检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,581 篇 会议
28 册 图书
23 篇 期刊文献

馆藏范围

1,632 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,110 篇 工学
- 1,018 篇 计算机科学与技术...
- 747 篇 软件工程
- 245 篇 信息与通信工程
- 90 篇 电气工程
- 69 篇 控制科学与工程
- 67 篇 生物工程
- 42 篇 化学工程与技术
- 24 篇 仪器科学与技术
- 24 篇 安全科学与工程
- 23 篇 生物医学工程（可授...
- 21 篇 交通运输工程
- 19 篇 机械工程
- 17 篇 网络空间安全
- 16 篇 电子科学与技术（可...
- 15 篇 建筑学
360 篇 管理学
- 288 篇 图书情报与档案管...
- 107 篇 管理科学与工程(可...
- 49 篇 工商管理
343 篇 理学
- 131 篇 数学
- 124 篇 物理学
- 75 篇 生物学
- 55 篇 统计学（可授理学、...
- 48 篇 系统科学
- 41 篇 化学
41 篇 教育学
- 41 篇 教育学
38 篇 法学
- 32 篇 社会学
37 篇 文学
- 31 篇 外国语言文学
29 篇 医学
- 27 篇 临床医学
- 22 篇 基础医学(可授医学...
19 篇 农学
- 17 篇 作物学
14 篇 经济学
4 篇 军事学

主题

183 篇 natural language...
65 篇 natural language...
55 篇 semantics
50 篇 web services
46 篇 sentiment analys...
42 篇 computational mo...
42 篇 accuracy
41 篇 deep learning
40 篇 information retr...
37 篇 data mining
36 篇 classification (...
35 篇 machine learning
35 篇 artificial intel...
33 篇 ontology
31 篇 speech recogniti...
31 篇 training
29 篇 data models
28 篇 semantic web
26 篇 search engines
26 篇 feature extracti...

机构

7 篇 spoken language ...
7 篇 sri lanka instit...
7 篇 faculty of compu...
6 篇 faculty of infor...
4 篇 key laboratory o...
4 篇 fujian yirong in...
4 篇 korea univ nat l...
4 篇 school of inform...
4 篇 international in...
4 篇 information engi...
3 篇 big data and art...
3 篇 graduate school ...
3 篇 national univers...
3 篇 institute of art...
3 篇 carnegie mellon ...
3 篇 school of inform...
3 篇 chitkara univers...
3 篇 beijing univ pos...
3 篇 ipswich
3 篇 department of in...

作者

7 篇 nakagawa seiichi
5 篇 ren fuji
5 篇 zhao tiejun
5 篇 rim hae-chang
4 篇 heyan huang
4 篇 shikano kiyohiro
4 篇 fuji ren
4 篇 liu ting
3 篇 li li
3 篇 rykowski jarogni...
3 篇 nakamura satoshi
3 篇 zheng dequan
3 篇 ngoc thanh nguye...
3 篇 medhat walaa
3 篇 kinshuk
3 篇 bogdan trawiński
3 篇 sun xu
3 篇 mizera-pietraszk...
3 篇 bollegala danush...
3 篇 kitsuregawa masa...

语言

1,592 篇 英文
37 篇 其他
11 篇 中文

检索条件"任意字段=6th International Conference on Advanced Language Processing and Web Information Technology"

共 1632 条记录，以下是1521-1530 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

3D Hand Pose Estimation Based on External Attention

3D Hand Pose Estimation Based on External Attention

引用

Natural language processing (ICNLP), international conference on

作者： Shoukun Li Xiaoying Pan Beibei Wang Jialong Gao School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi’an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

3D hand pose for a single depth image is an important topic in computer vision and human-computer interaction, and although significant progress has been made in this field in recent years, there is still room for improvement in accuracy for some specific application scenarios. To address this problem, a 3D hand pose estimation algorithm based on external attention is proposed. First, the target features are extracted by an hourglass network; then, a HEM (Hard Example Mining) loss based on a mean-variance loss function is proposed, which firstly calculates the L2 loss values of all N keypoints, and then sorts these loss values, and back-propagates the gradient only to the first m loss values. Meanwhile, external attention is introduced to enhance the ability to perceive the global information of the target, and the recognition ability of the features is improved by giving the features different influences through the attention weights. Experimental results show that the algorithm achieves an average distance error of 5.42 mm on the ICVL dataset and 7.11 mm on the MSRA dataset, which further improves the detection performance of the 3D hand pose estimation algorithm.

