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

52 篇 期刊文献
25 篇 会议

馆藏范围

77 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

73 篇 工学
- 46 篇 计算机科学与技术...
- 27 篇 电气工程
- 11 篇 软件工程
- 7 篇 信息与通信工程
- 6 篇 控制科学与工程
- 5 篇 电子科学与技术（可...
- 4 篇 测绘科学与技术
- 4 篇 交通运输工程
- 3 篇 水利工程
- 3 篇 生物医学工程（可授...
- 2 篇 机械工程
- 2 篇 仪器科学与技术
- 2 篇 土木工程
- 2 篇 环境科学与工程（可...
- 1 篇 力学（可授工学、理...
- 1 篇 材料科学与工程（可...
- 1 篇 动力工程及工程热...
- 1 篇 石油与天然气工程
- 1 篇 纺织科学与工程
- 1 篇 航空宇航科学与技...
11 篇 理学
- 6 篇 地球物理学
- 4 篇 物理学
- 1 篇 化学
- 1 篇 地理学
9 篇 医学
- 5 篇 临床医学
9 篇 管理学
- 8 篇 管理科学与工程(可...
1 篇 法学
- 1 篇 社会学
1 篇 文学
- 1 篇 外国语言文学
1 篇 农学

主题

77 篇 encoder-decoder ...
12 篇 image captioning
11 篇 attention mechan...
8 篇 deep learning
5 篇 decoding
5 篇 feature extracti...
4 篇 natural language...
4 篇 cnn
3 篇 reinforcement le...
3 篇 video captioning
2 篇 transformer
2 篇 semantic segment...
2 篇 lstm
2 篇 deep neural netw...
2 篇 task analysis
2 篇 remote sensing i...
2 篇 transformers
2 篇 image segmentati...
2 篇 retrieval based ...
2 篇 efficientnet

机构

3 篇 tianjin univ col...
3 篇 univ sci & techn...
2 篇 univ sci & techn...
2 篇 hohai univ natl ...
2 篇 hohai univ yangt...
2 篇 tianjin univ sch...
2 篇 hunan univ coll ...
2 篇 hohai univ coll ...
1 篇 univ sci & techn...
1 篇 univ texas dept ...
1 篇 xijing univ sch ...
1 篇 karlsruhe inst t...
1 篇 abdelmalek essaa...
1 篇 nanjing univ dep...
1 篇 nanjing univ pos...
1 篇 zhejiang univ co...
1 篇 prince sultan un...
1 篇 china electric p...
1 篇 chinese acad sci...
1 篇 univ chinese aca...

作者

3 篇 zhang ke
2 篇 xu teng
2 篇 wei haiyang
2 篇 liu jiadong
2 篇 wang wenwu
2 篇 lu chunhui
2 篇 zhang canlong
2 篇 abdussalam amr
2 篇 ye zhongfu
2 篇 hu qinghua
2 篇 li zhixin
2 篇 plumbley mark d.
1 篇 jiqing yao
1 篇 chaudhary gopal
1 篇 ge yisu
1 篇 ma lin
1 篇 xue youtao
1 篇 lian jing
1 篇 matthew martianu...
1 篇 hawbani ammar

语言

76 篇 英文
1 篇 其他

检索条件"主题词=encoder-decoder framework"

共 77 条记录，以下是51-60 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：

Recurrent Fusion Network for Image Captioning 15th

Recurrent Fusion Network for Image Captioning

引用

15th European Conference on Computer Vision (ECCV)

作者： Jiang, Wenhao Ma, Lin Jiang, Yu-Gang Liu, Wei Zhang, Tong Tencent AI Lab Shenzhen Peoples R China Fudan Univ Shanghai Peoples R China

ISBN: (纸本)9783030012168;9783030012151

Recently, much advance has been made in image captioning, and an encoder-decoder framework has been adopted by all the state-of-the-art models. Under this framework, an input image is encoded by a convolutional neural network (CNN) and then translated into natural language with a recurrent neural network (RNN). The existing models counting on this framework employ only one kind of CNNs, e.g., ResNet or Inception-X, which describes the image contents from only one specific view point. Thus, the semantic meaning of the input image cannot be comprehensively understood, which restricts improving the performance. In this paper, to exploit the complementary information from multiple encoders, we propose a novel recurrent fusion network (RFNet) for the image captioning task. The fusion process in our model can exploit the interactions among the outputs of the image encoders and generate new compact and informative representations for the decoder. Experiments on the MSCOCO dataset demonstrate the effectiveness of our proposed RFNet, which sets a new state-of-the-art for image captioning.

