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

53,147 篇 会议
1,123 篇 期刊文献
10 册 图书

馆藏范围

54,280 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

26,352 篇 工学
- 17,157 篇 计算机科学与技术...
- 9,456 篇 软件工程
- 8,127 篇 电气工程
- 3,785 篇 控制科学与工程
- 2,423 篇 信息与通信工程
- 2,392 篇 机械工程
- 1,902 篇 生物医学工程（可授...
- 1,312 篇 仪器科学与技术
- 1,054 篇 生物工程
- 778 篇 电子科学与技术（可...
- 754 篇 土木工程
- 713 篇 建筑学
- 679 篇 光学工程
- 530 篇 交通运输工程
- 508 篇 测绘科学与技术
- 388 篇 安全科学与工程
4,525 篇 理学
- 1,747 篇 数学
- 1,319 篇 物理学
- 984 篇 生物学
- 701 篇 系统科学
- 433 篇 统计学（可授理学、...
- 400 篇 化学
3,464 篇 管理学
- 2,116 篇 管理科学与工程(可...
- 1,608 篇 图书情报与档案管...
- 769 篇 工商管理
3,099 篇 医学
- 2,683 篇 临床医学
- 753 篇 基础医学(可授医学...
- 361 篇 药学(可授医学、理...
676 篇 教育学
- 662 篇 教育学
515 篇 农学
- 485 篇 作物学
346 篇 法学
190 篇 经济学
168 篇 艺术学
135 篇 文学
29 篇 军事学
4 篇 历史学
1 篇 哲学

主题

34,796 篇 visualization
7,402 篇 data visualizati...
4,850 篇 training
4,325 篇 feature extracti...
2,968 篇 computational mo...
2,949 篇 three-dimensiona...
2,920 篇 cameras
2,457 篇 computer vision
2,448 篇 semantics
2,073 篇 task analysis
1,947 篇 conferences
1,636 篇 accuracy
1,317 篇 image color anal...
1,303 篇 data mining
1,284 篇 image segmentati...
1,274 篇 navigation
1,204 篇 data models
1,204 篇 robustness
1,168 篇 real-time system...
1,106 篇 measurement

机构

96 篇 university of sc...
94 篇 tsinghua univers...
72 篇 univ chinese aca...
71 篇 shanghai jiao to...
66 篇 zhejiang univers...
59 篇 georgia inst tec...
48 篇 univ konstanz co...
46 篇 georgia institut...
41 篇 facebook ai rese...
41 篇 hong kong univ s...
39 篇 microsoft resear...
37 篇 school of comput...
36 篇 tu wien austria
34 篇 inria
34 篇 univ michigan an...
33 篇 massachusetts in...
32 篇 university of ce...
32 篇 carnegie mellon ...
31 篇 national institu...
30 篇 univ toronto on

作者

53 篇 itoh takayuki
44 篇 zhang lei
31 篇 lei wang
27 篇 jing zhang
26 篇 jun wang
25 篇 yongdong zhang
25 篇 pfister hanspete...
24 篇 schreck tobias
24 篇 van gool luc
24 篇 yang yi
24 篇 li li
22 篇 guangtao zhai
22 篇 nassir navab
22 篇 takahiro ogawa
20 篇 bin wang
20 篇 li xin
19 篇 shuqiang jiang
19 篇 chang remco
19 篇 jie yang
18 篇 yiming li

语言

52,648 篇 英文
1,394 篇 其他
189 篇 中文
18 篇 西班牙文
14 篇 土耳其文
9 篇 俄文
8 篇 葡萄牙文
1 篇 法文

检索条件"任意字段=IEEE Information Visualization Conference/IEEE Visualization Conference"

共 54280 条记录，以下是3841-3850 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：

Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations 39

Learning Sensorimotor Primitives of Sequential Manipulation ...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Liang, Junchi Wen, Bowen Bekris, Kostas Boularias, Abdeslam Rutgers State Univ Dept Comp Sci New Brunswick NJ 08901 USA

