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

53,095 篇 会议
1,122 篇 期刊文献
10 册 图书

馆藏范围

54,227 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

26,347 篇 工学
- 17,153 篇 计算机科学与技术...
- 9,460 篇 软件工程
- 8,121 篇 电气工程
- 3,788 篇 控制科学与工程
- 2,426 篇 信息与通信工程
- 2,394 篇 机械工程
- 1,900 篇 生物医学工程（可授...
- 1,313 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...
- 756 篇 土木工程
- 716 篇 建筑学
- 680 篇 光学工程
- 531 篇 交通运输工程
- 511 篇 测绘科学与技术
- 390 篇 安全科学与工程
4,525 篇 理学
- 1,749 篇 数学
- 1,317 篇 物理学
- 984 篇 生物学
- 699 篇 系统科学
- 434 篇 统计学（可授理学、...
- 400 篇 化学
3,469 篇 管理学
- 2,120 篇 管理科学与工程(可...
- 1,610 篇 图书情报与档案管...
- 770 篇 工商管理
3,102 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

34,750 篇 visualization
7,388 篇 data visualizati...
4,844 篇 training
4,318 篇 feature extracti...
2,961 篇 computational mo...
2,949 篇 three-dimensiona...
2,917 篇 cameras
2,455 篇 computer vision
2,445 篇 semantics
2,073 篇 task analysis
1,940 篇 conferences
1,627 篇 accuracy
1,315 篇 image color anal...
1,302 篇 data mining
1,283 篇 image segmentati...
1,271 篇 navigation
1,203 篇 robustness
1,201 篇 data models
1,156 篇 real-time system...
1,106 篇 measurement

机构

95 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...
35 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

53,423 篇 英文
563 篇 其他
189 篇 中文
21 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 54227 条记录，以下是4031-4040 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：

Immersive visualization for Surgical Planning Through Mental Model Elicitation: Work in Progress

Immersive Visualization for Surgical Planning Through Mental...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), ieee conference on

作者： Carlos J. Latorre-Rojas Javier A. Luzon Alexander Rozo-Torres Wilson J. Sarmiento Multimedia Research Group Universidad Militar Nueva Granada Akershus University Hospital Oslo Norway University of Oslo Oslo Norway

ISBN: (数字)9798350374490

ISBN: (纸本)9798350374506

Extended Reality (XR) technologies have opened new possibilities for image visualization in healthcare, but eliciting user requirements for XR development is challenging. Human-computer interaction can help obtain User Mental Models, mostly unexplored in XR for health. An ongoing project aims to address this gap by studying the skills and backgrounds of radiologists and surgeons using the same XR tool in Preoperative Surgical Planning for Complex Malformations through elucidating mental model, performing technical review and proposing Potential Interaction Models or Interaction Concepts. The work aims to contribute insights for designing more intuitive, immersive medical visualization tools.

关键词： visualization Solid modeling Three-dimensional displays Reviews Extended reality Surgery Medical services

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Online Learning for Safety-Critical Control using Stereo Vision 39

Self-Supervised Online Learning for Safety-Critical Control ...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Cosner, Ryan K. Rodriguez, Ivan D. Jimenez Molnar, Tamas G. Ubellacker, Wyatt Yue, Yisong Ames, Aaron D. Bouman, Katherine L. CALTECH Dept Control & Dynam Syst Dept Mech & Civil Engn Pasadena CA 91125 USA CALTECH Comp & Math Sci Pasadena CA 91125 USA

ISBN: (纸本)9781728196817

With the increasing prevalence of complex vision-based sensing methods for use in obstacle identification and state estimation, characterizing environment-dependent measurement errors has become a difficult and essential part of modern robotics. This paper presents a self-supervised learning approach to safety-critical control. In particular, the uncertainty associated with stereo vision is estimated, and adapted online to new visual environments, wherein this estimate is leveraged in a safety-critical controller in a robust fashion. To this end, we propose an algorithm that exploits the structure of stereo-vision to learn an uncertainty estimate without the need for ground-truth data. We then robustify existing Control Barrier Function-based controllers to provide safety in the presence of this uncertainty estimate. We demonstrate the efficacy of our method on a quadrupedal robot in a variety of environments. When not using our method safety is violated. With offline training alone we observe the robot is safe, but overly-conservative. With our online method the quadruped remains safe and conservatism is reduced.

