检索结果-内蒙古大学图书馆

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

作者： Shoutao Guo Shaolei Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences Beijing China

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the model predicts target tokens based on partial source tokens. However, the prefix2prefix training diminishes the ability of the model to capture global information and introduces forced predictions due to the absence of essential source information. Consequently, it is crucial to bridge the gap between the prefix2prefix training and seq2seq training to enhance the translation capability of the SiMT model. In this paper, we propose a novel method that glances future in curriculum learning to achieve the transition from the seq2seq training to prefix2prefix training. Specifically, we gradually reduce the available source information from the whole sentence to the prefix corresponding to that latency. Our method is applicable to a wide range of SiMT methods and experiments demonstrate that our method outperforms strong baselines 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combining different visual vocabularies with different sizes for image categorization

Combining different visual vocabularies with different sizes...

引用

Pacific-Asia Workshop on Computational Intelligence and Industrial Application, PACIIA

作者： Hui-Lan Luo Hui Wei Yuan Ren School of Information Engineering Jiangxi University of Science and Technology Ganzhou Jiangxi China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

In this paper, the advantages of ensemble methods are applied to image categorization. A novel method is introduced for image categorization by combining various visual vocabularies with different sizes in the popular vocabulary approach. The vocabulary approach describes an image as a bag of discrete visual codewords, where the frequency distributions of these words are used for image categorization. Based on vocabularies of various sizes, a classifier ensemble is learned, which can jointly exploit different information with various granularities. High classification accuracies of the proposed algorithm are demonstrated on four different datasets.

关键词： Vocabulary Dictionaries Histograms Humans Testing Image classification Computational intelligence Computer industry Laboratories information processing

来源：评论

学校读者我要写书评

暂无评论

STUDY ON THE CONSTRUCTION OF DOMAIN TEXT CLASSIFICATION MODEL WITH THE HELP OF DOMAIN KNOWLEDGE

STUDY ON THE CONSTRUCTION OF DOMAIN TEXT CLASSIFICATION MODE...

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： JIAN-YI GUO ZHENG-TAO YU LU HAN ZHI-KUN ZHANG XIANG-YAN MENG CUN-LI MAO The School of Information Engineering and Automation Kunming University of Science and Technology The School of Information Engineering and Automation Kunming University of Science and Technology The Institute of Intelligent Information Processing Computer Technology Application Key Laboratory

Traditional text classification model uses statistical methods to obtain features. But in the aspect of discrimination domain and non-domain text category, domain knowledge relations haven't been taken account of in these methods. A domain text classification model was presented in this paper. This model used the support vector machine learning algorithm, gained domain classification feature words through statistic and union domain words, structured domain classification feature space. With the help of domain knowledge relations, computed relevance between domain concepts, got domain classification feature weight. Finally domain text classification was realized. An experiment in the Yunnan tourism domain was carried on to confirm that domain knowledge relations have a good influence on the domain text classification. The classification accuracy rate has been increased 0.04 than improved TFIDF method.

关键词： Tezt classification Feature selection Domain knowledge Relations

来源：评论

学校读者我要写书评

暂无评论

recognition of architectural distortion in mammographic images with transfer learning

Recognition of architectural distortion in mammographic imag...

引用

International Congress on Image and Signal processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Xiaoming Liu Leilei Zhai Ting Zhu Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System College of Computer Science and Technology Wuhan University of Science and Technology

ISBN: (纸本)9781509037117

Computer-aided diagnosis (CAD) technology can improve the detection of abnormal. Such as calcifications, masses, and architectural distortion. Among the three abnormals, architectural distortion is the most difficult one to detect for both radiologists and CAD systems. In this article, we use automatic architectural distortion detection method to locate initial suspicious areas. Then, combine the transfer learning to detect architectural distortion, the reason we use transfer learning is the number of samples of architectural distortion in mini-MIAS database and Digital Database for Screening Mammography (DDSM) is small, and the number of malignant mass is much larger. The malignant mass and the architectural distortion are similar. Our objective is by transferring malignant mass information to improve the recognition rate of AD in the case of only a small amount of AD training samples.

关键词： Distortion Feature extraction Cancer Gabor filters Support vector machines Mammography Entropy

来源：评论

学校读者我要写书评

暂无评论

Generative Rendering Network based on U-shape Discriminator

Generative Rendering Network based on U-shape Discriminator

引用

2022 International Conference on Machine Vision, Automatic Identification and Detection, MVAID 2022

作者： Mu, Chen Zhao, Huaici Liu, Pengfei Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

This paper introduces a generative rendering network(GRN) based on a U-shape discriminator for novel view image synthesis. Recently, some generative adversarial networks start to explore 3D space and synthesize new images by rendering methods. Compared with 2D-only networks, they have achieved impressive results in synthesizing novel view images. However, they still have a common shortcoming: the discriminator cannot provide more detailed information for training a strong generator. For this problem, we design an U-shape based discriminator to extract both global information and pixel-wise information. This innovative discriminator will feedback more instructive clues to train a better generator. Benefit from this strategy, our synthesis results on ShapeNet v2 "cars"and "chairs"and celebA have achieved better performance than comparative methods. © Published under licence by IOP Publishing Ltd.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

Reform and Construction of Computer Major on Local Colleges under the Background of Emerging Engineering Education

Reform and Construction of Computer Major on Local Colleges ...

