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

543 篇 期刊文献
335 篇 会议
15 篇 学位论文
1 册 图书

馆藏范围

894 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

839 篇 工学
- 565 篇 计算机科学与技术...
- 319 篇 电气工程
- 130 篇 软件工程
- 87 篇 信息与通信工程
- 77 篇 控制科学与工程
- 57 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...
- 32 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 交通运输工程
- 9 篇 力学（可授工学、理...
- 9 篇 材料科学与工程（可...
- 8 篇 建筑学
185 篇 理学
- 81 篇 物理学
- 47 篇 地球物理学
- 35 篇 生物学
- 26 篇 化学
- 12 篇 数学
170 篇 医学
- 129 篇 临床医学
- 25 篇 基础医学(可授医学...
- 21 篇 特种医学
59 篇 管理学
- 54 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

894 篇 encoder-decoder
159 篇 deep learning
80 篇 attention mechan...
60 篇 attention
54 篇 semantic segment...
46 篇 lstm
46 篇 feature extracti...
36 篇 transformer
35 篇 decoding
35 篇 convolutional ne...
32 篇 cnn
24 篇 semantics
22 篇 image captioning
22 篇 u-net
21 篇 speech recogniti...
21 篇 convolutional ne...
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 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 ling zhen-hua
4 篇 xu fang
4 篇 jiao licheng
4 篇 toshniwal shubha...

语言

832 篇 英文
31 篇 中文
29 篇 其他
3 篇 法文
1 篇 德文
1 篇 俄文

检索条件"主题词=Encoder-decoder"

共 894 条记录，以下是111-120 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：

Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based encoder-decoder ASR 23

Internal Language Model Estimation Through Explicit Context ...

引用

Interspeech Conference

作者： Liu, Yufei Ma, Rao Xu, Haihua He, Yi Ma, Zejun Zhang, Weibin ByteDance AI LAB Beijing Peoples R China South China Univ Technol Guangzhou Peoples R China

An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log-likelihood produced by the ILM has to be accurately estimated and subtracted. In this paper we propose two novel approaches to estimate the ILM based on the Listen-Attend-Spell (LAS) framework. The first method is to replace the context vector of the LAS decoder at every time step with a vector that is learned with the training transcripts. The second approach is to use a lightweight feed-forward network to directly map query vectors to context vectors in a dynamic sense. Since the context vectors are learned by minimizing the perplexities on the training transcripts, and their estimation is independent of the encoder output, hence the ILMs are accurately learned for both methods. Experiments show that the ILMs achieve the lowest perplexity, indicating the efficacy of the proposed methods. In addition, they also significantly outperform the shallow fusion method, as well as two previously proposed ILM Estimation (ILME) approaches on several datasets.

关键词： speech recognition language model attention-based encoder-decoder internal language model estimation

来源：评论

学校读者我要写书评

暂无评论

Confidence measures in encoder-decoder models for speech recognition 21

Confidence measures in encoder-decoder models for speech rec...

引用

Interspeech Conference

作者： Woodward, Alejandro Bonnin, Clara Masuda, Issey Varas, David Bou-Balust, Elisenda Riveiro, Juan Carlos Vilynx Menlo Pk CA 94025 USA

ISBN: (纸本)9781713820697

Recent improvements in Automatic Speech Recognition (ASR) systems have enabled the growth of myriad applications such as voice assistants, intent detection, keyword extraction and sentiment analysis. These applications, which are now widely used in the industry, are very sensitive to the errors generated by ASR systems. This could be overcome by having a reliable confidence measurement associated to the predicted output. This work presents a novel method which uses internal neural features of a frozen ASR model to train an independent neural network to predict a softmax temperature value. This value is computed in each decoder time step and multiplied by the logits in order to redistribute the output probabilities. The resulting softmax values corresponding to predicted tokens constitute a more reliable confidence measure. Moreover, this work also studies the effect of teacher forcing on the training of the proposed temperature prediction module. The output confidence estimation shows an improvement of -25.78% in EER and +7.59% in AUC-ROC with respect to the unaltered softmax values of the predicted tokens, evaluated on a proprietary dataset consisting on News and Entertainment videos.

关键词： speech recognition encoder-decoder confidence

来源：评论

学校读者我要写书评

暂无评论

Transformer encoder-decoder with depth-wise separable convolution for Low-Dose CT Denoising 5

Transformer Encoder-Decoder with depth-wise separable convol...

