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

923 篇 期刊文献
619 篇 会议
12 篇 学位论文

馆藏范围

1,554 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,400 篇 工学
- 949 篇 计算机科学与技术...
- 492 篇 电气工程
- 179 篇 信息与通信工程
- 131 篇 控制科学与工程
- 129 篇 软件工程
- 76 篇 生物医学工程（可授...
- 73 篇 仪器科学与技术
- 60 篇 机械工程
- 49 篇 材料科学与工程（可...
- 37 篇 电子科学与技术（可...
- 32 篇 石油与天然气工程
- 27 篇 化学工程与技术
- 26 篇 测绘科学与技术
- 22 篇 动力工程及工程热...
- 22 篇 土木工程
- 22 篇 环境科学与工程（可...
- 18 篇 力学（可授工学、理...
- 17 篇 交通运输工程
- 14 篇 生物工程
334 篇 理学
- 126 篇 物理学
- 95 篇 生物学
- 62 篇 化学
- 53 篇 数学
- 37 篇 地球物理学
- 20 篇 统计学（可授理学、...
246 篇 医学
- 148 篇 临床医学
- 62 篇 特种医学
- 56 篇 基础医学(可授医学...
110 篇 管理学
- 89 篇 管理科学与工程(可...
- 15 篇 图书情报与档案管...
18 篇 农学
12 篇 经济学
10 篇 法学
10 篇 教育学
9 篇 文学
3 篇 艺术学

主题

1,554 篇 variational auto...
262 篇 deep learning
133 篇 anomaly detectio...
93 篇 machine learning
61 篇 generative adver...
47 篇 generative model
46 篇 training
43 篇 feature extracti...
42 篇 unsupervised lea...
39 篇 neural networks
37 篇 representation l...
36 篇 generative adver...
36 篇 data augmentatio...
34 篇 convolutional ne...
33 篇 data models
28 篇 artificial intel...
27 篇 semi-supervised ...
26 篇 collaborative fi...
26 篇 task analysis
26 篇 deep generative ...

机构

10 篇 natl chiao tung ...
6 篇 ucl england
6 篇 shenzhen univ co...
6 篇 shanghai univ sc...
5 篇 nanyang technol ...
5 篇 zhejiang lab peo...
5 篇 xiamen univ sch ...
5 篇 chung yuan chris...
4 篇 mit comp sci & a...
4 篇 univ chinese aca...
4 篇 beijing jiaotong...
4 篇 acad sinica res ...
4 篇 acad sinica taiw...
4 篇 oak ridge natl l...
4 篇 northwestern pol...
4 篇 ecole technol su...
4 篇 chongqing univ p...
4 篇 tsinghua univ de...
4 篇 univ elect sci &...
4 篇 zhejiang univ st...

作者

12 篇 chien jen-tzung
9 篇 tahan antoine
9 篇 zemouri ryad
8 篇 chen junghui
7 篇 yang fan
7 篇 utschick wolfgan...
7 篇 zhang hao
6 篇 tsao yu
6 篇 baur michael
6 篇 slavic giulia
6 篇 wang hsin-min
6 篇 regazzoni carlo
6 篇 marcenaro lucio
5 篇 guo rui
5 篇 li maokun
5 篇 hsu wei-ning
5 篇 glass james
5 篇 liu xin
5 篇 yoshii kazuyoshi
5 篇 li yan

语言

1,498 篇 英文
42 篇 其他
2 篇 中文
1 篇 朝鲜文
1 篇 土耳其文

检索条件"主题词=variational autoencoder"

共 1554 条记录，以下是911-920 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：

Unsupervised Quality Assurance for Brain MR Image Rigid Registration using Latent Shape Representation

Unsupervised Quality Assurance for Brain MR Image Rigid Regi...