关键词： Image captioning encoder-decoder framework Recurrent fusion network (RFNet)

来源：评论

学校读者我要写书评

暂无评论

Image Captioning Based on Visual and Semantic Attention 26th

Image Captioning Based on Visual and Semantic Attention

引用

26th International Conference on MultiMedia Modeling (MMM)

作者： Wei, Haiyang Li, Zhixin Zhang, Canlong Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China

ISBN: (纸本)9783030377311;9783030377304

Most of the existing image captioning methods only use the visual information of the image to guide the generation of the captions, lack the guidance of effective scene semantic information, and the current visual attention mechanism cannot adjust the focus intensity on the image. In this paper, we first propose an improved visual attention model. At each time step, we calculate the focus intensity coefficient of the attention mechanism through the context information of the model, and automatically adjust the focus intensity of the attention mechanism through the coefficient, so as to extract more accurate image visual information. In addition, we represent the scene semantic information of the image through some topic words related to the image scene, and add them to the language model. We use attention mechanism to determine the image visual information and scene semantic information that the model pays attention to at each time step, and combine them to guide the model to generate more accurate and scene-specific captions. Finally, we evaluate our model on MSCOCO dataset. The experimental results show that our approach can generate more accurate captions, and outperforms many recent advanced models on various evaluation metrics.

关键词： Image captioning Visual attention Scene semantics encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Encoding Emotional Information for Sequence-to-Sequence Response Generation

Encoding Emotional Information for Sequence-to-Sequence Resp...

引用

International Conference on Artificial Intelligence and Big Data (ICAIBD)

作者： Chan, Yin Hei Lui, Andrew Kwok Fai Open Univ Hong Kong Comp Sch Sci & Technol Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781538669877

This paper introduces an alternative approach on embedding emotional information at the encoder stage of a sequence-to-sequence based emotional response generation. It explores different positioning and styles of the embedding, which represent associations of emotion with specific words or the whole sentence. The experiment was set up with standard dataset as well as dataset annotated with emotional classifiers. Preliminary results showed that this new approach should better represent sentence level emotional and work well with standard Recurrent Neural network (RNN) with Long Short Term Memory (LSTM) architecture.

关键词： chatbots conversational agents long short term memory recurrent neural network encoder-decoder framework emotional response

来源：评论

学校读者我要写书评

暂无评论

Talking Face Generation with Expression-Tailored Generative Adversarial Network 20

Talking Face Generation with Expression-Tailored Generative ...

引用

28th ACM International Conference on Multimedia (MM)

作者： Zeng, Dan Liu, Han Lin, Hui Ge, Shiming Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China LAIX Inc Shanghai 200082 Peoples R China Shanghai Key Lab Artificial Intelligence Learning Shanghai 200082 Peoples R China Chinese Acad Sci Inst Informat Engn Beijing 100095 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China

ISBN: (纸本)9781450379885

A key of automatically generating vivid talking faces is to synthesize identity-preserving natural facial expressions beyond audio-lip synchronization, which usually need to disentangle the informative features from multiple modals and then fuse them together. In this paper, we propose an end-to-end Expression-Tailored Generative Adversarial Network (ET-GAN) to generate an expression enriched talking face video of arbitrary identity. Different from talking face generation based on identity image and audio, an expressional video of arbitrary identity serves as the expression source in our approach. Expression encoder is proposed to disentangle expression-tailored representation from the guiding expressional video, while audio encoder disentangles audio-lip representation. Instead of using single image as identity input, multi-image identity encoder is proposed by learning different views of faces and merging a unified representation. Multiple discriminators are exploited to keep both image-aware and the video-aware realistic details, including a spatial-temporal discriminator for visual continuity of expression synthesis and facial movements. We conduct extensive experimental evaluations on quantitative metrics, expression retention quality and audio-visual synchronization. The results show the effectiveness of our ET-GAN in generating high quality expressional talking face videos against existing state-of-the-arts.

