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

551 篇 期刊文献
335 篇 会议
15 篇 学位论文
1 册 图书

馆藏范围

902 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

847 篇 工学
- 570 篇 计算机科学与技术...
- 324 篇 电气工程
- 130 篇 软件工程
- 88 篇 信息与通信工程
- 77 篇 控制科学与工程
- 58 篇 仪器科学与技术
- 48 篇 测绘科学与技术
- 40 篇 生物医学工程（可授...
- 33 篇 土木工程
- 28 篇 环境科学与工程（可...
- 27 篇 机械工程
- 24 篇 电子科学与技术（可...
- 19 篇 石油与天然气工程
- 14 篇 动力工程及工程热...
- 11 篇 水利工程
- 10 篇 光学工程
- 10 篇 材料科学与工程（可...
- 10 篇 交通运输工程
- 9 篇 力学（可授工学、理...
- 8 篇 建筑学
187 篇 理学
- 82 篇 物理学
- 47 篇 地球物理学
- 35 篇 生物学
- 26 篇 化学
- 12 篇 数学
171 篇 医学
- 130 篇 临床医学
- 26 篇 基础医学(可授医学...
- 21 篇 特种医学
61 篇 管理学
- 56 篇 管理科学与工程(可...
10 篇 文学
- 8 篇 外国语言文学
7 篇 农学
5 篇 艺术学
2 篇 法学
1 篇 经济学
1 篇 教育学

主题

902 篇 encoder-decoder
159 篇 deep learning
81 篇 attention mechan...
60 篇 attention
54 篇 semantic segment...
48 篇 feature extracti...
46 篇 lstm
38 篇 transformer
36 篇 decoding
35 篇 convolutional ne...
32 篇 cnn
24 篇 semantics
22 篇 image captioning
22 篇 u-net
22 篇 convolutional ne...
21 篇 speech recogniti...
20 篇 task analysis
20 篇 machine learning
19 篇 long short-term ...
18 篇 image segmentati...

机构

8 篇 univ chinese aca...
8 篇 univ sci & techn...
6 篇 chinese acad sci...
6 篇 univ sci & techn...
6 篇 univ sci & techn...
5 篇 nanjing univ sci...
4 篇 jiangnan univ sc...
4 篇 microsoft corp r...
4 篇 chongqing univ c...
4 篇 wuhan univ sch r...
4 篇 shenyang siasun ...
4 篇 southeast univ s...
4 篇 univ sci & techn...
4 篇 toyota technol i...
4 篇 iflytek res peop...
4 篇 google inc mount...
4 篇 shanghai jiao to...
4 篇 northeastern uni...
4 篇 tianjin univ sch...
4 篇 chinese acad sci...

作者

8 篇 watanabe shinji
7 篇 du jun
6 篇 liu yang
6 篇 chen kai
6 篇 zhang jianshu
5 篇 ling zhen-hua
5 篇 zhang limao
5 篇 wang feng
5 篇 wang jun
4 篇 gaur yashesh
4 篇 zhang chunyu
4 篇 wu chengdong
4 篇 wang qing
4 篇 wang bing
4 篇 li chen
4 篇 song xiao
4 篇 xu bo
4 篇 xu fang
4 篇 jiao licheng
4 篇 toshniwal shubha...

语言

839 篇 英文
31 篇 中文
29 篇 其他
3 篇 法文
1 篇 德文

检索条件"主题词=Encoder-decoder"

共 902 条记录，以下是381-390 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：

DM-BDD: Real-time Vessel Trajectory Prediction Based on Diffusion Probability Model Balancing Diversity and Determinacy

DM-BDD: Real-time Vessel Trajectory Prediction Based on Diff...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ma, Kun Han, Qilong Yao, Jingzheng Zhang, Yuntao Harbin Engn Univ Coll Comp Sci & Technol Harbin Peoples R China Harbin Engn Univ Yantai Res Inst Yantai Peoples R China Harbin Engn Univ Coll Shipbuilding Engn Harbin Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Accurate ship trajectory prediction is crucial to ensure the safety and interaction efficiency of maritime traffic, especially in areas with dense ships and areas with intersecting waterways. Different from the certainty of short-term trajectory prediction, for long-term trajectory prediction, the uncertainty of direction and speed changes in operation is amplified, and the prediction of ship trajectory is more difficult. To solve this problem, we propose A framework based on a diffusion probability model balancing diversity and determinacy (DMBDD). Inspired by the denoising process in the diffusion model, we gradually reduce the range of trajectories that the ships are navigable, and finally achieve a desired and deterministic trajectory. This process is learned using a parameterized Markov chain based on the currently observed trajectory. The length of the chain is adjusted to control the degree of uncertainty of the running trajectory and the final position, and to balance the diversity and certainty of the prediction results. We design an architecture consisting of a temporal-social encoding network and an LSTM-based decoder network to achieve the purpose of capturing the spatial dependence and social dependence of *** test and compare on the AIS dataset of the real Weihai Port and the Nantong waterway of the Yangtze River estuary. The experimental results show that the short, medium and long-term prediction results of the proposed model on the two data sets achieve the best performance in the field of ship trajectory prediction.