ISBN: (纸本)9781728196817

This work aims to learn how to perform complex robot manipulation tasks that are composed of several, consecutively executed low-level sub-tasks, given as input a few visual demonstrations of the tasks performed by a person. The sub-tasks consist of moving the robot's end-effector until it reaches a sub-goal region in the task space, performing an action, and triggering the next sub-task when a pre-condition is met. Most prior work in this domain has been concerned with learning only low-level tasks, such as hitting a ball or reaching an object and grasping it. This paper describes a new neural network-based framework for learning simultaneously low-level policies as well as high-level policies, such as deciding which object to pick next or where to place it relative to other objects in the scene. A key feature of the proposed approach is that the policies are learned directly from raw videos of task demonstrations, without any manual annotation or post-processing of the data. Empirical results on object manipulation tasks with a robotic arm show that the proposed network can efficiently learn from real visual demonstrations to perform the tasks, and outperforms popular imitation learning algorithms.

关键词： Training visualization Solid modeling Target tracking Manuals Grasping Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Intelligent Soft Robotic Gripper Enabled by Multimodal Sensors and Deep Learning 18

Intelligent Soft Robotic Gripper Enabled by Multimodal Senso...

引用

18th International conference on Nano/Micro Engineered and Molecular Systems, NEMS 2023

作者： Shi, Qiongfeng Sun, Zhongda Le, Xianhao Xie, Jin Lee, Chengkuo Southeast University Joint International Research Laboratory of Information Display and Visualization School of Electronic Science and Engineering Nanjing China National University of Singapore Department of Electrical and Computer Engineering Singapore Singapore Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou China

ISBN: (纸本)9798350333480

Here we report an intelligent soft robotic gripper enabled by the integration of an ultrasonic remote sensor and triboelectric sensors. Due to the noncontact distance sensing ability, the ultrasonic sensor is used to find the object's visual information including position and height by lateral scanning. The information is then used for adjusting the robotic gripper to an appropriate grasp location, after which grasp operation is performed to obtain the object's tactile information through triboelectric bending and tactile sensors. To efficiently analyze the multimodal information, a deep-learning neural network based on feature-level data fusion is constructed, which is able to achieve a high accuracy of 99.3% in classifying 14 objects, enabling the intelligent soft robotic gripper for various smart applications. © 2023 ieee.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Selective neuromodulation of retinal ganglion cells via a hybrid optic-nerve and retinal neuroprosthesis for visual restoration 44

Selective neuromodulation of retinal ganglion cells via a hy...

引用

44th Annual International conference of the ieee-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Pratiwi, Ariastity M. Kekesi, Orsolya Suaning, Gregg J. Univ Sydney Sch Biomed Engn Sydney NSW 2006 Australia

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

A visual neuroprosthesis delivers electrical stimulation to the surviving neural cells of the visual pathway to produce prosthetic vision. While the retina is often chosen as the stimulation site, current retinal prostheses are hindered by the lack of functional selectivity that impairs the resolution. A possible strategy to improve the resolution is to combine the retinal stimulation and the stimulation of the optic nerve bundle, which contains myelinated fibres of retinal ganglion cells (RGCs) axons that vary in diameter. In this study, we used a computational model of retinal ganglion cells (RGCs) with myelinated axons to predict whether the frequency of electrical stimulation delivered to the optic nerve can be modulated to preferentially inhibit a subset of optic nerve fibres classified by diameter. The model combined a finite element model of bipolar penetrating electrodes delivering sinusoidal stimulation in the range of 25-10000 Hz to the optic nerve, and a double-cable model, to represent an optic nerve fibre. We found that the diameter of the axon fibre and ion kinetic properties of the RGC affect the neuron's frequency response, demonstrating the potential of an optic nerve stimulation to produce selective inhibition based on the axon fibre size.