关键词： talking face generation generative adversarial network encoder-decoder framework spatial-temporal discriminator expression-tailored facial videos

来源：评论

学校读者我要写书评

暂无评论

Efficient Audio Captioning with encoder-Level Knowledge Distillation 25

Efficient Audio Captioning with Encoder-Level Knowledge Dist...

引用

25th Interspeech Conference

作者： Xu, Xuenan Liu, Haohe Wu, Mengyue Wang, Wenwu Plumbley, Mark D. Shanghai Jiao Tong Univ MoE Key Lab Artificial Intelligence X LANCE Lab Shanghai Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc CVSSP Guildford Surrey England

Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD) framework for AAC. Our analysis shows that in the encoder-decoder based AAC models, it is more effective to distill knowledge into the encoder as compared with the decoder. To this end, we incorporate encoder-level KD loss into training, in addition to the standard supervised loss and sequence-level KD loss. We investigate two encoder-level KD methods, based on mean squared error (MSE) loss and contrastive loss, respectively. Experimental results demonstrate that contrastive KD is more robust than MSE KD, exhibiting superior performance in data-scarce situations. By leveraging audio-only data into training in the KD framework, our student model achieves competitive performance, with an inference speed that is 19 times faster(1).

关键词： automated audio captioning encoder-decoder framework knowledge distillation EfficientNet

来源：评论

学校读者我要写书评

暂无评论

END-TO-END SPEECH RECOGNITION WITH ADAPTIVE COMPUTATION STEPS 44

END-TO-END SPEECH RECOGNITION WITH ADAPTIVE COMPUTATION STEP...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Li, Mohan Liu, Min Masanori, Hattori Toshiba China R&D Ctr Kawasaki Kanagawa Japan

ISBN: (纸本)9781479981311

In this paper, we present Adaptive Computation Steps ( ACS) algorithm, which enables end-to-end speech recognition models to dynamically decide how many frames should be processed to predict a linguistic output. The model that applies ACS algorithm follows the encoder-decoder framework, while unlike the attention-based models, it produces alignments independently at the encoder side using the correlation between adjacent frames. Thus, predictions can be made as soon as sufficient acoustic information is received, which makes the model applicable in online cases. Besides, a small change is made to the decoding stage of the encoder-decoder framework, which allows the prediction to exploit bidirectional contexts. We verify the ACS algorithm on a Mandarin speech corpus AIShell-1, and it achieves a 31.2% CER in the online occasion, compared to the 32.4% CER of the attention-based model. To fully demonstrate the advantage of ACS algorithm, offline experiments are conducted, in which our ACS model achieves an 18.7% CER, outperforming the attention-based counterpart with the CER of 22.0%.

关键词： Adaptive Computation Steps encoder-decoder framework End-to-End Training

来源：评论

学校读者我要写书评

暂无评论

Abstractive Document Summarization via Neural Model with Joint Attention 6th

Abstractive Document Summarization via Neural Model with Joi...

引用

6th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC)

作者： Hou, Liwei Hu, Po Bei, Chao Cent China Normal Univ Sch Comp Sci Wuhan 430079 Hubei Peoples R China Global Tone Commun Technol Co Ltd Beijing 100043 Peoples R China

ISBN: (纸本)9783319736181;9783319736174

Due to the difficulty of abstractive summarization, the great majority of past work on document summarization has been extractive, while the recent success of sequence-to-sequence framework has made abstractive summarization viable, in which a set of recurrent neural networks models based on attention encoder-decoder have achieved promising performance on short-text summarization tasks. Unfortunately, these attention encoder-decoder models often suffer from the undesirable shortcomings of generating repeated words or phrases and inability to deal with out-of-vocabulary words appropriately. To address these issues, in this work we propose to add an attention mechanism on output sequence to avoid repetitive contents and use the subword method to deal with the rare and unknown words. We applied our model to the public dataset provided by NLPCC 2017 shared task3. The evaluation results show that our system achieved the best ROUGE performance among all the participating teams and is also competitive with some state-of-the-art methods.

