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

132 篇 期刊文献
48 篇 会议

馆藏范围

180 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

176 篇 工学
- 113 篇 计算机科学与技术...
- 74 篇 电气工程
- 35 篇 信息与通信工程
- 19 篇 软件工程
- 18 篇 生物医学工程（可授...
- 16 篇 控制科学与工程
- 15 篇 仪器科学与技术
- 15 篇 测绘科学与技术
- 14 篇 环境科学与工程（可...
- 8 篇 机械工程
- 6 篇 电子科学与技术（可...
- 5 篇 船舶与海洋工程
- 4 篇 土木工程
- 3 篇 石油与天然气工程
- 2 篇 建筑学
- 2 篇 水利工程
- 2 篇 交通运输工程
- 1 篇 光学工程
46 篇 医学
- 28 篇 临床医学
- 12 篇 基础医学(可授医学...
- 10 篇 特种医学
34 篇 理学
- 13 篇 生物学
- 10 篇 地球物理学
- 8 篇 物理学
- 6 篇 化学
- 1 篇 地理学
- 1 篇 海洋科学
- 1 篇 系统科学
11 篇 管理学
- 11 篇 管理科学与工程(可...
6 篇 农学
- 3 篇 农业资源与环境
1 篇 艺术学

主题

180 篇 encoder-decoder ...
29 篇 deep learning
17 篇 attention mechan...
14 篇 semantic segment...
13 篇 convolutional ne...
12 篇 feature extracti...
11 篇 image segmentati...
8 篇 real-time semant...
6 篇 decoding
6 篇 lightweight netw...
6 篇 convolutional ne...
5 篇 convolution
5 篇 computational mo...
5 篇 image inpainting
4 篇 task analysis
4 篇 transfer learnin...
4 篇 residual network
4 篇 feature fusion
4 篇 semantics
4 篇 remote sensing

机构

5 篇 chongqing univ p...
5 篇 tianjin univ sch...
4 篇 xian hitech res ...
3 篇 xian hitech res ...
2 篇 chongqing univ p...
2 篇 qingzhou hitech ...
2 篇 lakehead univ de...
2 篇 cent south univ ...
2 篇 chinese acad sci...
2 篇 wuhan univ state...
2 篇 south china univ...
2 篇 univ illinois de...
2 篇 east china norma...
2 篇 nanjing univ sci...
2 篇 chongqing univ p...
2 篇 southwest univ s...
1 篇 etri artificial ...
1 篇 telkom univ sch ...
1 篇 king saud univ c...
1 篇 beijing inst tec...

作者

5 篇 hu xuegang
4 篇 wang shuyang
4 篇 he hao
4 篇 yang dongfang
3 篇 mu xiaodong
3 篇 gong jun
3 篇 yu wenxin
3 篇 wang qi
3 篇 watanabe shinji
3 篇 zhao peng
2 篇 turkoglu muammer
2 篇 nie liang
2 篇 liu yuan
2 篇 jing liyuan
2 篇 liu qi
2 篇 fu yingnan
2 篇 wang bing
2 篇 reyes mauricio
2 篇 scott matthew r.
2 篇 masumoto yusuke

语言

173 篇 英文
7 篇 其他

检索条件"主题词=encoder-decoder network"

共 180 条记录，以下是131-140 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：

encoder-decoder-based image transformation approach for integrating precipitation forecasts 13

Encoder-decoder-based image transformation approach for inte...

引用

13th Asian Conference on Machine Learning (ACML)

作者： Hachiya, Hirotaka Masumoto, Yusuke Mori, Yuki Ueda, Naonori Wakayama Univ Grad Sch Syst Engn Wakayama Japan RIKEN Ctr AIP Wako Saitama Japan Japan Meteorol Agency Numer Predict Dev Ctr Tokyo Japan Fujitsu Ltd Tokyo Japan

As the damage caused by heavy rainfall is becoming more serious, the improvement of precipitation forecasts is highly demanded. For this purpose, arithmetic and Bayesian average-based methods have been proposed to integrate multiple 2D-grid forecasts. However, since a single weight is shared in the entire grid in these methods, local variations of the importance of forecasts could not be taken into account. Besides, although a variety of information is available in precipitation forecast, it would not be straightforwardly to incorporate the additional information in the existing methods. To overcome these problems, we propose an encoder-decoder-based image transformation method that generates a weight image that is optimized in a pixel-wise manner, and additional information could be embedded as the channel of input images and feature maps. Through the experiment of precipitation forecast in the period from April 2018 to March 2019 in Japan, we will show that our proposed integration method outperforms existing methods.