引用

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

作者： Guo, Weizhen Yuan, Huaqiang Li, Yakang Li, Jianfang Dongguan Univ Technol Sch Comp Dongguan Peoples R China Chinese Acad Sci Inst High Energy Phys Beijing Peoples R China Spallat Neutron Source Sci Ctr Dongguan Peoples R China

ISBN: (纸本)9798350386783;9798350386776

Low-dose computed tomography ( LDCT) images frequently suffer from noise and artifacts due to diminished radiation doses, challenging the diagnostic integrity of the images. We introduce an innovative approach, the Transformer encoder-decoder with Depth-wise Separable Convolution (ECformer), which incorporates depth-wise separable convolution into the Transformer architecture. This synergistic fusion of convolutional neural network (CNN) and Transformer capabilities notably enhances spatial information capture while concurrently mitigating computational demands. Specifically, depth-wise separable convolution supplants traditional linear projection within the Transformer, facilitating efficient learning of local contextual dynamics. Further, the adoption of an encoder-decoder architecture bolsters the hierarchical feature representation, with shortcut connections ensuring the preservation of detail. Empirical evaluations on the AAPM-Mayo Clinic Low-Dose CT Grand Challenge Dataset confirm that ECformer outperforms existing denoising methods.

关键词： LDCT denoising transformer depth-wise separable convolution encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Human Action Recognition with A Physics-Augmented encoder-decoder Network 13

Skeleton-Based Human Action Recognition with A Physics-Augme...

引用

Conference on Geospatial Informatics XIII

作者： Guo, Hongji Aved, Alexander Roller, Collen Ardiles-Cruz, Erika Ji, Qiang Rensselaer Polytech Inst Troy NY 12180 USA Air Force Res Lab Rome NY 13441 USA

ISBN: (数字)9781510661653

ISBN: (纸本)9781510661646;9781510661653

Human action recognition is important for many applications such as surveillance monitoring, safety, and health-care. As 3D body skeletons can accurately characterize body actions and are robust to camera views, we propose a 3D skeleton-based human action method. Different from the existing skeleton-based methods that use only geometric features for action recognition, we propose a physics-augmented encoder and decoder model that produces physically plausible geometric features for human action recognition. Specifically, given the input skeleton sequence, the encoder performs a spatiotemporal graph convolution to produce spatiotemporal features for both predicting human actions and estimating the generalized positions and forces of body joints. The decoder, implemented as an ODE solver, takes the joint forces and solves the Euler-Lagrangian equation to reconstruct the skeletons in the next frame. By training the model to simultaneously minimize the action classification and the 3D skeleton reconstruction errors, the encoder is ensured to produce features that are consistent with both body skeletons and the underlying body dynamics as well as being discriminative. The physics-augmented spatiotemporal features are used for human action classification. We evaluate the proposed method on NTU-RGB+D, a large-scale dataset for skeleton-based action recognition. Compared with existing methods, our method achieves higher accuracy and better generalization ability.

关键词： Skeleton-based action recognition physics encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Wound Semantic Segmentation Framework with encoder- decoder Architecture 4

Wound Semantic Segmentation Framework with Encoder- Decoder ...

引用

4th IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI)

作者： Jiang, Wenda Gao, Zhen Brahim, Wael McMaster Univ W Booth Sch Engn Practice & Technol Fac Engn Hamilton ON Canada

ISBN: (纸本)9798350374353;9798350374346

Medical Image Segmentation Framework (MISEG) is proposed on this study to efficiently streamline the image segmentation challenge in the medical fields. While many existing study related to the medical image segmentation are focusing on the algorithms of accurate segmentation, we expanded our scope to integrate the life cycle of machine learning into medical image segmentation. Under the proposed MISEG framework, we leveraged the encoder-decoder model to participate the recent DFUC2022 foot ulcer image segmentation challenge. In this challenge, we have recorded an outstanding accuracy of 0.7501 in IoU score, despite only utilizing 80% of the training data.

关键词： medical image encoder-decoder semantic segmentation framework

来源：评论

学校读者我要写书评

暂无评论

Robust Beam Search for encoder-decoder Attention Based Speech Recognition without Length Bias 21

Robust Beam Search for Encoder-Decoder Attention Based Speec...

引用

Interspeech Conference

作者： Zhou, Wei Schluter, Ralf Ney, Hermann Rhein Westfal TH Aachen Human Language Technol & Pattern Recognit Comp Sci Dept D-52074 Aachen Germany AppTek GmbH D-52062 Aachen Germany

ISBN: (纸本)9781713820697

As one popular modeling approach for end-to-end speech recognition, attention-based encoder-decoder models are known to suffer the length bias and corresponding beam problem. Different approaches have been applied in simple beam search to ease the problem, most of which are heuristic-based and require considerable tuning. We show that heuristics are not proper modeling refinement, which results in severe performance degradation with largely increased beam sizes. We propose a novel beam search derived from reinterpreting the sequence posterior with an explicit length modeling. By applying the reinterpreted probability together with beam pruning, the obtained final probability leads to a robust model modification, which allows reliable comparison among output sequences of different lengths. Experimental verification on the LibriSpeech corpus shows that the proposed approach solves the length bias problem without heuristics or additional tuning effort. It provides robust decision making and consistently good performance under both small and very large beam sizes. Compared with the best results of the heuristic baseline, the proposed approach achieves the same WER on the 'clean' sets and 4% relative improvement on the 'other' sets. We also show that it is more efficient with the additional derived early stopping criterion.

