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

108 篇 期刊文献
32 篇 会议

馆藏范围

140 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

133 篇 工学
- 84 篇 计算机科学与技术...
- 53 篇 电气工程
- 19 篇 信息与通信工程
- 12 篇 软件工程
- 10 篇 控制科学与工程
- 10 篇 测绘科学与技术
- 8 篇 仪器科学与技术
- 8 篇 环境科学与工程（可...
- 6 篇 水利工程
- 6 篇 生物医学工程（可授...
- 5 篇 机械工程
- 5 篇 电子科学与技术（可...
- 5 篇 土木工程
- 3 篇 光学工程
- 3 篇 材料科学与工程（可...
- 3 篇 动力工程及工程热...
- 3 篇 建筑学
- 3 篇 石油与天然气工程
- 2 篇 化学工程与技术
- 2 篇 交通运输工程
32 篇 医学
- 25 篇 临床医学
- 4 篇 基础医学(可授医学...
27 篇 理学
- 13 篇 物理学
- 7 篇 地球物理学
- 5 篇 生物学
- 3 篇 化学
- 2 篇 数学
- 2 篇 大气科学
8 篇 管理学
- 7 篇 管理科学与工程(可...
2 篇 文学
2 篇 农学
2 篇 艺术学
1 篇 法学

主题

140 篇 encoder-decoder ...
33 篇 deep learning
16 篇 semantic segment...
14 篇 attention mechan...
11 篇 feature extracti...
9 篇 convolutional ne...
7 篇 image segmentati...
6 篇 real-time semant...
6 篇 convolutional ne...
5 篇 transfer learnin...
5 篇 feature fusion
5 篇 decoding
5 篇 training
5 篇 recurrent neural...
4 篇 lstm
4 篇 image captioning
4 篇 convolution
4 篇 remote sensing
4 篇 medical image se...
3 篇 autonomous drivi...

机构

2 篇 monash univ dept...
2 篇 soochow univ sch...
2 篇 iit hyderabad hy...
2 篇 zhejiang univ sc...
2 篇 zhejiang univ in...
2 篇 king mongkuts un...
1 篇 multimedia univ ...
1 篇 nanjing univ pos...
1 篇 xiangtan univ sc...
1 篇 zhejiang univ te...
1 篇 yanshan univ qin...
1 篇 univ waterloo wa...
1 篇 the communicatio...
1 篇 national key lab...
1 篇 ningbo univ coll...
1 篇 east china univ ...
1 篇 polytech univ tu...
1 篇 kyungpook natl u...
1 篇 govt coll techno...
1 篇 natl res council...

作者

3 篇 singh maheep
3 篇 sharma gaurav
2 篇 zhou peng
2 篇 chiracharit wera...
2 篇 zhou yanlai
2 篇 zhang lei
2 篇 makwana dhruv
2 篇 corcoran peter
2 篇 xu xinmeng
2 篇 deng jianghua
2 篇 basak shubhajit
2 篇 chakraborty dipa...
2 篇 mohan c. krishna
2 篇 lu ye
2 篇 nag subhrajit
2 篇 xu chong-yu
2 篇 mittal sparsh
2 篇 zhou wujie
2 篇 khan faisal
2 篇 chamnongthai kos...

语言

137 篇 英文
3 篇 其他

检索条件"主题词=encoder-decoder architecture"

共 140 条记录，以下是91-100 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：

Self-Learned Feature Reconstruction and Offset-Dilated Feature Fusion for Real-Time Semantic Segmentation 31

Self-Learned Feature Reconstruction and Offset-Dilated Featu...

引用

31st IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

作者： Qi, Gege Pan, Lin Liu, Song Luo, Zhengding Zhu, Yuesheng Peking Univ Shenzhen Grad Sch Commun & Informat Secur Lab Shenzhen Peoples R China

ISBN: (纸本)9781728137988

Recent approaches for real-time semantic segmentation usually employ the encoder-decoder architecture as the backbone to generate a high-quality segmentation prediction. There has been a lot of research on designing efficient encoding methods. However, enhancing the performance of components in decoder is also crucial for pixel-level recognition. In this paper, we propose a self-learned feature reconstruction (SFR) method and an offset-dilated feature fusion (ODFF) module to improve the prediction reconstruction capability of the decoder. Concretely, SFR can effectively reconstruct the high-resolution feature maps by recombining feature space, in which the space transformation matrix implicitly contained in a convolution layer can selectively highlight features at each position by leveraging the knowledge of label space in a self-learned way. Moreover, ODFF module can effectively fuse multilevel features with multiscale contextual information by feeding the feature maps into designed parallel offset-dilated convolutions, which enhances the feature representation capability of the decoder. Experiments on Cityscapes and CamVid datasets demonstrate the superior performance of our proposed methods embedded in ESPNet.