关键词： Optical fibers Axons visualization Biomedical optical imaging Stimulated emission Computational modeling Neuroprostheses

来源：评论

学校读者我要写书评

暂无评论

Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution

Details or Artifacts: A Locally Discriminative Learning Appr...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Liang, Jie Zeng, Hui Zhang, Lei HongKong Polytech Univ Hong Kong Peoples R China OPPO Res Shenzhen Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Single image super-resolution (SISR) with generative adversarial networks (GAN) has recently attracted increasing attention due to its potentials to generate rich details. However, the training of GAN is unstable, and it often introduces many perceptually unpleasant artifacts along with the generated details. In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts. Based on the observation that the local statistics (e.g., residual variance) of artifact areas are often different from the areas of perceptually friendly details, we develop a framework to discriminate between GAN-generated artifacts and realistic details, and consequently generate an artifact map to regularize and stabilize the model training process. Our proposed locally discriminative learning (LDL) method is simple yet effective, which can be easily plugged in off-the-shelf SISR methods and boost their performance. Experiments demonstrate that LDL outperforms the state-of-the-art GAN based SISR methods, achieving not only higher reconstruction accuracy but also superior perceptual quality on both synthetic and real-world datasets. Codes and models are available at https://***/csjliang/LDL.

关键词： Training visualization Computer vision Codes Computational modeling Superresolution Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Modeling, Simulation and visualization of Acoustic Coherent Images

Modeling, Simulation and Visualization of Acoustic Coherent ...

引用

ieee lnternational conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET 2022

作者： Hvozdeva, Iryna Myrhorod, Volodymyr National University "Odessa Maritime Academy" 8 Didrikhsona Street Odessa65029 Ukraine

ISBN: (纸本)9783031249624

This study is devoted to the consideration of methods for creating mathematical models of acoustic coherent images in relation to the tasks of monitoring the underwater environment of the World Ocean using modern distributed information and telecommunication networks. The combination of the theoretical approach to constructing an acoustic image as a section of the secondary field at the aperture of the receiving antenna, and the experimental method for obtaining such images with instrumental measuring instruments of a hydroacoustic tank was chosen as the main research method. Comparison of theoretical and experimental results makes it possible to verify the proposed mathematical models of acoustic coherent images. The proposed models, confirmed experimentally, make it possible to perform computer simulation of the processes of formation and processing of acoustic coherent images (ACI) to solve the problems of creating and improving methods for processing such images for their recognition and classification, as well as for testing the technical means of underwater monitoring networks during their tests. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

Audio-Adaptive Activity Recognition Across Video Domains

Audio-Adaptive Activity Recognition Across Video Domains

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhang, Yunhua Doughty, Hazel Shao, Ling Snoek, Cees G. M. Univ Amsterdam Amsterdam Netherlands Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates Terminus Grp Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint. The leading approaches reduce the shift in activity appearance by adversarial training and self-supervised learning. Different from these vision-focused works we leverage activity sounds for domain adaptation as they have less variance across domains and can reliably indicate which activities are not happening. We propose an audio-adaptive encoder and associated learning methods that discriminatively adjust the visual feature representation as well as addressing shifts in the semantic distribution. To further eliminate domain-specific features and include domain-invariant activity sounds for recognition, an audio-infused recognizer is proposed, which effectively models the cross-modal interaction across domains. We also introduce the new task of actor shift, with a corresponding audio-visual dataset, to challenge our method with situations where the activity appearance changes dramatically. Experiments on this dataset, EPIC-Kitchens and CharadesEgo show the effectiveness of our approach. Project page: https://xiaobai1217. ***/DomainAdaptation

关键词： Training Adaptation models visualization Computer vision Computational modeling Semantics Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Action unit detection by exploiting spatial-temporal and label-wise attention with transformer

Action unit detection by exploiting spatial-temporal and lab...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wang, Lingfeng Qi, Jin Cheng, Jian Suzuki, Kenji Univ Elect Sci & Technol China Chengdu Peoples R China Tokyo Inst Technol Tokyo Japan

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The facial action units (FAU) defined by the Facial Action Coding System (FACS) has become an important approach of facial expression analysis. Most work on FAU detection only considers the spatial-temporal feature and ignores the label-wise AU correlation. In practice, the strong relationships between facial AUs can help AU detection. We proposed a transformer based FAU detection model by leverage both the local spatial-temporal features and label-wise FAU correlation. To be specific, we firstly designed a visual spatial-temporal transformer based model and a convolution based audio model to extract action unit specific features. Secondly, inspired by the relationship between FAUs, we proposed a transformer based correlation module to learn correlation between AUs. The action unit specific features from aural and visual models are further aggregated in the correlation modules to produce per-frame prediction of 12 AUs. Our model was trained on Aff-Wild2 dataset of the ABAW3 challenge and achieved state of art performance in the FAU task, which verified that the effectiveness of the proposed network.