引用

Conference on Medical Imaging - Image Processing

作者： Xue, Yuan Zuo, Lianrui Remedios, Samuel W. Dewey, Blake E. Duan, Peiyu Liu, Yihao Zhang, Rendong Newsome, Scott D. Mowry, Ellen M. Carass, Aaron Prince, Jerry L. Johns Hopkins Univ Dept Elect & Comp Engn Baltimore MD 21218 USA Johns Hopkins Univ Dept Comp Sci Baltimore MD 21218 USA NIA Labo Behav Neurosci NIH Bethesda MD 20892 USA Johns Hopkins Sch Med Dept Neurol Baltimore MD 21287 USA Johns Hopkins Sch Med Dept Biomed Engn Baltimore MD 21287 USA

ISBN: (纸本)9781510660335;9781510660342

Linear registration to a standard space is a crucial early step in the processing of magnetic resonance images (MRIs) of the human brain. Thus an accurate registration is essential for subsequent image processing steps, as well as downstream analyses. Registration failures are not uncommon due to poor image quality, irregular head shapes, and bad initialization. Traditional quality assurance (QA) for registration requires a substantial manual assessment of the registration results. In this paper, we propose an automatic quality assurance method for the rigid registration of brain MRIs. A variational autoencoder (VAE) model is used to learn shape representations from MRIs after a rigid registration to an MNI standard space. The shape representations are then fed into an anomaly detection model to identify failed registration cases. Without using any manual annotations in the model training, our proposed QA method achieved 99.1% sensitivity and 86.7% specificity in a pilot study on 537 T1-weighted scans acquired from multiple imaging centers.

关键词： Magnetic resonance imaging variational autoencoder Linear registration Quality assurance

来源：评论

学校读者我要写书评

暂无评论

Adversarial Anomaly Detection using Gaussian Priors and Nonlinear Anomaly Scores 23

Adversarial Anomaly Detection using Gaussian Priors and Nonl...

引用

23rd IEEE International Conference on Data Mining (IEEE ICDM)

作者： Lueer, Fiete Weber, Tobias Dolgich, Maxim Boehm, Christian eMundo Gmbh Gofore Oyj Munich Germany Ludwig Maximilians Univ Munchen Dept Stat Munich Germany Univ Vienna Fac Comp Sci Vienna Austria

ISBN: (纸本)9798350381641

Anomaly detection in imbalanced datasets is a frequent and crucial problem, especially in the medical domain where retrieving and labeling irregularities is often expensive. By combining the generative stability of a beta-variational autoencoder (VAE) with the discriminative strengths of generative adversarial networks (GANs), we propose a novel model, beta-VAEGAN. We investigate methods for composing anomaly scores based on the discriminative and reconstructive capabilities of our model. Existing work focuses on linear combinations of these components to determine if data is anomalous. We advance existing work by training a kernelized support vector machine (SVM) on the respective error components to also consider nonlinear relationships. This improves anomaly detection performance, while allowing faster optimization. Lastly, we use the deviations from the Gaussian prior of beta-VAEGAN to form a novel anomaly score component. In comparison to state-of-the-art work, we improve the F-1 score during anomaly detection from 0.85 to 0.92 on the widely used MITBIH Arrhythmia Database.(1)

关键词： adversarial autoencoder generative adversarial networks variational autoencoder anomaly detection time series

来源：评论

学校读者我要写书评

暂无评论

Frame-Level Event Representation Learning for Semantic-Level Generation and Editing of Avatar Motion 23

Frame-Level Event Representation Learning for Semantic-Level...

引用

25th International Conference on Multimodal Interaction (ICMI)

作者： Ideno, Ayaka Kaneko, Takuhiro Harada, Tatsuya Univ Tokyo Tokyo Japan NTT Corp Yokosuka Kanagawa Japan Univ Tokyo RIKEN Tokyo Japan