关键词： Training visualization Uncertainty Self-supervised learning Robot sensing systems Stereo vision Safety

来源：评论

学校读者我要写书评

暂无评论

Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species

Few-shot Keypoint Detection with Uncertainty Learning for Un...

引用

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

作者： Lu, Changsheng Koniusz, Piotr Australian Natl Univ Canberra ACT Australia CSIRO Data61 Canberra ACT Australia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Current non-rigid object keypoint detectors perform well on a chosen kind of species and body parts, and require a large amount of labelled keypoints for training. Moreover, their heatmaps, tailored to specific body parts, cannot recognize novel keypoints (keypoints not labelled for training) on unseen species. We raise an interesting yet challenging question: how to detect both base (annotated for training) and novel keypoints for unseen species given a few annotated samples? Thus, we propose a versatile Few-shot Keypoint Detection (FSKD) pipeline, which can detect a varying number of keypoints of different kinds. Our FSKD provides the uncertainty estimation of predicted keypoints. Specifically, FSKD involves main and auxiliary keypoint representation learning, similarity learning, and keypoint localization with uncertainty modeling to tackle the localization noise. Moreover, we model the uncertainty across groups of keypoints by multivariate Gaussian distribution to exploit implicit correlations between neighboring keypoints. We show the effectiveness of our FSKD on (i) novel keypoint detection for unseen species, (ii) few-shot Fine-Grained Visual Recognition (FGVR) and (iii) Semantic Alignment (SA) downstream tasks. For FGVR, detected keypoints improve the classification accuracy. For SA, we showcase a novel thin-plate-spline warping that uses estimated keypoint uncertainty under imperfect keypoint corespondences.

关键词： Training Location awareness Representation learning Computer vision visualization Uncertainty Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Critical Issues in Bias Mitigation Techniques 22

An Investigation of Critical Issues in Bias Mitigation Techn...

引用

22nd ieee/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Shrestha, Robik Kafle, Kushal Kanan, Christopher Rochester Inst Technol Rochester NY 14623 USA Adobe Res San Jose CA USA Paige Rochester NY USA Cornell Tech New York NY USA

ISBN: (纸本)9781665409155

A critical problem in deep learning is that systems learn inappropriate biases, resulting in their inability to perform well on minority groups. This has led to the creation of multiple algorithms that endeavor to mitigate bias. However, it is not clear how effective these methods are. This is because study protocols differ among papers, systems are tested on datasets that fail to test many forms of bias, and systems have access to hidden knowledge or are tuned specifically to the test set. To address this, we introduce an improved evaluation protocol, sensible metrics, and a new dataset, which enables us to ask and answer critical questions about bias mitigation algorithms. We evaluate seven state-of-the-art algorithms using the same network architecture and hyperparameter selection policy across three benchmark datasets. We introduce a new dataset called Biased MNIST that enables assessment of robustness to multiple bias sources. We use Biased MNIST and a visual question answering (VQA) benchmark to assess robustness to hidden biases. Rather than only tuning to the test set distribution, we study robustness across different tuning distributions, which is critical because for many applications the test distribution may not be known during development. We find that algorithms exploit hidden biases, are unable to scale to multiple forms of bias, and are highly sensitive to the choice of tuning set. Based on our findings, we implore the community to adopt more rigorous assessment of future bias mitigation methods. All data, code, and results are publicly available(1).

关键词： Measurement Deep learning visualization Computer vision Protocols Codes Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Plotting Method for Large-Scale Symbols

An Adaptive Plotting Method for Large-Scale Symbols

引用

2022 International conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2022

作者： Zhong, Zhinong Ni, Hao Liu, Feng Yang, Anran College of Electronic Science National University of Defense Technology Changsha China

ISBN: (数字)9781665498586

ISBN: (纸本)9781665498586

In view of current shortcomings in solving problem of overlapping when plotting large-scale symbols, this paper aims to explore an adaptive plotting method for large-scale symbols and data visualization. We utilize improved SA algorithm to achieve an automatic avoidance of similar classes, and employ SP-DBSCAN algorithm to achieve automatic clustering of different classes. We construct a qualitive evaluation model based on the two algorithms mentioned above and optimize key procedures of each algorithm. Eventually, through practical experiments, we compare the visualization effect and algorithm performance of different schemes, whose results verify that our technical scheme is more effective and superiority. Then we demonstrate the new solution in large scale symbols plotting, which might be effectively applied to practical application. © 2022 ieee.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Collaborative Dataset Exploration in VR: The Impact of Gaze visualization on Tutors’ Spatial Guidance and Communication

