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

65 篇 期刊文献
39 篇 会议

馆藏范围

104 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

94 篇 工学
- 63 篇 计算机科学与技术...
- 34 篇 电气工程
- 13 篇 软件工程
- 12 篇 信息与通信工程
- 7 篇 控制科学与工程
- 5 篇 机械工程
- 5 篇 土木工程
- 4 篇 化学工程与技术
- 4 篇 环境科学与工程（可...
- 3 篇 仪器科学与技术
- 3 篇 测绘科学与技术
- 3 篇 石油与天然气工程
- 2 篇 动力工程及工程热...
- 2 篇 电子科学与技术（可...
- 2 篇 水利工程
- 2 篇 交通运输工程
- 1 篇 力学（可授工学、理...
- 1 篇 光学工程
23 篇 理学
- 8 篇 物理学
- 4 篇 化学
- 4 篇 地球物理学
- 3 篇 数学
- 3 篇 生物学
- 2 篇 大气科学
- 1 篇 地理学
- 1 篇 地质学
- 1 篇 系统科学
10 篇 管理学
- 9 篇 管理科学与工程(可...
8 篇 医学
- 7 篇 临床医学
4 篇 文学
- 3 篇 外国语言文学
1 篇 农学

主题

104 篇 encoder-decoder ...
19 篇 deep learning
9 篇 transformer
8 篇 convolutional ne...
6 篇 lstm
6 篇 long short-term ...
6 篇 attention mechan...
5 篇 semantic segment...
5 篇 neural networks
4 篇 dialogue system
4 篇 handwritten math...
4 篇 predictive model...
4 篇 decoding
3 篇 long short-term ...
3 篇 task analysis
3 篇 recurrent neural...
3 篇 neural network
3 篇 policy gradient
2 篇 abstractive text...
2 篇 machine translat...

机构

3 篇 peking univ wang...
2 篇 department of co...
2 篇 shanghai normal ...
1 篇 islamia univ bah...
1 篇 anhui univ sci &...
1 篇 china univ geosc...
1 篇 univ elect sci &...
1 篇 univ windsor dep...
1 篇 huanggang jinghe...
1 篇 harbin inst tech...
1 篇 harbin inst tech...
1 篇 lakehead univ so...
1 篇 waseda univ grad...
1 篇 delhi technol un...
1 篇 ntt corp ntt med...
1 篇 zhejiang univ in...
1 篇 sichuan univ col...
1 篇 tokyo univ agr &...
1 篇 univ washington ...
1 篇 dongguk univ seo...

作者

4 篇 gao liangcai
4 篇 zhao wenqi
2 篇 nakagawa masaki
2 篇 li ge
2 篇 ji yuzhu
2 篇 li nannan
2 篇 watchanan chanta...
2 篇 karn patanukhom
2 篇 zhang haijun
2 篇 huang jingjia
1 篇 zhenqi sun
1 篇 wang yiming
1 篇 atsunori ogawa
1 篇 ou zhihang
1 篇 zhu jianhua
1 篇 lai can
1 篇 nair sharika sas...
1 篇 gu zheming
1 篇 quan zhibin
1 篇 kwon oh-sang

语言

97 篇 英文
5 篇 其他
1 篇 中文

检索条件"主题词=Encoder-Decoder Model"

共 104 条记录，以下是61-70 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：

Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer 16th

Handwritten Mathematical Expression Recognition with Bidirec...

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Zhao, Wenqi Gao, Liangcai Yan, Zuoyu Peng, Shuai Du, Lin Zhang, Ziyin Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China Huawei AI Applicat Res Ctr Beijing Peoples R China

ISBN: (纸本)9783030863319

encoder-decoder models have made great progress on handwritten mathematical expression recognition recently. However, it is still a challenge for existing methods to assign attention to image features accurately. Moreover, those encoder-decoder models usually adopt RNN-based models in their decoder part, which makes them inefficient in processing long LATEX sequences. In this paper, a transformer-based decoder is employed to replace RNN-based ones, which makes the whole model architecture very concise. Furthermore, a novel training strategy is introduced to fully exploit the potential of the transformer in bidirectional language modeling. Compared to several methods that do not use data augmentation, experiments demonstrate that our model improves the ExpRate of current state-of-the-art methods on CROHME 2014 by 2.23%. Similarly, on CROHME 2016 and CROHME 2019, we improve the ExpRate by 1.92% and 2.28% respectively.