ISBN: (纸本)9798400700552

Understanding an avatar's motion and controlling its content is important for content creation and has been actively studied in computer vision and graphics. An avatar's motion consists of frames representing poses each time, and a subsequence of frames can be grouped into a segment based on semantic meaning. To enable semantic-level control of motion, it is important to understand the semantic division of the avatar's motion. We define a semantic division of avatar's motion as an "event", which switches only when the frame in the motion cannot be predicted from the previous frames and information of the last event, and tackled editing motion and inferring motion from text based on events. However, it is challenging because we need to obtain the event information, and control the content of motion based on the obtained event information. To overcome this challenge, we propose obtaining frame-level event representation from the pair of motion and text and using it to edit events in motion and predict motion from the text. Specifically, we learn a frame-level event representation by reconstructing the avatar's motion from the corresponding frame-level event representation sequence while inferring the sequence from the text. By doing so, we can predict motion from the text. Also, since the event at each motion frame is represented with the corresponding event representation, we can edit events in motion by editing the corresponding event representation sequence. We evaluated our method on the HumanML3D dataset and demonstrated that our model can generate motion from the text while editing motion flexibly (e.g., allowing the change of the event duration, modifcation of the event characteristics, and the addition of new events).

关键词： variational autoencoder natural language motion content control

来源：评论

学校读者我要写书评

暂无评论

A Continuous Representation Of Switching Linear Dynamic Systems For Accurate Tracking 22

A Continuous Representation Of Switching Linear Dynamic Syst...

引用

22nd IEEE Statistical Signal Processing Workshop (SSP)

作者： Karimi, Parisa Naumer, Helmuth Kamalabadi, Farzad Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA

ISBN: (纸本)9781665452458

We propose a method for tracking linear representations of a nonlinear dynamic system with time-varying parameters based on a continuous representation of its switching linear dynamic system (SLDS) model. Given approximate linear representations for a finite set of unknown intrinsic parameters of the dynamics, a combination of autoencoder-based dimensionality reduction and cubic curve-fitting are applied to learn the continuous manifold of dynamics embedded in the evolution operator. This representation enables a significant reduction of the squared Frobenius norm of error in maximum likelihood (ML) system identification relative to that of the original SLDS model. Numerical experiments also verify this result.

关键词： Dynamic systems Online tracking Manifold learning Koopman operator Switching linear dynamic system variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep Generative Imputation Model for Missing Not At Random Data 23

Deep Generative Imputation Model for Missing Not At Random D...

引用

32nd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Chen, Jialei Xu, Yuanbo Wang, Pengyang Yang, Yongjian Jilin Univ Dept Comp Sci & Technol MIC Lab Changchun Peoples R China Univ Macau Dept Comp & Informat Sci SKL IOTSC Macau Peoples R China

ISBN: (纸本)9798400701245

Data analysis usually suffers from the Missing Not At Random (MNAR) problem, where the cause of the value missing is not fully observed. Compared to the naive Missing Completely At Random (MCAR) problem, it is more in line with the realistic scenario whereas more complex and challenging. Existing statistical methods model the MNAR mechanism by different decomposition of the joint distribution of the complete data and the missing mask. But we empirically find that directly incorporating these statistical methods into deep generative models is sub-optimal. Specifically, it would neglect the confidence of the reconstructed mask during the MNAR imputation process, which leads to insufficient information extraction and less-guaranteed imputation quality. In this paper, we revisit the MNAR problem from a novel perspective that the complete data and missing mask are two modalities of incomplete data on an equal footing. Along with this line, we put forward a generative-model-specific joint probability decomposition method, conjunction model, to represent the distributions of two modalities in parallel and extract sufficient information from both complete data and missing mask. Taking a step further, we exploit a deep generative imputation model, namely GNR, to process the real-world missing mechanism in the latent space and concurrently impute the incomplete data and reconstruct the missing mask. The experimental results show that our GNR surpasses state-of-the-art MNAR baselines with significant margins (averagely improved from 9.9% to 18.8% in RMSE) and always gives a better mask reconstruction accuracy which makes the imputation more principle.

关键词： Missing Data Missing Not At Random Imputation Deep Generative Models variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A UAV Indoor Obstacle Avoidance System Based on Deep Reinforcement Learning

A UAV Indoor Obstacle Avoidance System Based on Deep Reinfor...