关键词： Abstractive summarization Attentional mechanism encoder-decoder framework Neural network

来源：评论

学校读者我要写书评

暂无评论

Images Inpainting via Region Convolution and Feature Fusion 24

Images Inpainting via Region Convolution and Feature Fusion

引用

1st International Conference on Image Processing Machine Learning and Pattern Recognition

作者： Li, Jinrong Gao, Zhisheng Zhou, Bin Xihua Univ Sch Comp & Software Engn Chengdu Peoples R China

ISBN: (纸本)9798400707032

Image inpainting aims to fill damaged regions with reasonable structure, fine texture details, and semantically consistent content. However, existing deep learning algorithms mostly employ standard convolution architecture on damaged images, resulting in meaningless content such as color differences, blurring, and other artifacts. Aiming at the problem that the standard convolution methods cannot fully exploit the known regions to predict the damaged region features, this paper proposes an efficient region convolution (ERC) module to distinguish between known and damaged regions, and effectively prevent interference from invalid pixels through feature migration, additionally, the sampling regions are dynamically expanded to reconstruct the damaged regions more accurately. This article proposes a novel inpainting network that utilizes an encoder-decoder framework to restore images that are both semantically reasonable and visually realistic. Extensive experiments on two public datasets, Paris StreetView and CelebA, both qualitatively and quantitatively prove the strengths of the proposed approach.

关键词： Image inpainting Deep learning Efficient region convolution encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Enhancement of medical report generation by multi-scale image deblurring strategy

Enhancement of medical report generation by multi-scale imag...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wang, Yuxin Du, Yongping Tang, Shaorou Beijing Univ Technol Fac Informat Technol Beijing Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Automatic high-quality medical report generation plays an important role in the clinical diagnosis, which can assist and reduce the burden of doctors. Previous works often adopt the Transformer based structure and focus on the work of report generation process. Few studies consider the importance of image clarity by utilizing image deblurring to improve the quality of generated reports. We propose the multi-scale medical image deblurring network based on U-Net, improving the deblurring performance and recovering clear images gradually. Specially, the encoded representations of medical images and corresponding texts are aligned accurately by cross-modal feature alignment module. The experiments conducted on the IU-Xray and MIMIC-CXR datasets provide evidence that the proposed method outperforms previous studies in terms of both NLG metrics and Clinical Evaluation (CE) metrics, and the generated reports contain the professional medical terminology for higher quality.

关键词： medical report generation radiology image deblurring feature alignment encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Image steganography using texture features and GANs

Image steganography using texture features and GANs

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Huang, Jinjing Cheng, Shaoyin Lou, Songhao Jiang, Fan Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Peoples R China Univ Sci & Technol China Informat Technol Secur Evaluat Ctr Hefei 230027 Peoples R China

ISBN: (纸本)9781728119854

As steganography is the main practice of hidden writing, many deep neural networks are proposed to conceal secret information into images, whose invisibility and security are unsatisfactory. In this paper, we present an encoder-decoder framework with an adversarial discriminator to conceal messages or images into natural images. The message is embedded into QR code first which significantly improves the fault-tolerance. Considering the mean squared error (MSE) is not conducive to perfectly learn the invisible perturbations of cover images, we introduce a texture-based loss that is helpful to hide information into the complex texture regions of an image, improving the invisibility of hidden information. In addition, we design a truncated layer to cope with stego image distortions caused by data type conversion and a moment layer to train our model with varisized images. Finally, our experiments demonstrate that the proposed model improves the security and visual quality of stego images.

关键词： steganography convolutional network encoder-decoder framework adversarial training texture feature

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8页 << < 1 2 3 4 5 6 7 8 > >>

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：