关键词： real-time semantic segmentation encoder-decoder architecture feature reconstruction feature fusion

来源：评论

学校读者我要写书评

暂无评论

Upsampling Matters for Road Marking Segmentation of Autonomous Driving 3rd

Upsampling Matters for Road Marking Segmentation of Autonomo...

引用

3rd IFAC Workshop pn Cyber-Physical and Human Systems (CPHS)

作者： Liu, Ye Zhang, Xi Liu, Lei Zhang, Lei Shanghai Jiao Tong Univ Sch Mech Engn Shanghai Peoples R China CSSC Beijing Peoples R China

Although autonomous driving have become applicable to the industry, the prevalent application of key techniques to the autonomous vehicles still needs to be refined. For instance, how to fast and accurately segment road markings in order to assist the next pedestrian path prediction and the creation of high-definition (HD) map respectively is useful for autonomous driving to be more practical. Current road marking segmentation mainly rely on the techniques of semantic segmentation of computer vision with encoder-decoder architecture. However, as demonstrated in this paper, the upsampling layer of convolutional neural networks with encoder-decoder architecture plays a significant role in the efficiency and accuracy of the road marking segmentation. The bilinear upsampling layer is fast due to its intrinsic simple interpolation but with less accuracy;on the contrary, the upsampling layer with offsets is relatively accurate but with more computational cost. Therefore, at least, in terms of prevalent application, efficiency, and accuracy, the upsampling layer of decoder of convolution neural networks should be paid more attention to for the next research work of autonomous driving. Copyright (C) 2020 The Authors.

关键词： Semantic Segmentation Upsampling encoder-decoder architecture Road Marking Autonomous Driving

来源：评论

学校读者我要写书评

暂无评论

Image Caption via Visual Attention Switch on DenseNet 6

Image Caption via Visual Attention Switch on DenseNet

引用

6th IEEE International Conference on Network Infrastructure and Digital Content (IEEE IC-NIDC)

作者： Hao, Yanlong Xie, Jiyang Lin, Zhiqing Beijing Univ Posts & Telecommun Pattern Recognit & Intelligent Syst Lab Beijing 100876 Peoples R China

ISBN: (纸本)9781538660676

We introduce a novel approach that is used to convert images into the corresponding language descriptions. This method follows the most popular encoder-decoder architecture. The encoder uses the recently proposed densely convolutional neural network (DenseNet) to extract the feature maps. Meanwhile, the decoder uses the long short time memory (LSTM) to parse the feature maps to descriptions. We predict the next word of descriptions by taking the effective combination of feature maps with word embedding of current input word by "visual attention switch". Finally, we compare the performance of the proposed model with other baseline models and achieve good results.

关键词： Image caption Visual attention switch encoder-decoder architecture DenseNet LSTM

来源：评论

学校读者我要写书评

暂无评论

Solving Machine Learning Problems 13

Solving Machine Learning Problems

引用

13th Asian Conference on Machine Learning (ACML)

作者： Tran, Sunny Krishna, Pranav Pakuwal, Ishan Kafle, Prabhakar Singh, Nikhil Lynch, Jayson Drori, Iddo MIT EECS Cambridge MA 02139 USA MIT Media Lab Cambridge MA 02139 USA Univ Waterloo Waterloo ON Canada

Can a machine learn Machine Learning? This work trains a machine learning model to solve machine learning problems from a University undergraduate level course. We generate a new training set of questions and answers consisting of course exercises, homework, and quiz questions from MIT's 6.036 Introduction to Machine Learning course and train a machine learning model to answer these questions. Our system demonstrates an overall accuracy of 96% for open-response questions and 97% for multiple-choice questions, compared with MIT students' average of 93%, achieving grade A performance in the course, all in real-time. Questions cover all 12 topics taught in the course, excluding coding questions or questions with images. Topics include: (i) basic machine learning principles;(ii) perceptrons;(iii) feature extraction and selection;(iv) logistic regression;(v) regression;(vi) neural networks;(vii) advanced neural networks;(viii) convolutional neural networks;(ix) recurrent neural networks;(x) state machines and MDPs;(xi) reinforcement learning;and (xii) decision trees. Our system uses Transformer models within an encoder-decoder architecture with graph and tree representations. An important aspect of our approach is a data-augmentation scheme for generating new example problems. We also train a machine learning model to generate problem hints. Thus, our system automatically generates new questions across topics, answers both open-response questions and multiple-choice questions, classifies problems, and generates problem hints, pushing the envelope of AI for STEM education.