引用

Asia-Pacific-Signal-and-Information-Processing-Association Annual Summit and Conference (APSIPA ASC)

作者： Lo, Chun-Huang Lee, Chung-Nan Natl Sun Yat Sen Univ Dept Comp Sci & Engn Kaohsiung Taiwan

ISBN: (纸本)9798350300673

This paper presents a vision-based unmanned aerial vehicle (UAV) indoor obstacle avoidance using a deep reinforcement learning (DRL). The system consists of two parts a depth map compression and a UAV control. For the depth map compression part, the pre-trained variational autoencoder model is used to improve obstacle avoidance and reduce the training time. The states include the UAV information, gray images and compressed features. A dueling double deep recurrent Q network model is used to control the UAV. The network is trained in the AirSim simulation. To validate the performance of the proposed algorithm some simulations are conducted. The results show that the proposed algorithm can avoid obstacles at a fast speed in a narrow space, and fly through a difficult L-shaped corner in an indoor simulation.

关键词： Unmanned Aerial Vehicle Obstacle Avoidance Deep Reinforcement Learning AirSim variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multivariate air quality time series analysis via a recurrent variational deep learning model 13

Multivariate air quality time series analysis via a recurren...

引用

Conference on Geospatial Informatics XIII

作者： Loughlin, Cooper Manolakis, Dimitris Ingle, Vinay Northeastern Univ 360 Huntington Ave Boston MA 02115 USA MIT Lincoln Lab 244 Wood St Lexington MA 02421 USA

ISBN: (数字)9781510661653

ISBN: (纸本)9781510661646;9781510661653

Monitoring of air pollutants across space and time is critical in understanding pollution trends and reporting air quality. The Air Quality Index (AQI) is a tool used to communicate air quality that incorporates atmospheric concentrations of five major pollution indicators: ground-level ozone, particulate matter, carbon monoxide, sulfur dioxide, and nitrogen dioxide. The ability to accurately forecast these concentrations and identify unusual levels is of particular importance. In this work, we develop a generative time series model for air quality indicators and use it for long and short-term probabilistic forecasts. Air quality data are multivariate and exhibit high variability across indicators in both space and time. Marginal indicator distributions are typically skewed and contain substantial zeros, while indicator-wise cross-correlations can be highly non-linear. We find that hourly measurements additionally exhibit substantial temporal cross-correlation, long-term dependence, and daily periodicity. To capture these complexities, we employ a recurrent extension of the variational autoencoder (VAE) to sequential data. The VAE is a generative neural network architecture capable of learning complex, high dimensional manifolds on which data are distributed. Furthermore, recurrent architectures can capture non-linear and long-term temporal qualities of time series data. We train the proposed time series model on historical air quality measurements at multiple locations and demonstrate its ability to capture observed indicator-wise and temporal complexities. We additionally use the trained model to compute probabilistic forecasts and credible intervals of air quality indicators.

关键词： air quality index multivariate time series analysis deep latent variable model recurrent neural network variational autoencoder generative time series model

来源：评论

学校读者我要写书评

暂无评论

Generative Slate Recommendation with Reinforcement Learning 23

Generative Slate Recommendation with Reinforcement Learning

引用

16th International Conference on Web Search and Data Mining

作者： Deffayet, Romain Thonet, Thibaut Renders, Jean-Michel de Rijke, Maarten Naver Labs Europe Meylan France Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9781450394079