关键词： precipitation forecast image-to-image transformation encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

MsEDNet: Multi-Scale Deep Saliency Learning for Moving Object Detection

MsEDNet: Multi-Scale Deep Saliency Learning for Moving Objec...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Patil, Prashant W. Murala, Subrahmanyam Dhall, Abhinav Chaudhary, Sachin Indian Inst Technol Ropar Comp Vis & Pattern Recognit Lab Rupnagar Punjab India Indian Inst Technol Ropar Learning Afffect & Semant Image Anal LASII Grp Rupnagar Punjab India

ISBN: (纸本)9781538666500

Moving object detection (foreground and background) is an important problem in computer vision. Most of the works in this problem are based on background subtraction. However, these approaches are not able to handle scenarios with infrequent motion of object, illumination changes, shadow, camouflage etc. To overcome these, here a two stage robust and compact method for moving object detection (MOD) is proposed. In first stage, to generate the saliency map, background image is estimated using a temporal histogram technique with the help of several input frames. In the second stage, multiscale encoder-decoder network is used to learn multiscale semantic feature of estimated saliency for foreground extraction. The encoder is used to extract multi-scale features from multi-scale saliency map. The decoder part is designed to learn the mapping of low resolution multi-scale features into high resolution output frame. To observe the efficacy of proposed MsEDNet, experiments are conducted on two benchmark datasets (change detection (CDnet-2014) [1] and Wallflower [2]) for MOD. The precision, recall and F-measure are used as performance parameter for comparison with the existing state-of-the-art methods. Experimental results show a significant improvement in detection accuracy and decrement in execution time as compared to the state-of-the-art methods for MOD.

关键词： Histogram Background estimation CNN encoder-decoder network foreground detection

来源：评论

学校读者我要写书评

暂无评论

Robust Speech Recognition Via Anchor Word Representations 18

Robust Speech Recognition Via Anchor Word Representations

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： King, Brian Chen, I-Fan Vaizman, Yonatan Liu, Yuzong Maas, Roland Parthasarathi, Sree Hari Krishnan Hoffmeister, Bjorn Amazon Seattle WA 98109 USA Univ Calif San Diego San Diego CA 92103 USA

ISBN: (纸本)9781510848764

A challenge for speech recognition for voice-controlled household devices, like the Amazon Echo or Google Home, is robustness against interfering background speech. Formulated as a far-field speech recognition problem. another person or media device in proximity can produce background speech that can interfere with the device-directed speech. We expand on our previous work on device-directed speech detection in the far-field speech setting and introduce two approaches for robust acoustic modeling. Both methods are based on the idea of using an anchor word taken from the device directed speech. Our first method employs a simple yet effective normalization of the acoustic features by subtracting the mean derived over the anchor word. The second method utilizes an encoder network projecting the anchor word onto a fixed-size embedding. which serves as an additional input to the acoustic model. The encoder network and acoustic model are jointly trained. Results on an in-house dataset reveal that, in the presence of background speech, the proposed approaches can achieve up to 35% relative word error rate reduction.

关键词： robust speech recognition speaker adaptation encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition with Homophones-Noisy Data 16th

Named Entity Recognition with Homophones-Noisy Data

引用

16th Pacific Rim International Conference on Artificial Intelligence (PRICAI)

作者： Liu, Zhicheng Wu, Gang Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9783030299088;9783030299071

General named entity recognition systems exclusively focus on higher accuracy regardless of dirty data. However, raw source data face serious challenges specially that are originated from automated speech recognition systems' results. In this paper, we propose Pinyin (Pinyin is the official romanization system for Standard Chinese, each Chinese character has its own pinyin sequence which is composed of Latin alphabet) Hierarchical Attention encoder-decoder network and Character Alternate network to overcome Chinese homophones' problems which frequently frustrate researchers in consecutive Natural Language Understanding (NLU). Our models present a none word segmentation structure to effectively avoid secondary data corruption and adequately extract words' internal features. Besides, corrupted sequences can be revised by character-level network. Evaluation demonstrates that our proposed method achieves 93.73% F1 scores which are higher than 90.97% F1 scores using baseline models in homophone-noisy dataset. Additional experiments are conducted to show equivalent results in the universal dataset.

