposes an Object-Z based formal verification method for APIs in the supply chain, aiming to address the security risks associated with API applications. By incorporating the concept of design by contract and using Object-Z for formal modeling, a dynamic defense against API threats is implemented. Finally, based on a classification analysis of API threats in the supply chain, this paper presents a ase study through modeling and application analysis.

关键词： Analytical models Computational modeling Supply chains Software Security Formal specifications Contracts Formal verification

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：