Recent research has employed reinforcement learning (RL) algorithms to optimize long-term user engagement in recommender systems, thereby avoiding common pitfalls such as user boredom and filter bubbles. They capture the sequential and interactive nature of recommendations, and thus offer a principled way to deal with long-term rewards and avoid myopic behaviors. However, RL approaches are intractable in the slate recommendation scenario - where a list of items is recommended at each interaction turn due to the combinatorial action space. In that setting, an action corresponds to a slate that may contain any combination of items. While previous work has proposed well-chosen decompositions of actions so as to ensure tractability, these rely on restrictive and sometimes unrealistic assumptions. Instead, in this work we propose to encode slates in a continuous, low-dimensional latent space learned by a variational auto-encoder. Then, the RL agent selects continuous actions in this latent space, which are ultimately decoded into the corresponding slates. By doing so, we are able to (i) relax assumptions required by previous work, and (ii) improve the quality of the action selection by modeling full slates instead of independent items, in particular by enabling diversity. Our experiments performed on a wide array of simulated environments confirm the effectiveness of our generative modeling of slates over baselines in practical scenarios where the restrictive assumptions underlying the baselines are lifted. Our findings suggest that representation learning using generative models is a promising direction towards generalizable RL-based slate recommendation.

关键词： Slate recommendation Reinforcement learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Towards Multi-User Activity Recognition through Facilitated Training Data and Deep Learning for Human-Robot Collaboration Applications

Towards Multi-User Activity Recognition through Facilitated ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Semeraro, Francesco Carberry, Jon Cangelosi, Angelo Univ Manchester Manchester Ctr Robot & Manchester Lancs England BAE Syst Plc BAE Syst Operat Ltd Warton England

ISBN: (纸本)9781665488679

Human-robot interaction (HRI) research is progressively addressing multi-party scenarios, where a robot interacts with more than one human user at the same time. Conversely, research is still at an early stage for human-robot collaboration. The use of machine learning techniques to handle such type of collaboration requires data that are less feasible to produce than in a typical HRC setup. This work outlines scenarios of concurrent tasks for non-dyadic HRC applications. Based upon these concepts, this study also proposes an alternative way of gathering data regarding multi-user activity, by collecting data related to single users and merging them in post-processing, to reduce the effort involved in producing recordings of pair settings. To validate this statement, 3D skeleton poses of activity of single users were collected and merged in pairs. After this, such datapoints were used to separately train a long shortterm memory (LSTM) network and a variational autoencoder (VAE) composed of spatio-temporal graph convolutional networks (STGCN) to recognise the joint activities of the pairs of people. The results showed that it is possible to make use of data collected in this way for pair HRC settings and get similar performances compared to using training data regarding groups of users recorded under the same settings, relieving from the technical difficulties involved in producing these data. The related code and collected data are publicly available(1).

关键词： multi-user activity recognition single-user training data concurrent tasks multi-party human-robot collaboration non-dyadic human-robot collaboration deep learning long short-term memory variational autoencoder spatio-temporal graph convolutional network transfer learning

来源：评论

学校读者我要写书评

暂无评论

Two-stage instrument timbre transfer method using RAVE 26

Two-stage instrument timbre transfer method using RAVE

引用

26th International Symposium on Multimedia, ISM 2024

作者： Hu, Di Ito, Katunobu Hosei University Graduate School of Computer and Information Sciences Tokyo Japan Hosei University Faculty of Computer and Information Sciences Tokyo Japan

ISBN: (纸本)9798331511111

Recently, the real-time audio variational autoencoder (RAVE) method was developed for high-quality audio waveform synthesis. The RAVE method is based on a variational autoencoder and employs a two-stage training strategy. However, the RAVE model still has limitations in timbre transformation, especially when converting between instruments with significantly different timbres. Issues such as pitch instability, inaccurate timbre reproduction, and severe degradation in sound quality can arise. To enhance timbre transfer performance, we propose a two-stage timbre transformation method using RAVE, which involves applying two timbre transfer models to perform a dual transformation on the original input audio. To evaluate the proposed method, we trained the model and tested its performance using audio generated from MIDI and SoundFont2 sound sources. The results demonstrate that the proposed method improves timbre transfer compared to the single-stage RAVE model. © 2024 IEEE.

关键词： audio synthesis timbre transfer variational autoencoder

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156页 << < 88 89 90 91 92 93 94 95 96 97 > >>

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：