关键词： Named entity recognition Homophone encoder-decoder network Autoencoder

来源：评论

学校读者我要写书评

暂无评论

Automatic Brain Tumor Segmentation with Domain Adaptation 4th

Automatic Brain Tumor Segmentation with Domain Adaptation

引用

4th International Workshop on Brainlesion - Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (BrainLes)

作者： Dai, Lutao Li, Tengfei Shu, Hai Zhong, Liming Shen, Haipeng Zhu, Hongtu Univ Hong Kong Fac Business & Econ Pok Fu Lam Hong Kong Peoples R China Univ N Carolina Biomed Res Imaging Ctr Dept Radiol Chapel Hill NC 27515 USA Univ N Carolina Dept Biostat Chapel Hill NC 27515 USA Univ Texas MD Anderson Canc Ctr Dept Biostat Houston TX 77030 USA Southern Med Univ Sch Biomed Engn Guangdong Prov Key Lab Med Image Proc Guangzhou Peoples R China

ISBN: (纸本)9783030117269;9783030117252

Deep convolution neural networks, in particular, the encoder-decoder networks, have been extensively used in image segmentation. We develop a deep learning approach for tumor segmentation by combining a modified U-Net and its domain-adapted version (DAU-Net). We divide training samples into two domains according to preliminary segmentation results, and then equip the modified U-Net with domain adaptation structure to obtain a domain invariant feature representation. Our proposed segmentation approach is applied to the BraTS 2018 challenge for brain tumor segmentation, and achieves the mean dice score of 0.91044, 0.85057 and 0.80536 for whole tumor, tumor core and enhancing tumor, respectively, on the challenge's validation data set.

关键词： Confusion loss Domain adaptation encoder-decoder network Brain tumor Segmentation

来源：评论

学校读者我要写书评

暂无评论

EDSL: An encoder-decoder Architecture with Symbol-Level Features for Printed Mathematical Expression Recognition 17th

EDSL: An Encoder-Decoder Architecture with Symbol-Level Feat...

引用

17th International Conference on Document Analysis and Recognition (ICDAR)

作者： Fu, Yingnan Liu, Tingting Gao, Ming Zhou, Aoying East China Normal Univ Sch Data Sci & Engn Shanghai Peoples R China East China Normal Univ Sch Psychol & Cognit Sci Shanghai Key Lab Mental Hlth & Psychol Crisis Int Shanghai Peoples R China

ISBN: (纸本)9783031416750;9783031416767

Printed mathematical expression recognition (PMER) aims to transcribe a printed mathematical expression image into a structural expression. The task is useful in a wide spectrum of applications, including personalized question recommendation and automatic problem solving. In this paper, we propose a new method named EDSL, shorted for an encoder-decoder architecture with Symbol-Level features, to recognize printed mathematical expressions from input images. Its encoder consists of a segmentation module to identify all symbols and their spatial information from the image in an unsupervised manner, and a reconstruction module to recover symbol dependencies after symbol segmentation. Furthermore, we employ a position correction attention mechanism to capture the spatial relationship between symbols, and apply a transformer model to alleviate the negative impact from long output. We conduct extensive experiments on two real datasets to verify the effectiveness and rationality of our proposed EDSL model. The experimental results illustrated that EDSL outperformed state-of-the-art methods by an accuracy margin of 3.47% and 4.04% in the two datasets, respectively.

关键词： printed mathematical expression recognition encoder-decoder network segmentation position correction attention

来源：评论

学校读者我要写书评

暂无评论

MULTI HYBRID EXTRACTOR network FOR 3D HUMAN POSE ESTIMATION 30

MULTI HYBRID EXTRACTOR NETWORK FOR 3D HUMAN POSE ESTIMATION

引用

30th IEEE International Conference on Image Processing (ICIP)

作者： Yuan, Zhixiang Zhang, Xitie Wu, Suping Zhang, Boyang Peng, Yuxin Wang, Bing Ningxia Univ Sch Informat Engn Yinchuan Ningxia Peoples R China

ISBN: (纸本)9781728198354

Monocular image or video based 3D human pose estimation remains a very challenging task because of depth ambiguity and occluded joints. To relieve this limitation, we propose a Multiple Hybrid Extraction network (MHENet), which obtains three different representations of pose hypotheses features by multiple hybrid extractors with different structures, and uses pose interaction and fusion to obtain accurate 3D pose. The Hybrid Extraction Module obtains three hypotheses features: base features correspond to structural information, diverse features correspond to detail information, and condensed features correspond to action information. Hypotheses Interaction Fusion Modul builds relationships across hypotheses feature to generate more accurate 3D poses. Extensive qualitative and quantitative experimental results on a large-scale publicly available dataset demonstrate that our approach achieves competitive performance compared to state-of-the-art methods. The code will be made publicly.