关键词： Diffusion model Markov chain Trajectory prediction LSTM encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

RESIDUAL GROUP ENHANCED GAN FOR REMOTE SENSING IMAGE CLOUD SHADOW REMOVAL

RESIDUAL GROUP ENHANCED GAN FOR REMOTE SENSING IMAGE CLOUD S...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Yang, Jiajun Liu, Chenyang Chen, Keyan Zou, Zhengxia Shi, Zhenwei Beihang Univ Image Proc Ctr Sch Astronaut Beijing 100191 Peoples R China Beihang Univ Sch Astronaut Dept Guidance Nav & Control Beijing 100191 Peoples R China

ISBN: (纸本)9798350360332;9798350360325

Cloud shadow is an unignorable factor affecting the quality of remote sensing images, but there are few researches specifically focusing on cloud shadow removal and its impact on downstream remote sensing tasks. In this paper, we propose a residual group enhanced generative adversarial network (RGE-GAN) for cloud shadow removal. We design an encoder-decoder with residual group enhancement (RGE) module to remove cloud shadows from remote sensing images. RGE module can effectively enhance the deep features extracted by encoder. We further introduce a discriminator network and employ adversarial training strategy to constrain the generator to reconstruct high-quality cloud shadow removed images conforming to the distribution of remote sensing images. The joint experiments of cloud shadow removal and building extraction on real remote sensing dataset show that our cloud shadow removal method can effectively enhance the quality of remote sensing images and improve the performance of downstream remote sensing processing tasks.

关键词： Cloud shadow removal remote sensing encoder-decoder generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Study of Various Text Summarization Methods 1

引用

International Conference on Artificial Intelligence: Theory and Applications (AITA)

作者： Khan, Sarim Pathak, Abhay Chopra, Rishabh Parihar, Hemant Singh Kaur, Preet Chandan Ramrao Adik Inst Technol Navi Mumbai 400706 Maharashtra India

ISBN: (数字)9789819984763

ISBN: (纸本)9789819984756;9789819984763

This paper presents an analysis of various text summarization methods used to condense lengthy pieces of text into shorter versions while retaining the most relevant information. The study reviews different approaches to text summarization, including extraction-based and abstraction-based methods. These techniques are assessed in terms of accuracy, fluency, and coherence, using a variety of metrics such as ROUGE, BLEU, and F1 measures. The suggested model may efficiently produce a smaller body of text that is both accurate in both the semantic sense and linguistic sense by comprehending the entire text and framing it on its own. The findings of this study can help researchers and practitioners in the field of NLP to choose the most suitable text summarization method for their particular application.

关键词： encoder-decoder RNN Text summarization LSTM Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Adaptive Beamforming Based on Recurrent Deep Learning for GNSS Bands 32

Adaptive Beamforming Based on Recurrent Deep Learning for GN...

引用

32nd IEEE Signal Processing and Communications Applications Conference (SIU)

作者： Aras, Irem Erer, Isin Akdemir, Eren ASELSAN AS REHIS Ankara Turkiye Istanbul Tech Univ Elekt Muh Istanbul Turkiye

ISBN: (纸本)9798350388978;9798350388961

Global Navigation Satellite Systems (GNSS) are undoubtedly the most preferred navigation method in these days. However, GNSS signals can frequently become a target for undesired jammer signals. The most known solution for this problem is beamforming methods. In this study, recurrent neural network (RNN) structures are used to determine the beamforming coefficients of signals with known angle of arrivals. A new encoder-decoder (ED) beamforming approach is presented, which is built with long short-term memory (LSTM) cells. ED beamforming approach is compared with a previously proposed multilayer LSTM network and known null steering beamforming (NSB), which ED beamforming is resulted more successfully in terms of beam and null divergences in directions of signal arrivals and with a shorter response time.

关键词： GNSS deep learning long-short term memory (LSTM) encoder-decoder null-steering beamforming

来源：评论

学校读者我要写书评

暂无评论

A Deep-Learning Approach for the Identification of New Subtypes of Lung Cancer 25th

A Deep-Learning Approach for the Identification of New Subty...