关键词： Human computer interaction Computer vision three-dimensional displays Accuracy Target recognition Pose estimation Feature extraction Prediction algorithms Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Edge optimization detection network for camouflaged targets

Edge optimization detection network for camouflaged targets

引用

Natural language processing (ICNLP), international conference on

作者： Hao Yuan Haibo Ge Wenhao He Chaofeng Huang School of Electrical Engineering Xi’an University of Posts and Telecommunications Xi’an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

In order to solve the problem of incomplete spatial information and blurred target boundary in traditional camouflaged target detection (COD), an edge optimization detection network for camouflaged target is proposed. Texture highlight module (thM), Global scale matching module (GSMM), Target boundary exploration module (TBEM) and Boundary inference module (BIM). thM first uses the sensing field to cover the entire multi-stage features extracted by the Res2Net-50 backbone network to realize the global understanding of the visual scene, and then adopts the parallel multi-branch mixed convolution mode to amplify the difference between the target and the background. GSMM encodes the features at the top of the network in channel and spatial dimensions, and can extract the features of different sizes of camouflaged targets from multiple angles. TBEM uses self-attention mechanism to combine lower-level features with higher-level features to deal with the dependency between different boundary pixels in multi-target camouflage. the BIM module uses the boundary guidance factor provided by the TBEM module to guide the inference of the real target and refine the edge details from the features fused by the Attentional Feature Fusion module (AFFM). Quantitative and qualitative experiments were carried out on the public benchmark data set, and the experimental results proved that the proposed algorithm still outperforms the other 8 most advanced models under four objective evaluation indicators.

关键词： Visualization Image edge detection Semantics Object detection Feature extraction Inference algorithms Natural language processing Sensors Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

KGAT-MRC: A Knowledge Graph and Attention Mechanism-Based Model for Machine Reading Comprehension

KGAT-MRC: A Knowledge Graph and Attention Mechanism-Based Mo...

引用

international conference on Communications, information System and Computer Engineering (CISCE)

作者： Miaomiao Zhou Dongsheng Wang Yue Feng Sha Liu Department of Computer Science Jiangsu University of Science and Technology Zhenjiang China

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

Machine Reading Comprehension (MRC) has garnered significant attention in the field of natural language processing. While the maritime domain lacks openly available MRC task models and corresponding datasets, resulting in a deficiency within existing models to provide accurate answers tailored to the maritime domain. In response to these issues, our work uses hand annotation and data augmentation to create the OurShipSet machine reading comprehension dataset, which is tailored for the maritime industry. Additionally, we propose the KGAT-MRC model, which integrates relevant knowledge triplets from the domain to enhance the understanding of text semantics. In order to mitigate the issue of noise introduced by incorporating knowledge triplets, this paper embeds the most relevant knowledge triplets to the questions, ensuring that the impact of noisy questions on the model is minimized through computation-based selection. Experimental results demonstrate that the proposed approach achieves an EM (Exact Match) score of 70.69% and an F1 score of 87.94%, representing improvements of 4.22% and 2.47% respectively over existing methods.

关键词： Knowledge engineering Computational modeling Semantics Noise Knowledge graphs Data models Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Investigating the Dynamic Decision Mechanisms of Users' Relevance Judgment for information Retrieval via Log Analysis 15th

Investigating the Dynamic Decision Mechanisms of Users' Rele...

引用

15th Pacific Rim international conference on Artificial Intelligence (PRICAI) / 15th Pacific Rim Knowledge Acquisition Workshop (PKAW)

作者： Su, Yi Li, Jingfei Song, Dawei Zhang, Pengqing Zhang, Yazhou Tianjin Univ Sch Comp Sci & Technol 135 Yaguan Rd Tianjin 300350 Peoples R China Coordinat Ctr China Natl Comp Network Emergency Response Tech Team 3A Yumin Rd Beijing 100020 Peoples R China Beijing Inst Technol Sch Comp Sci & Technol 5 South Zhongguancun St Beijing 100081 Peoples R China Open Univ Sch Comp & Commun Walton Hall Milton Keynes MK7 6AA Bucks England

ISBN: (纸本)9783319973043;9783319973036

Measuring relevance of documents with respect to a user's query is at the heart of information retrieval ( IR), where the user's relevance judgment criteria have been recognized as multi-dimensional. A set of relevance dimensions that are considered as critical factors in document relevance judgment have been investigated, such as topicality, novelty, and reliability. However, most existing work focuses on individual relevance dimensions, yet neglecting how different dimensions would interact with each other to influence the overall relevance judgment in real-world search scenarios. this paper aims at an initial step to fill the gap. Specifically, we divide 7 relevance dimensions in an enriched Multidimensional User Relevance Model ( MURM) into three categories according to three main requirements for document relevance, i.e., document content requirement, document quality requirement and personalization requirement. We then exploit the Learning to Rank framework to conduct document ranking experiments on a query log dataset from a prominent search engine. the experimental results indicate the existence of an order effect between different dimensions, and suggest that considering different dimensions across categories in different orders for document relevance judgment could lead to distinct search results. Our findings provide valuable insights to build more intelligent and user-centric information retrieval systems, and potentially benefit other natural language processing tasks that involve decision making from multiple perspectives.