关键词： Learning to learn Machine Learning course Transformers Graph neural network Expression trees encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

ATU-NET: AN ADAPTIVE TRANSFORMATION-BASED U-NET FOR MEDICAL IMAGE SEGMENTATION 31

ATU-NET: AN ADAPTIVE TRANSFORMATION-BASED U-NET FOR MEDICAL ...

引用

2024 International Conference on Image Processing

作者： Du, Qianyu Zhong, Baojiang Ma, Kai-Kuang Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Elect & Informat Engn Coll Integrated Circuits Nanjing Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Both the U-Net and its variants, which produce the state-of-the-art performance in the field of medical image segmentation, are founded on an encoder-decoder architecture. However, this architecture generally processes the input image in the spatial domain only, overlooking potential insights that could be gained from other transform domains. For that, an adaptive transformation-based U-Net (ATU-Net) is proposed in this paper. Our ATU-Net is based on a novel network architecture called the adaptive transformation-encoder-decoder (ATU), which adaptively transforms the input image into a more suitable domain by training the transformation kernel for processing to make it easier for the encoder and decoder to extract key features of the image. Extensive experimental results obtained on benchmark datasets have shown that our proposed ATU-Net can deliver superior performance to the existing methods.

关键词： Deep learning medical image segmentation transform domain encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

GLD-Net: Improving Monaural Speech Enhancement by Learning Global and Local Dependency Features with GLD Block 23

GLD-Net: Improving Monaural Speech Enhancement by Learning G...

引用

Interspeech Conference

作者： Xu, Xinmeng Wang, Yang Jia, Jie Chen, Binbin Hao, Jianjun Trinity Coll Dublin Elect & Elect Engn Dublin Ireland Vivo AI Lab Shenzhen Peoples R China Hubei Univ Chinese Med Sch Foreign Languages Wuhan Peoples R China

For monaural speech enhancement, contextual information is important for accurate speech estimation. However, commonly used convolution neural networks (CNNs) are weak in capturing temporal contexts since they only build blocks that process one local neighborhood at a time. To address this problem, we learn from human auditory perception to introduce a two-stage trainable reasoning mechanism, referred as global-local dependency (GLD) block. GLD blocks capture long-term dependency of time-frequency bins both in global level and local level from the noisy spectrogram to help detecting correlations among speech part, noise part, and whole noisy input. What is more, we conduct a monaural speech enhancement network called GLD-Net, which adopts encoder-decoder architecture and consists of speech object branch, interference branch, and global noisy branch. The extracted speech feature at global-level and local-level are efficiently reasoned and aggregated in each of the branches. We compare the proposed GLD-Net with existing state-of-art methods on WSJ0 and DEMAND dataset. The results show that GLD-Net outperforms the state-of-the-art methods in terms of PESQ and STOI.

关键词： monaural speech enhancement global and local dependency encoder-decoder architecture two-stage trainable reasoning mechanism

来源：评论

学校读者我要写书评

暂无评论

SIMULTANEOUS SEGMENTATION AND CLASSIFICATION OF BIRD SONG USING CNN

SIMULTANEOUS SEGMENTATION AND CLASSIFICATION OF BIRD SONG US...

引用

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

作者： Narasimhan, Revathy Fern, Xiaoli Z. Raich, Raviv Oregon State Univ Sch EECS Corvallis OR 97331 USA

ISBN: (纸本)9781509041176

In bioacoustics, automatic animal voice detection and recognition from audio recordings is an emerging topic for animal preservation. Our research focuses on bird bioacoustics, where the goal is to segment bird syllables from the recording and predict the bird species for the syllables. Traditional methods for this task addresses the segmentation and species prediction separately, leading to propagated errors. This work presents a new approach that performs simultaneous segmentation and classification of bird species using a Convolutional Neural Network (CNN) with encoder-decoder architecture. Experimental results on bird recordings show significant improvement compared to recent state-of-the-art methods for both segmentation and species classification.