关键词： visualization Gold Correlation Convolution Computational modeling Predictive models Transformers

来源：评论

学校读者我要写书评

暂无评论

Web Development Using ReactJS 5

Web Development Using ReactJS

引用

5th ieee International conference on Advances in Computing, Communication Control and Networking, ICAC3N 2023

作者： Keshari, Pankaj Maurya, Priya Kumar, Pankaj Katiyar, Alok Galgotias University School Of Computer Science And Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350330861

In recent years, there have been considerable developments in web development, and ReactJS has become a potent tool for creating effective and engaging web apps. This abstract offers a succinct synopsis of the study's research paper on ReactJS-based web development. [1] The purpose of the study article is to examine ReactJS's main characteristics, benefits, and potential uses in web development. It explores subjects including ReactJS' component-based architecture, virtual DOM, reconciliation method, and advantages of React Hooks. The paper also covers ReactJS's support for server-side rendering and its interoperability with the creation of mobile apps using React Native [14]. The research paper also emphasises the benefits of adopting ReactJS in online development, including better performance with the virtual DOM, reusable code, increased user interface creation, and SEO friendly web applications. As well investigates the strong ReactJS ecosystem and developer support available. The construction of a real-time chat application and a data visualisation dashboard are showcased as case studies in the article to explain the practical applications of ReactJS. Additionally, it contrasts ReactJS with two other well-known web development frameworks, Angular and ***, in order to assist readers, grasp the unique qualities and applications of each framework. © 2023 ieee.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Preliminary Analysis of Data visualization based Uber Technology using R: A Review

Preliminary Analysis of Data Visualization based Uber Techno...

引用

2022 International conference on Augmented Intelligence and Sustainable Systems, ICAISS 2022

作者： Riya Singh, Gurpreet Singh, Jaspreet Singh, Pankaj Kumar Chandigarh University Department of Mathematics Mohali India Chandigarh University Department of CSE Mohali India

ISBN: (纸本)9781665489621

Understanding data is crucial right now since doing so will improve the productivity and efficiency of corporate operations across the globe. Data analysis employs methodical techniques to search for patterns, clusters, or other connections among various data kinds. Data visualization aids analysis and interpretation of data by placing data into a chart, graph or other visual format. Analytics and visualizations have the power to drill down the data to gives various rich benefits to any organization through its findings by spotting new trends and data patterns which brings more profitable business operations, new revenue prospects, improved operational efficiency and customer service and most significantly helps the organization to take smart decisions. In this paper we perform analysis and visualization on the data of one such organization i.e. Uber, the uber dataset involves uber pickups in New York city which is over 4.5 million from April through September 2014. The analysis is done using R programming language containing various libraries and packages for clear visualization and insights. © 2022 ieee.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation

Not All Relations are Equal: Mining Informative Labels for S...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Goel, Arushi Fernando, Basura Keller, Frank Bilen, Hakan Univ Edinburgh Sch Informat Edinburgh Midlothian Scotland ASTAR IHPC CFAR Singapore Singapore

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Scene graph generation (SGG) aims to capture a wide variety of interactions between pairs of objects, which is essential for full scene understanding. Existing SGG methods trained on the entire set of relations fail to acquire complex reasoning about visual and textual correlations due to various biases in training data. Learning on trivial relations that indicate generic spatial configuration like 'on' instead of informative relations such as 'parked on' does not enforce this complex reasoning, harming generalization. To address this problem, we propose a novel framework for SGG training that exploits relation labels based on their informativeness. Our model-agnostic training procedure imputes missing informative relations for less informative samples in the training data and trains a SGG model on the imputed labels along with existing annotations. We show that this approach can successfully be used in conjunction with state-of-the-art SGG methods and improves their performance significantly in multiple metrics on the standard Visual Genome benchmark. Furthermore, we obtain considerable improvements for unseen triplets in a more challenging zero-shot setting.

关键词： Training Measurement visualization Training data Data models Cognition Pattern recognition

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500页 << < 381 382 383 384 385 386 387 388 389 390 > >>

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：