关键词： information retrieval User relevance dimensions Order effect

来源：评论

学校读者我要写书评

暂无评论

Relation Extraction Based on Relation Label Constraints

Relation Extraction Based on Relation Label Constraints

引用

international conference on Computer and Communications (ICCC)

作者： Kaihong Lin Kehua Miao Wenxing Hong Chaoyi Yuan Automation Xiamen University Xia men China North China Institute of Computing Technology Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

Knowledge graphs have a significant role in promoting natural language processing tasks, and they have received substantial attention. the relation extractor is a key step in the construction of a knowledge graph, so it is important to improve its performance. However, previous works are mainly based on the pipeline method, which rarely address the problem of overlapping triplets. In addition, the literature does not consider models in which the correlation between relation pairs is addressed, which limits their accuracy. In this paper, we propose a new model called Relation Extraction Based On Relation Label Constraints(RRC) that is based on relation matrix constraints. the subject is extracted in our model in the first step; then, the relation and object are extracted based on the subject information. Each relation is regarded as a vector to assist in the extraction of the relation and object; the vector is used to consider the correlation between the relation vectors. this is used as a constraint to optimize the relation vector. Experiments on two public datasets, NYT and webNLG, show that this method can perform well.

关键词： Correlation Computational modeling Pipelines Data models Natural language processing Data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Improvement of Timing Synchronization Algorithm for FBMC-OQAM System Based on Training Sequence

Improvement of Timing Synchronization Algorithm for FBMC-OQA...

引用

Natural language processing (ICNLP), international conference on

作者： Xihai Xie Ruichao Ning School of Communications and Information Engineering Xi’an University of Posts & Telecommunications Xi’an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

In the context of 5G with high rate transmission, the filter bank multicarrier-offset orthogonal amplitude modulation (FBMC-OQAM) technique has attracted much attention as an alternative to OFDM technology because the FBMC system reduces the wastage of spectral resources and has better time-frequency focusing characteristics, as well as better robustness to channel frequency selective fading. However, the inter-symbol overlap and interference caused by this modulation can make timing synchronization difficult. To address this problem, this paper designs a special training sequence based on existing synchronization algorithms, which exploits the conjugate symmetry property of the FBMC system for timing synchronization, and consists of four symbols, the first two of which are computed to have conjugate symmetry in the time domain; and the last two of which are zero-valued. the length of the correlation sequence is enlarged compared to the traditional algorithm, and the number of symbols used for training is increased. theoretical analysis and simulation results show that the proposed algorithm has higher timing accuracy and better synchronization performance.

关键词： Training Time-frequency analysis Analytical models Accuracy OFDM Simulation Symbols Interference Synchronization Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Architecture of Approximate Softmax Functions for Transformer in Edge Computing

An Energy-Efficient Architecture of Approximate Softmax Func...

引用

Electronics and Electrical Engineering technology (EEET), international conference on

作者： Suhang Li Bo Yin Hao Zhang Information Science and Engineering Ocean University of China Qingdao China

ISBN: (数字)9798350395594

ISBN: (纸本)9798350395600

Recently, Transformer models have provided better accuracy than traditional models in fields such as computer vision (CV) and natural language processing (NLP). However, compared with traditional convolutional neural networks (CNNs), a large number of softmax function calculations in Transformer models involve expensive exponential and division calculations, resulting in huge consumption of computing and storage resources and waste of power consumption, which makes Transformer networks unable to be effectively applied to edge computing. To solve this problem, in this paper an approximate softmax computation architecture is proposed. Compared with the classic base-e softmax function or the base-2 softmax function proposed in recent years, our proposed design uses simpler shift and fixed-point addition operations to replace complex exponential and division operations, and thus significantly reduces the resource consumption while maintaining a high computation accuracy. the proposed architecture can effectively accelerate the Softmax computation of Transformer models in edge computing. Experimental results show that for 16-bit Softmax computation, the proposed design can achieve less resource occupation and energy consumption. Vision transformer(ViT) models are also used to verify the effectiveness of the proposed method in real transformer models.

关键词： Computer vision Accuracy Power demand Computational modeling Computer architecture Transformers Natural language processing

来源：评论

学校读者我要写书评

暂无评论

DESIGN OF ROBUST SUBTRACTIVE BEAMFORMER FOR NOISY SPEECH RECOGNITION

DESIGN OF ROBUST SUBTRACTIVE BEAMFORMER FOR NOISY SPEECH REC...