引用

25th International Conference on Intelligent Data Engineering and Automated Learning

作者： Banerjee, Tuhin Corradini, Andrea Canon EMEA Amstelveen Netherlands MCI Innsbruck Austria

ISBN: (纸本)9783031777301;9783031777318

Lung cancer is the deadliest cancer in the world. It is caused by unchecked cell division of damaged cells in the lungs forming tumors that eventually prevent the lung from functioning properly. Identification of novel unsupervised subtypes of lung cancer is critical to reveal new insights into the underlying biology of cancer and ensure that patients receive specialized precision treatment based on the subtype of cancer they are suffering from. The ability of modern sequencing tools to produce patient-specific RNA sequencing (RNA-seq) gene expression data has transformed cancer research by offering in-depth understanding of the molecular landscape of cancer. This paper reports on a pipeline that comprise of a Deep Autoencoder (DAE) model coupled with hierarchical agglomerative clustering (H-Clust). It aims to identify new unsupervised lung cancer subtypes from RNA-seq expression samples collected from a publicly available dataset. Further, a deep learning (DL) model, Artificial Neural Network (ANN) is used to classify a patient's data into one of the newly identified subtypes.

关键词： lung cancer subtype TCGA RNA-seq deep learning DAE encoder-decoder agglomerative clustering ANN

来源：评论

学校读者我要写书评

暂无评论

Mask-Guided Joint Single Image Specular Highlight Detection and Removal 6th

Mask-Guided Joint Single Image Specular Highlight Detection ...

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Chen, Hao Li, Li Yu, Neng Wuhan Textile Univ Sch Comp Sci & Artificial Intelligence Wuhan 430200 Peoples R China Engn Res Ctr Hubei Prov Clothing Informat Wuhan 430200 Peoples R China Hubei Prov Engn Res Ctr Intelligent Textile & Fas Wuhan 430200 Peoples R China

ISBN: (纸本)9789819985456;9789819985463

Detecting and removing specular highlights is a highly challenging task that can effectively enhance the performance of other computer vision tasks in real-world scenarios. Traditional highlight removal algorithms struggle to accurately distinguish the differences between pure white or nearly white materials and highlights, while recent deep learning-based highlight removal algorithms suffer from complex network architectures, lack of flexibility, and limited object adaptability. To address these issues, we propose an end-to-end framework for single-image highlight detection and removal that utilizes mask guidance. Our framework adopts an encoder-decoder structure, with EfficientNet serving as the backbone network for feature extraction in the encoder. The decoder gradually restores the feature map to its original size through upsampling. In the highlight detection module, the network layers are deepened, and residual modules are introduced to extract more feature information and improve detection accuracy. In the highlight removal module, we introduce the Convolutional Block Attention Module, which dynamically learns the importance of each channel and spatial position in the input feature map. This helps the model better distinguish foreground and background and improve adaptability and accuracy in complex *** results demonstrate that our proposed method outperforms existing methods, as evaluated on the public SHIQ dataset through comparative experiments. Our method achieves superior performance in highlight detection and removal.

关键词： Highlight detection Highlight removal Attention End to End encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Learning-based Algorithm for Chinese Image Caption Generation in Electric Robot Inspection Processing 7

Self-supervised Learning-based Algorithm for Chinese Image C...

引用

7th International Conference on Automation Electronics and Electrical Engineering

作者： Qian Ping Zhang Yong Cao Yang Zhou Gang Qi Zhongyi State Grid Dongtou Power Supply Co Dept Management Hangzhou Peoples R China State Grid Zhejiang Elect Power Dept Equipment Hangzhou Peoples R China State Grid Jiaxing Power Supply Co Dept Operat & Maintenance Jiaxing Zhejiang Peoples R China State Grid Zhejiang Elect Power Jiaxing Power Sup Dept Operat & Inspect Jiaxing Zhejiang Peoples R China State Grid Zhejiang Elect Power Jiaxing Power Sup Dept Operat Jiaxing Zhejiang Peoples R China

ISBN: (数字)9798350377033

ISBN: (纸本)9798350377040;9798350377033

Electric robot will obtain a large amount of image information during inspection, and if these images are checked whether there are faults in power inspection is time-consuming and labor-intensive. There is an urgent need for power image Chinese title generation technology to solve it. However, existing image Chinese title generation methods face the problems of small training data sets, differences in specific applications, and few methods for generating Chinese titles for power images. To this end, this paper proposes a self-supervised learning-based image Chinese title generation algorithm for fault detection in electric robot inspection. Specifically, a contrastive learning-based model to automatically capture the semantic relationship between images and text. Then, we propose an end-to-end encoding-decoding model combined with an attention mechanism to obtain Chinese title generation for inspection images. The effectiveness of the proposed algorithm is experimentally verified on two real datasets.