关键词： Handwritten mathematical expression recognition Transformer Bidirection encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Imputation of Missing Sensor Data 32nd

Sequence-to-Sequence Imputation of Missing Sensor Data

引用

32nd Australasian Joint Conference on Artificial Intelligence

作者： Dabrowski, Joel Janek Rahman, Ashfaqur CSIRO Data61 Brisbane Qld Australia CSIRO Data61 Hobart Tas Australia

ISBN: (纸本)9783030352882;9783030352875

Although the sequence-to-sequence (encoder-decoder) model is considered the state-of-the-art in deep learning sequence models, there is little research into using this model for recovering missing sensor data. The key challenge is that the missing sensor data problem typically comprises three sequences (a sequence of observed samples, followed by a sequence of missing samples, followed by another sequence of observed samples) whereas, the sequence-to-sequence model only considers two sequences (an input sequence and an output sequence). We address this problem by formulating a sequence-to-sequence in a novel way. A forward RNN encodes the data observed before the missing sequence and a backward RNN encodes the data observed after the missing sequence. A decoder decodes the two encoders in a novel way to predict the missing data. We demonstrate that this model produces the lowest errors in 12% more cases than the current state-of-the-art.

关键词： Imputation Interpolation LSTM encoder-decoder model Sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Emotion-Aware Transformer encoder for Empathetic Dialogue Generation 9

Emotion-Aware Transformer Encoder for Empathetic Dialogue Ge...

引用

9th International Conference on Affective Computing and Intelligent Interaction (ACII)

作者： Goel, Raman Susan, Seba Vashisht, Sachin Dhanda, Armaan Delhi Technol Univ Dept Informat Technol New Delhi 110042 India

ISBN: (纸本)9781665400213

Modern day conversational agents are trained to emulate the manner in which humans communicate. To emotionally bond with the user, these virtual agents need to be aware of the affective state of the user. Transformers are the recent state of the art in sequence-to-sequence learning that involves training an encoder-decoder model with word embeddings from utterance-response pairs. We propose an emotion-aware transformer encoder for capturing the emotional quotient in the user utterance in order to generate human-like empathetic responses. The contributions of our paper are as follows: 1) An emotion detector module trained on the input utterances determines the affective state of the user in the initial phase 2) A novel transformer encoder is proposed that adds and normalizes the word embedding with emotion embedding thereby integrating the semantic and affective aspects of the input utterance 3) The encoder and decoder stacks belong to the Transformer-XL architecture which is the recent state of the art in language modeling. Experimentation on the benchmark Facebook AI empathetic dialogue dataset confirms the efficacy of our model from the higher BLEU-4 scores achieved for the generated responses as compared to existing methods. Emotionally intelligent virtual agents are now a reality and inclusion of affect as a modality in all human-machine interfaces is foreseen in the immediate future.

关键词： Transformer-XL Empathetic dialogue generation Affective state encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

Combining CNN and Transformer as encoder to Improve End-to-End Handwritten Mathematical Expression Recognition Accuracy 18th

Combining CNN and Transformer as Encoder to Improve End-to-E...

引用

18th International Conference on Frontiers in Handwriting Recognition (ICFHR)

作者： Zhang, Zhang Zhang, Yibo Beijing Natl Day Sch 66 Yuquan Rd Beijing Peoples R China Beijing Jiaotong Univ 3 Shangyuancun Beijing Peoples R China

ISBN: (纸本)9783031216473;9783031216480

The attention-based encoder-decoder (AED) models are increasingly used in handwritten mathematical expression recognition (HMER) tasks. Given the recent success ofTransformer in computer vision and a variety of attempts to combine Transformer with convolutional neural network (CNN), in this paper, we study 3 ways of leveraging Transformer and CNN designs to improve AED-based HMER models: 1) Tandem way, which feeds CNN-extracted features to a Transformer encoder to capture global dependencies;2) Parallel way, which adds a Transformer encoder branch taking raw image patches as input and concatenates its output with CNN's as final feature;3) Mixing way, which replaces convolution layers of CNN's last stage withmulti-head self-attention (MHSA). We compared these 3 methods on the CROHME benchmark. On CROHME 2016 and 2019, Tandem way attained the ExpRate of 54.85% and 58.56%, respectively;Parallel way attained the ExpRate of 55.63% and 57.39%;and Mixing way achieved the ExpRate of 53.93% and 55.64%. This result indicates that Parallel and Tandem ways perform better than Mixing way, and have little difference between each other.