关键词： 3D human pose estimation Transformer CNN encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

A FCN Approach to Blockage Correction in Radars 19

A FCN Approach to Blockage Correction in Radars

引用

6th IEEE Cyber Science and Technology Congress (CyberSciTech)

作者： Wu, Hao Liu, Qi Liu, Xiaodong Zhang, Yonghong Xu, Xiaolong Bilal, Muhammad Nanjing Univ Informat Sci & Technol Sch Comp & Software Engn Res Ctr Digital Forens Minist Educ Nanjing Peoples R China Edinburgh Napier Univ Sch Comp Edinburgh EH11 4BN Midlothian Scotland Nanjing Univ Informat Sci Technol Jiangsu Collaborat Innovat Ctr Atmospher Environm Nanjing Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing Peoples R China Hankuk Univ Foreign Studies Dept Comp & Elect Syst Engn Seoul South Korea

ISBN: (纸本)9781665421744

Doppler weather radar is the most widely used convection detector with the highest resolution in the ground. Echo reflectance data from the weather radar is the key reference for the meteorological department to carry out severe convective weather forecast and early warning, quantitative precipitation estimation(QPE) and quantitative precipitation forecast(QPF). However, in the process of radar detection, it is inevitable to be affected by obstacles, ground object echo interference, radar echo attenuation and other phenomena, resulting in poor data quality of detection results. Therefore, it is very important to correct the missing or disturbed data. On the other hand, with the rapid development of artificial intelligence technology in recent years, more and more meteorological researchers begin to introduce deep learning and other machine learning methods into the research of meteorological field such as weather radar data processing. In this paper, a deep convolutional encoderdecoder network is proposed to correct the beam blocking of weather radar. In this study, the correction of radar beam blockage is regarded as an image inpainting problem. It's the first trying to use deep learning to realize the correction of radar beam blockage. Experiment shows that the method proposed in this paper is significantly better than the traditional method in accuracy, error rate, false alarm rate and other aspects. The method can directly identify and correct the blocking area, and the operation procedure is simple compared traditional methods.

关键词： Deep learning convolutional neural networks encoder-decoder network weather radar image inpainting blockage correction

来源：评论

学校读者我要写书评

暂无评论

Self-attentive Pyramid network for Single Image De-raining 26th

Self-attentive Pyramid Network for Single Image De-raining

引用

26th International Conference on Neural Information Processing (ICONIP) of the Asia-Pacific-Neural-network-Society (APNNS)

作者： Guo, Taian Dai, Tao Li, Jiawei Xia, Shu-Tao Tsinghua Univ Grad Sch Shenzhen Shenzhen 518055 Guangdong Peoples R China Peng Cheng Lab PCL Res Ctr Networks & Commun Shenzhen 518055 Guangdong Peoples R China

ISBN: (纸本)9783030367084;9783030367077

Rain Streaks in a single image can severely damage the visual quality, and thus degrade the performance of current computer vision algorithms. To remove the rain streaks effectively, plenty of CNN-based methods have recently been developed, and obtained impressive performance. However, most existing CNN-based methods focus on network design, while rarely exploits spatial correlations of feature. In this paper, we propose a deep self-attentive pyramid network (SAPN) for more powerful feature expression for single image de-raining. Specifically, we propose a self-attentive pyramid module (SAM), which consists of convolutional layers enhanced by self-attention calculation units (SACUs) to capture the abstraction of image contents, and deconvolutional layers to upsample the feature maps and recover image details. Besides, we propose self-attention based skip connections to symmetrically link convolutional and deconvolutional layers to exploit spatial contextual information better. To model rain streaks with various scales and shapes, a multi-scale pooling (MSP) module is also introduced to efficiently leverage features from different scales. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of our proposed method in terms of both quantitative and visual quality.

关键词： Rain streak removal encoder-decoder network Self-attention

来源：评论

学校读者我要写书评

暂无评论

EANET: EFFICIENT ATTENTION-AUGMENTED network FOR REAL-TIME SEMANTIC SEGMENTATION 29

EANET: EFFICIENT ATTENTION-AUGMENTED NETWORK FOR REAL-TIME S...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Dong, Jianan Guo, Jichang Yue, Huihui Gao, Huan Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Real-time semantic segmentation plays a significant role in many real-world applications. However, existing methods usually neglect the importance of aggregating global scene clues and multi-level semantics due to computational limits of mobile devices. To address the above challenges and maintain higher accuracy, we propose an efficient attention-augmented network, namely EANet. Specifically, we first leverage an extremely lightweight attention module called sparse strip attention module (SSAM) to retain global contextual information while greatly reducing computation cost. Moreover, the meticulously designed joint attention fusion module (JAFM) follows an attention strategy to efficiently integrate semantics and details from multi-level features. On Cityscapes test set, our network achieves 74.6% mIoU at 35.4 FPS on a single GTX1080Ti GPU with a 1024x2048-pixel image. Extensive experiments show that our EANet achieves promising results on Cityscapes dataset.

关键词： Real-time Semantic Segmentation Attention Mechanism encoder-decoder network Multi-level Features

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18页 << < 9 10 11 12 13 14 15 16 17 18 > >>

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：