关键词： Convolutional Neural Network encoder-decoder architecture bioacoustic species classification

来源：评论

学校读者我要写书评

暂无评论

LocalBins: Improving Depth Estimation by Learning Local Distributions 17th

LocalBins: Improving Depth Estimation by Learning Local Dist...

引用

17th European Conference on Computer Vision (ECCV)

作者： Bhat, Shariq Farooq Alhashim, Ibraheem Wonka, Peter KAUST Thuwal Saudi Arabia Saudi Data & Artificial Intelligence Authority SD Natl Ctr Artificial Intelligence NCAI Riyadh Saudi Arabia

ISBN: (纸本)9783031197680;9783031197697

We propose a novel architecture for depth estimation from a single image. The architecture itself is based on the popular encoder-decoder architecture that is frequently used as a starting point for all dense regression tasks. We build on AdaBins which estimates a global distribution of depth values for the input image and evolve the architecture in two ways. First, instead of predicting global depth distributions, we predict depth distributions of local neighborhoods at every pixel. Second, instead of predicting depth distributions only towards the end of the decoder, we involve all layers of the decoder. We call this new architecture LocalBins. Our results demonstrate a clear improvement over the state-of-the-art in all metrics on the NYU-Depth V2 dataset. Code and pretrained models will be made publicly available (https://***/sharigfarooq123/LocalBins).

关键词： Single image depth estimation encoder-decoder architecture Deep learning Dense regression Histogram prediction

来源：评论

学校读者我要写书评

暂无评论

ABSTRACTIVE HEADLINE GENERATION FOR SPOKEN CONTENT BY ATTENTIVE RECURRENT NEURAL NETWORKS WITH ASR ERROR MODELING

ABSTRACTIVE HEADLINE GENERATION FOR SPOKEN CONTENT BY ATTENT...

引用

IEEE Workshop on Spoken Language Technology (SLT)

作者： Yu, Lang-Chi Lee, Hung-yi Lee, Lin-shan Natl Taiwan Univ Grad Inst Commun Engn Taipei Taiwan Natl Taiwan Univ Grad Inst Comp Sci & Informat Engn Taipei Taiwan

ISBN: (纸本)9781509049035

Headline generation for spoken content is important since spoken content is difficult to be shown on the screen and browsed by the user. It is a special type of abstractive summarization, for which the summaries are generated word by word from scratch without using any part of the original content. Many deep learning approaches for headline generation from text document have been proposed recently, all requiring huge quantities of training data, which is difficult for spoken document summarization. In this paper, we propose an ASR error modeling approach to learn the underlying structure of ASR error patterns and incorporate this model in an Attentive Recurrent Neural Network (ARNN) architecture. In this way, the model for abstractive headline generation for spoken content can be learned from abundant text data and the ASR data for some recognizers. Experiments showed very encouraging results and verified that the proposed ASR error model works well even when the input spoken content is recognized by a recognizer very different from the one the model learned from.

关键词： abstractive summarization headline generation ASR error modeling attention mechanism encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

CRVOS: CLUE REFINING NETWORK FOR VIDEO OBJECT SEGMENTATION

CRVOS: CLUE REFINING NETWORK FOR VIDEO OBJECT SEGMENTATION

引用

IEEE International Conference on Image Processing (ICIP)

作者： Cho, Suhwan Cho, MyeongAh Chung, Tae-young Lee, Heansung Lee, Sangyoun Yonsei Univ Seoul South Korea

ISBN: (纸本)9781728163956

The encoder-decoder based methods for semi-supervised video object segmentation (Semi-VOS) have received extensive attention due to their superior performances. However, most of them have complex intermediate networks which generate strong specifiers to be robust against challenging scenarios, and this is quite inefficient when dealing with relatively simple scenarios. To solve this problem, we propose a real-time network, Clue Refining Network for Video Object Segmentation (CRVOS), that does not have any intermediate network to efficiently deal with these scenarios. In this work, we propose a simple specifier, referred to as the Clue, which consists of the previous frame's coarse mask and coordinates information. We also propose a novel refine module which shows the better performance compared with the general ones by using a deconvolution layer instead of a bilinear upsampling layer. Our proposed method shows the fastest speed among the existing methods with a competitive accuracy. On DAVIS 2016 validation set, our method achieves 63.5 fps and J&F score of 81.6%.

关键词： Video object segmentation Real-time tracker encoder-decoder architecture

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14页 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：