关键词： Handwritten mathematical expression recognition Transformer encoder-decoder model Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A Non-Task-Oriented Dialogue System Controlling the Utterance Length 10

A Non-Task-Oriented Dialogue System Controlling the Utteranc...

引用

Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) / 19th International Symposium on Advanced Intelligent Systems (ISIS)

作者： Isoshima, Kazuki Hagiwara, Masafumi Keio Univ Dept Informat & Comp Sci Yokohama Kanagawa Japan

ISBN: (纸本)9781538626337

In this paper, we propose a non-task-oriented dialogue system controlling the utterance length. The dialogue system can be classified into a task-oriented dialogue system or a non-task-oriented dialogue system. Recently, demand for the non-task-oriented dialogue system is increasing. The utterance length is one of the important information in a dialogue system. In general, our utterance length tends to he long when we are speakers. On the other hand, the length of our utterance tends to he short when we are listeners. In addition, the utterance length differs from person to person, so we change our utterance length for friendly communication. The effect of the utterance length has never considered in dialogue systems using encoder-decoder model. Therefore, we propose an utterance length estimator (ULE) and an index of the utterance length. ULE is a neural network which learns the utterance length by training data of dialogue. The index of the utterance length is the parameter considers user's personality and it is calculated during dialogue. Our dialogue system decides the length of system's utterance by ULE and index of the utterance length, and generates output sequences by using a neural encoder-decoder controlling output length. Experimental results show our system can decide the appropriate length of the utterance and makes users more satisfied than the conventional method.

关键词： neural network encoder-decoder model dialogue System the utterance length

来源：评论

学校读者我要写书评

暂无评论

A Neural model for Method Name Generation from Functional Description 26

A Neural Model for Method Name Generation from Functional De...

引用

26th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Gao, Sa Chen, Chunyang Xing, Zhenchang Ma, Yukun Song, Wen Lin, Shang-Wei Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Monash Univ Fac Informat Technol Clayton Vic Australia Australian Natl Univ Res Sch Comp Sci Canberra ACT Australia

ISBN: (纸本)9781728105918

The names of software artifacts, e.g., method names, are important for software understanding and maintenance, as good names can help developers easily understand others' code. However, the existing naming guidelines are difficult for developers, especially novices, to come up with meaningful, concise and compact names for the variables, methods, classes and files. With the popularity of open source, an enormous amount of project source code can be accessed, and the exhaustiveness and instability of manually naming methods could now be relieved by automatically learning a naming model from a large code repository. Nevertheless, building a comprehensive naming system is still challenging, due to the gap between natural language functional descriptions and method names. Specifically, there are three challenges: how to model the relationship between the functional descriptions and formal method names, how to handle the explosion of vocabulary when dealing with large repositories, and how to leverage the knowledge learned from large repositories to a specific project. To answer these questions, we propose a neural network to directly generate readable method names from natural language description. The proposed method is built upon the encoder-decoder framework with the attention and copying mechanisms. Our experiments show that our method can generate meaningful and accurate method names and achieve significant improvement over the state-of-the-art baseline models. We also address the cold-start problem using a training trick to utilize big data in Github for specific projects.

关键词： Naming Convention encoder-decoder model Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Training an End-to-End System for Handwritten Mathematical Expression Recognition by Generated Patterns 14

Training an End-to-End System for Handwritten Mathematical E...

引用

14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Anh Duc Le Nakagawa, Masaki Tokyo Univ Agr & Technol Dept Comp Informat Fuchu Tokyo Japan

ISBN: (纸本)9781538635865

Motivated by recent successes in neural machine translation and image caption generation, we present an end-to-end system to recognize Online Handwritten Mathematical Expressions (OHMEs). Our system has three parts: a convolution neural network for feature extraction, a bidirectional LSTM for encoding extracted features, and an LSTM and an attention model for generating target LaTex. For recognizing complex structures, our system needs large data for training. We propose local and global distortion models for generating OHMEs from the CROHME database. We evaluate the end-to-end system on the CROHME database and the generated databases. The experiential results show that the end-to-end system achieves 28.09% and 35.19% recognition rates on CROHME without and with the generated data, respectively.