关键词： self-supervised learning attention mechanism encoder-decoder image caption generation electric robot Semantic feature

来源：评论

学校读者我要写书评

暂无评论

GAP: A Grammar and Position-Aware Framework for Efficient Recognition of Multi-Line Mathematical Formulas 24

GAP: A Grammar and Position-Aware Framework for Efficient Re...

引用

17th ACM International Conference on Web Search and Data Mining (WSDM)

作者： Yang, Zhe Liu, Qi Zhang, Kai Tong, Shwei Chen, Enhong Univ Sci & Technol China Sch Comp Sci & Technol Hefei Anhui Peoples R China State Key Lab Cognit Intelligence Hefei Anhui Peoples R China

ISBN: (纸本)9798400703713

Formula recognition endeavors to automatically identify mathematical formulas from images. Currently, the encoder-decoder model has significantly advanced the translation from image to corresponding formula markups. Nonetheless, previous research primarily concentrated on single-line formula recognition, ignoring the recognition of multi-line formulas, which presents additional challenges such as more stringent grammatical restrictions and twodimensional positions. In this work, we present GAP (Grammar And Position-Aware formula recognition), a comprehensive framework designed to tackle the challenges in multi-line mathematical formula recognition. First, to overcome the limitations imposed by grammar, we design a novel Grammar Aware Contrastive Learning (GACL) module, integrating complex grammar rules into the transcription model through a contrastive learning mechanism. Furthermore, primitive contrastive learning lacks clear directions for comprehending grammar rules and can lead to unstable convergence or prolonged training cycles. To enhance training efficiency, we propose Rank-Based Sampling (RBS) specialized for multi-line formulas, which guides the learning process by the importance ranking of different grammar errors. Finally, spatial location information is critical considering the two-dimensional nature of multiline formulas. To aid the model in keeping track of that global information, we introduced a Visual Coverage (VC) mechanism that incorporates historical attention information into the image features via a parameter-free way. To validate the effectiveness of our GAP framework, we construct a new dataset Multi-Line containing 12,002 multi-line formulas and conduct extensive experiments to show the efficacy of our GAP framework in capturing grammatical rules, enhancing recognition accuracy, and enhancing training efficiency. Codes and datasets are available at https://***/Sinon02/GAP.

关键词： Formula Recognition Contrastive Learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Methodology for Video Description Generation with Semantic Feature Selection and Attention Fusion 5

Methodology for Video Description Generation with Semantic F...

引用

5th International Conference on Computer Engineering and Application (ICCEA)

作者： Che, Zhanbin Wang, Zhihao Zhongyuan Univ Technol Sch Comp Sci Zhengzhou Peoples R China

ISBN: (纸本)9798350386783;9798350386776

To enhance the semantic relevance between the textual descriptions of entities and the video content and to address the inefficiency of multi-modal features. This paper proposes a novel method for video description generation focusing on semantic feature selection and attention fusion. By selecting semantic objects from the video that appear in the text description and retrieving the corresponding behavioral representations from the motion features. Utilizing a cross-attention mechanism, integrating semantic and action features. The fused features are then input into a decoder to generate semantic descriptions. Experiments demonstrate that this approach effectively screens semantic objects within videos and generates complete textual descriptions based on their actions.

关键词： Video description Semantic feature selection Attention fusion encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Multimodal Enhanced Target Representation for Machine Translation 1

引用

13th International Conference on Computer Engineering and Networks (CENet)

作者： Zang, Xiaogang Zhu, Huidong Dai, Xue Zhengzhou Univ Light Ind Zhengzhou Peoples R China

ISBN: (数字)9789819992430

ISBN: (纸本)9789819992454;9789819992430;9789819992423

Recently, visual annotation is successfully introduced into the encoder-decoder framework to open a new multimodal neural machine translation (MMT) scenario. However, it is still difficult for MMT to simulate the ground-truth target future context due to the autoregressive decoder. The visual annotation, which presents the content described in the bilingual parallel sentence pair, provides a ground-truth global contextual information for the auto-regressive decoder. Thus, we propose to directly learn a practical target for future contextual information from the visual modality space, thereby enhancing the target representation of the decoder. Empirical results on several widely used multimodal translation benchmarks demonstrated that the proposed approach significantly improved the performance of MMT over strong baselines.

关键词： Neural machine translation encoder-decoder Multimodal

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91页 << < 35 36 37 38 39 40 41 42 43 44 > >>

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：