引用

6～(th) international conference on Spoken language processing

作者： Mitsunori Mizuma(?hi Masato Nkagi Satoshi Nakamura ATR Spoken Language Translation Research Laboratories 2-2-2 Hikaridai. Seika-(?h(?. Souraku-gun. Kyoto 619-0288. JAPAN. School of Information Science. Japan Advanced Insti(?ute of Science and Technology. (? Asahidai. (? atsunokuchi. Nomi-gun. Ishikawa 923-1292. JAPAN. ATR Spoken Language Translation Research Laboratories 2-2-2 Hikaridai. Seika-(?h(?. Souraku-gun. Kyoto 619-0288. JAPAN.

there is a big demand for noise reduetion to enhance ASR robustuess. A great variety of noise reduction methods have been proposed. but almost none of them can reduce non-stationary noises. the authers have proposed an algorithm that can redu(?)(?) noises that former methods, such as adaptive beamfor(?)ers. find difflicult to deal with. In this paper, the authors verify the proposed method as a front-end for ASR by phoneme recognition tests. Its feasibility is also discussed under reverberaut environments.

关键词： SOI DESIGN OF ROBUST SUBTRACTIVE BEAMFORMER FOR NOISY SPEECH RECOGNITION

来源：评论

学校读者我要写书评

暂无评论

An Enhanced BLSTIP Dialogue Research Platform

An Enhanced BLSTIP Dialogue Research Platform

引用

6～(th) international conference on Spoken language processing

作者： Qiru Zhou Antoine Saad Shereiff Abdou Dialogue Systems Research Department Bell Labs Lucent Technologies 600 Mountain Ave. Murray Hill NJ 07974 USA Dialogue Systems Research Department Bell Labs Lucent Technologies 600 Mountain Ave. Murray Hill NJ 07974 USA Dialogue Systems Research Department Bell Labs Lucent Technologies 600 Mountain Ave. Murray Hill NJ 07974 USA

this paper presents some recent enhancement to Bell Labs Speech technology Integration Platform (BLSTIP), a common platform to integrate Bell Lab's speech, telephony, Internet, and dialogue technologies for spoken and multi-modal dialogue system research and prototyping. Last year, we introduced BLSTIP to our partners as a speech technology platform for collaborative research and new application development. BLSTIP software is packaged as a single, network downloadable installation file. It supports a variety of speech applications such as natural language call routing/steering for call centers, natural language information system, messaging system with voice user interface, speaker verification, speech application trial and data collection, etc. As an enhancement to BLSTIP, we also designed a VoiceXML (Voice eXtensible Markup language) integration infrastructure to study emerging web hosted speech applications such as voice portal, multimodal internet access, and wireless internet access.

关键词： service An Enhanced BLSTIP Dialogue Research Platform session

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Legal Documentation Assistant

AI-Powered Legal Documentation Assistant

引用

Pervasive Computing and Social Networking (ICPCSN), international conference on

作者： Kuldeep Vayadande Aditi Bhat Pranav Bachhav Aditya Bhoyar Zulfikar Charoliya Aayush Chavan Department of Information Technology Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798350386349

ISBN: (纸本)9798350386356

Legal systems worldwide vary in structure and principles, reflecting the diverse legal traditions of different countries. the legal system, inherently complex and reliant on meticulous documentation, often faces challenges related to time-consuming manual processes and the potential for human errors. the system proposed provides a transformative solution to the above problems. the system emerges as a groundbreaking solution within the intricate landscape of legal systems which responds to these challenges by seamlessly integrating advanced AI techniques. At its core, OpenAI embeddings takes center stage, demonstrating unparalleled proficiency in document generation, comprehension, and abnormality detection, addressing the complexities ingrained in legal documentation. In contrast to traditional approaches, this system maximizes the versatility of ChatGPT 3.5, allowing it to not only issue commands but also proficiently generate a diverse array of legal documents. By incorporating an understanding module equipped with PyPDF, Amazon Textract, and langchain utilities, the system adeptly handles document intricacies. the utilization of OpenAI Embeddings further enhances natural language understanding. Leveraging sentiment analysis and Named Entity Recognition (NER) in its natural language processing (NLP) toolkit, the system employs an intuitive web interface for irregularities detection. the exploration of AI for automated irregularity detection showcases its transformative potential in ensuring document accuracy within the legal domain. this project, therefore, stands as a beacon of innovation, promising to reshape the dynamics of legal document processing by merging advanced AI capabilities with the unique demands of legal systems.

关键词： Pervasive computing Technological innovation Sentiment analysis Law Social networking (online) Documentation Named entity recognition

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共164页 << < 149 150 151 152 153 154 155 156 157 158 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：