关键词： Online Handwritten Mathematical Expression Recognition End-to-End model encoder-decoder model Patterns Generation

来源：评论

学校读者我要写书评

暂无评论

Temporal Classification Constraint for Improving Handwritten Mathematical Expression Recognition 16th

Temporal Classification Constraint for Improving Handwritten...

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Cuong Tuan Nguyen Hung Tuan Nguyen Morizumi, Kei Nakagawa, Masaki Tokyo Univ Agr & Technol Tokyo 1848588 Japan

ISBN: (纸本)9783030861599;9783030861582

We present a temporal classification constraint as an auxiliary learning method for improving the recognition of Handwritten Mathematical Expression (HME). Connectionist temporal classification (CTC) is used to learn the temporal alignment of the input feature sequence and corresponding symbol label sequence. The CTC alignment is trained with the encoder-decoder alignment through a combination of CTC loss and encoder-decoder loss to improve the feature learning of the encoder in the encoder-decoder model. We show the effectiveness of the approach in improving symbol classification and expression recognition on the CROHME datasets.

关键词： Temporal classification Mathematical expression encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

A Scheme for Inverse Design of Encoded Metasurfaces Supported by encoder-decoder and Generative models 16

A Scheme for Inverse Design of Encoded Metasurfaces Supporte...

引用

16th International Conference on Microwave and Millimeter Wave Technology (ICMMT)

作者： Chen, Bin Li, Da Gu, Zheming Wu, Yunlong Fan, Yudi Liu, Wenjie Wu, Jianguo Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou Peoples R China

ISBN: (纸本)9798350389968

In recent years, coding metasurfaces have become a research hotspot in the field of metasurfaces. In the traditional reverse design of coding metasurfaces, genetic algorithms (GA) combined with forward prediction networks are commonly used for optimization design, but this requires a substantial amount of time in the search process, especially for large coding metasurfaces. To conquer the time-consuming issue of genetic algorithms and to meet diverse design needs, we propose a solution of multi-branched encoder-decoder. In addition, we use Conditional Generative Adversarial Networks (cGAN) to optimize the model. While solving the non-unique mapping problem, our method negates the need for a complicated search process and can directly provide coding metasurfaces designs that meet specific targets, greatly enhancing the efficiency of the design. This method has been verified in our closed-loop simulation, providing an effective solution for the reverse design of coding metasurfaces.

关键词： Coding metasurfaces encoder-decoder model Conditional Generative Adversarial Network (cGAN)

来源：评论

学校读者我要写书评

暂无评论

Online Action Tube Detection via Resolving the Spatio-temporal Context Pattern 18

Online Action Tube Detection via Resolving the Spatio-tempor...

引用

26th ACM Multimedia Conference (MM)

作者： Huang, Jingjia Li, Nannan Zhong, Jiaxing Li, Thomas H. Li, Ge Peking Univ Sch Elect & Comp Engn Beijing Peoples R China Peking Univ Shenzhen Grad Sch Beijing Peoples R China Gpower Semicond Inc Suzhou Peoples R China

ISBN: (纸本)9781450356657

At present, spatio-temporal action detection in the video is still a challenging problem, considering the complexity of the background, the variety of the action or the change of the viewpoint in the unconstrained environment. Most of current approaches solve the problem via a two-step processing: first detecting actions at each frame;then linking them, which neglects the continuity of the action and operates in an offline and batch processing manner. In this paper, we attempt to build an online action detection model that introduces the spatio-temporal coherence existed among action regions when performing action category inference and position localization. Specifically, we seek to represent the spatio-temporal context pattern via establishing an encoder-decoder model based on the convolutional recurrent network. The model accepts a video snippet as input and encodes the dynamic information of the action in the forward pass. During the backward pass, it resolves such information at each time instant for action detection via fusing the current static or motion cue. Additionally, we propose an incremental action tube generation algorithm, which accomplishes action bounding-boxes association, action label determination and the temporal trimming in a single pass. Our model takes in the appearance, motion or fused signals as input and is tested on two prevailing datasets, UCF-Sports and UCF-101. The experiment results demonstrate the effectiveness of our method which achieves a performance superior or comparable to compared existing approaches.

关键词： Spatio-temporal action detection encoder-decoder model online action tune generation

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11页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：