引用

3rd International Conference on Politics,Economics and Law(ICPEL 2018)

作者： Yaojie Chen Xin Yuan Hai Zhou Zhijing Wan School of Computer Science and Technology Wuhan university of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System

In recent years, with the accelerated development of the global new economy, the country desperately need the support of new engineering talents, which raises higher requirements for the development of higher education in *** in 2016, the "emerging engineering education" was first proposed in China, which is more significant on colleges across the country. Computer major that is an enormous engineering category has trained a large number of talents for the ***, how to pay attention to the new needs of social development and cultivate more high-quality computer professionals is the key for computer major to take the road of connotation development in the future. In this paper, under the background of emerging engineering education, how to carry out teaching reform in local colleges, how to promote the cross-integration of computer subject, and how to strengthen the integration of research, education and industry are discussed in depth. Therefore, the construction of a new project education concept is the future core direction for local colleges.

关键词： emerging engineering education computer major local colleges interdisciplinary innovation

来源：评论

学校读者我要写书评

暂无评论

A Novel Image Encryption Scheme Based on Poker Cross-Shuffling and Fractional Order Hyperchaotic System

A Novel Image Encryption Scheme Based on Poker Cross-Shuffli...

引用

作者： Zhong Chen Huihuang Zhao Junyao Chen College of Computer Science and Technology Hengyang Normal University Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Department of Computer Engineering Ajou University

A novel digital image encryption scheme based on Poker shuffling and fractional order hyperchaotic system is proposed. Poker intercrossing operation has nonlinearity and periodicity, and can form permutation group. Firstly, the plain image is transformed into block image, and each block is confused by Poker shuffling operation with key. Secondly, bit plane of every pixel in each block is confused. Lastly, the scrambled image is encrypted by fractional order hyperchaotic sequence. This encryption scheme provides a secure and efficient key stream, and guarantees a large key space. The experimental results and security analysis imply that the new encryption method has secure encryption effect and property of resisting common attacks.

关键词： Image encryption algorithm Poker shuffling operation Fractional order hyperchaotic system

来源：评论

学校读者我要写书评

暂无评论

High order SF-SFDTD method for solving the time-dependent Schrödinger equation

High order SF-SFDTD method for solving the time-dependent Sc...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Pan Pan Guoda Xie Zhixiang Huang Guilin Hou Ziheng Song School of Electronic and Information Engineering Anhui university Hefei China Education of Anhui Province. Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan Anhui China Ministry of Education. the Key Laboratory of Intelligent Computing and Signal Processing Hefei China Key Laboratory of Electromagnetic Environmental Sensing Anhui Province Anhui University Hefei China Anhui university Hefei China

A high-order spatial filtering-symplectic finite difference time domain (SF-SFDTD) scheme with controllable stability condition is proposed to solve the time-dependent Schrödinger equation (TDSE). Firstly, the higher-order symplectic framework for the discretization of Schrödinger equation is described, and then the spatial filtering method is carried out to extend the stability of the standard SFDTD method. Finally, a numerical example is given to evaluate the correctness of the SF-SFDTD method in numerical solving Schrödinger equation.

关键词： Filtering Filtering algorithms Computational electromagnetics Mathematical models Time-domain analysis Numerical stability Standards

来源：评论

学校读者我要写书评

暂无评论

Fusion of reverse hierarchical alignment for Web-based English-Chinese bilingual dictionary construction

Fusion of reverse hierarchical alignment for Web-based Engli...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Yue-Jie Zhang Lei Cen Qing-Xin Wu Cheng Jin Tao Zhang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai China

In this paper, a new Web-based English-Chinese bilingual dictionary construction pattern is established on the basis of the fusion of the reverse hierarchical alignment. On the one hand, English-Chinese bilingual corpora are collected based on Web mining. On the other hand, unlike the traditional alignment manner from sentence level to word level, the reverse alignment and verification from word level to sentence level is implemented by combining K-vec-based word-level alignment algorithm and Champollion-based sentence-level alignment algorithm. The experimental results show that the more ideal effect is obtained in the manner of “word level” -> “sentence level” reverse alignment dictionary construction.

关键词： History Artificial neural networks Dictionaries Tagging

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Adaptive Self-Loading Fxlms and Cnn-Gru Net for Active Time-Varying Noise Control

SSRN

引用

SSRN 2024年

作者： Zhu, Wenzhao Luo, Lei Key Laboratory of Intelligent Control and Neural Information Processing Education Ministry of China Yanshan University Qinhuangdao066004 China Key Laboratory of Optoelectronic Technology and Systems Education Ministry of China Chongqing University Chongqing400044 China

Active noise control (ANC) provides a lightweight and quick-to-deploy noise attenuation solution compared to traditional passive noise control. However, time-varying noise caused by the changing acoustic environment usually occurs in moving spaces, such as a car cabin, which further deteriorates the robustness of the adaptive filter and even deep networks in the ANC system. To use a deep ANC neural network with great denoising performance in a complex time-varying noise environment and reduce the interference of uncertain noise on the stability of the network, a new hybrid adaptive self-loading filtered-x least mean square (ASL-FxLMS) and convolutional neural network-gate recurrent unit (CNN-GRU) network is proposed. First, based on the CNN-LSTM structure, an improved CNN-GRU network with a multi-head attention mechanism is proposed to enhance attenuation performance for complicated periodical components in the time-varying noise and decrease the computing load as much as possible. In addition, an improved time-delay estimator is applied to improve the real-time ANC performance of CNN-GRU. Meanwhile, an adaptive self-loading FxLMS algorithm has been developed to deal with the uncertain components of time-varying noise. Moreover, to achieve balance attenuation, robustness, and tracking performance, the ASL-FxLMS and CNN-GRU are connected by a convex combination structure. Furthermore, theoretical analysis and simulations are also conducted to show the effectiveness of the proposed method. © 2024, The Authors. All rights reserved.

关键词： Active noise control

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：