关键词： speech recognition encoder-decoder beam search length bias

来源：评论

学校读者我要写书评

暂无评论

DENSIFICATION OF AIRBORNE LIDAR POINT CLOUD WITH FUSED encoder-decoder NETWORKS

DENSIFICATION OF AIRBORNE LIDAR POINT CLOUD WITH FUSED ENCOD...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Wang, Weimin Vinayaraj, Poliyapram Nakamura, Ryosuke Natl Inst Adv Ind Sci & Technol Tokyo Japan AIST Tokyo Tech Real World Big Data Computat Open Tokyo Japan

ISBN: (纸本)9781728163741

This paper presents a density enhancement method for airborne LiDAR point cloud with the corresponding image based on a fused encoder-decoder network. Different from terrestrial indoor or outdoor scenes, the variance of objects and depth ranges in the large scale airborne data is challenging. To address the problem of objects at different scales, we propose a RGB and depth fused encoder-decoder structure inspired by UNet. In addition, we propose a heuristic method for refining the result if instance segmentation labels are available. Both quantitative and qualitative evaluations are performed on a dataset covering 24km(2) area of Osaka in Japan validates the feasibility of the proposed method for densification of point cloud in large scale environment.

关键词： Densification Airborne LiDAR Point cloud UNet encoder-decoder Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Automatic Generation of Chinese Couplets with Attention Based encoder-decoder Model 2

Automatic Generation of Chinese Couplets with Attention Base...

引用

2nd IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR)

作者： Yuan, Shengqiong Zhong, Luo Li, Lin Zhang, Rui Wuhan Univ Technol Sch Comp Sci & Technol Wuhan Hubei Peoples R China

ISBN: (纸本)9781728111988

Chinese couplets, as one of the traditional Chinese culture, is the treasure of Chinese civilization and the inheritance of Chinese history. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Because of the complexity of the semantic and grammatical rules of couplet, it is not easy to create a suitable couplet that meets the requirements of sentence pattern, context, and flatness. In this paper, given the issued antecedent clause, we can automatically generate the subsequent clause by encoder-decoder model. Moreover, to satisfy special characteristics of couplets, we incorporate the attention mechanism into the encoding-decoding process, which greatly improves the accuracy of couplets generated automatically.

关键词： Deep learning Recurrent Neural Network attention encoder-decoder couplet

来源：评论

学校读者我要写书评

暂无评论

An Effective encoder-decoder Network for Neural Cell Bodies and Cell Nucleus Segmentation of EM Images 41

An Effective Encoder-Decoder Network for Neural Cell Bodies ...

引用

41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Jiang, Yi Xiao, Chi Li, Linlin Chen, Xi Shen, Lijun Han, Hua Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Chinese Acad Sci Ctr Excellence Brain Sci & Intelligence Technol Shanghai 200031 Peoples R China Univ Chinese Acad Sci Sch Future Technol Beijing 101408 Peoples R China

ISBN: (纸本)9781538613115

Neural systems are complicated networks connected by a large number of neurons through gap junctions and synapse. At present, for electron microscopy connectomics research, neuron structure recognition algorithms mostly focus on synapses, dendrites, axons and mitochondria, etc. However, effective methods for automatic recognition of neuronal cell bodies are rare. In this paper, we proposed an effective encoder-decoder network, which extracted segmentation features of neural cell bodies and cell nucleus by the modified residual network and pyramid module. The framework is capable of merging multi-scale contextual information and generating efficient segmentation results by integrating multilevel features. We applied this proposed network on two segmentation tasks for electron microscope (EM) images and compared it with other promising methods as U-Net and deeplab v3+. The results demonstrated that our method achieved the state-of-the-art performance on quality metrics. Finally, we visualized two intact neural cell bodies and cell nucleus to provide a close look into these fine structures.

关键词： encoder-decoder Electron Microscopy Neural Cell Bodies Cell Nucleus Image Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Multi-Head Self-Attention-based on GRU encoder-decoder Framework for Predicting Molten Iron Silicon Content 12

A Multi-Head Self-Attention-based on GRU Encoder-Decoder Fra...

引用

IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS)

作者： Cai, Yu Yang, Chunjie Lou, Siwei Zeng, Zhenyu Liao, Huanyu Zhang, Bing Zhejiang Univ Coll Control Sci & Engn Hangzhou 310013 Peoples R China Alibaba Grp Hangzhou 311121 Peoples R China

ISBN: (纸本)9798350321050

Silicon content is a significant index in the process of blast furnace ironmaking. It is used to measure the quality of molten iron *** only meets the requirements if it is too high or too low. In the production process,the silicon content in molten iron needs to be controlled within a stable *** the same time,due to the time lag, nonlinear and dynamic characteristics of blast furnace itself, it is difficult to predict the silicon content accurately. This paper proposes a multi-head self-attention-based gate recurrent unit encoder-decoder framework that can better extract global dynamic features and local features, improve prediction accuracy and pass the experimental verification.

关键词： Blast Furnace Si Content Prediction encoder-decoder Multi-Head Attention Mechanism Gate Recurrent Unit

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90页 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：