Enhancing Collaborative Dataset Exploration in VR: The Impac...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), ieee conference on

作者： Adil Khokhar Christoph W. Borst Md Istiak Jaman Ami Niloofar Heidarikohol University of Louisiana at Lafayette

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

We investigate the effects of gaze visualization on instructional communication and effectiveness in a collaborative geosciences virtual reality (VR) environment. Our study provides new, specific insights into the effects of gaze visualization on guidance strategies, based on detailed communication analysis. Unlike prior research that employed simplified tasks (e.g., tangram puzzles or identifying symbols), we focused on realistic tasks involving the identification, alignment, and matching of 3D geo-terrain dataset *** the study, subjects acted as tutors leading students (confederates blind to the condition) through three terrain interpretation tasks, locating, aligning, and matching geological terrain features, in a collaborative VR environment. The subjects performed tasks under two conditions: with and without live visualization of student gaze. We analyzed subjective ratings, task completion times, number of words spoken, and time spent looking at the student. Our findings indicate that gaze visualization not only reduces the overall time and verbal instructions required for corrective guidance, but also shifts the way participants provide guidance. This shift is reflected by fewer words used and shorter task completion times, suggesting a more efficient and visually oriented communication strategy. This suggests that gaze visualization enabled tutors to use more effective spatial guidance strategies thus reducing the reliance on extended verbal descriptions.

关键词： Hands visualization Three-dimensional displays Uncertainty Geology Collaboration Symbols Virtual reality User interfaces Real-time systems

来源：评论

学校读者我要写书评

暂无评论

An Interactive Dashboard for Visualizing the Provenance of Software Development Processes

An Interactive Dashboard for Visualizing the Provenance of S...

引用

Working conference on Software visualization (VISSOFT)

作者： Schreiber, Andreas von Kurnatowski, Lynn Meinecke, Annika de Boer, Claas German Aerosp Ctr DLR Inst Software Technol Cologne Germany German Aerosp Ctr DLR Inst Software Technol Wessling Germany German Aerosp Ctr DLR Inst Software Technol Dresden Germany

ISBN: (纸本)9781665431446

Software development is a complex process involving many people and development tools and their interactions;during development, a lot of data such as source code, documents, or software artifacts and information such as issues, discussions, or code analyses are generated or modified. In addition to the analysis and visualization of software systems, it is useful to analyze the software development process to obtain better information about the quality, reliability, and trustworthiness of the software. To gain insights and knowledge about software development processes, we extract the provenance of development processes, especially from version control systems for Git-based software projects, and visualize the provenance information using graph visualization, metrics representation, and development timelines;including an integration of these methods into a web-based dashboard. With the help of visual provenance representations, project managers can gain an overview and insights into development progress, effects of process changes, and interactions among developers and with external contributors, which we exemplify with a case study of a software with high social relevance.

关键词： provenance software visualization software development processes visual analytics interactive dashboards

来源：评论

学校读者我要写书评

暂无评论

Drift Reduced Navigation with Deep Explainable Features

Drift Reduced Navigation with Deep Explainable Features

引用

ieee/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Mama, Mohd Sripada, Sundar V. S. Chinchali, Sandeep Singh, Arun Kumar Krishna, K. Madhava IIT Hyderabad Robot Res Ctr Hyderabad Telangana India Univ Texas Austin ECT Dept Austin TX 78712 USA Univ Tartu Inst Technol Tartu Estonia

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

Modern autonomous vehicles (AVs) often rely on vision, LIDAR, and even radar-based simultaneous localization and mapping (SLAM) frameworks for precise localization and navigation. However, modern SLAM frameworks often lead to unacceptably high levels of drift (i.e., localization error) when AVs observe few visually distinct features or encounter occlusions due to dynamic obstacles. This paper argues that minimizing drift must be a key desiderata in AV motion planning, which requires an AV to take active control decisions to move towards feature-rich regions while also minimizing conventional control cost. To do so, we first introduce a novel data-driven perception module that observes LIDAR point clouds and estimates which features/regions an AV must navigate towards for drift minimization. Then, we introduce an interpretable model predictive controller (MPC) that moves an AV toward such feature-rich regions while avoiding visual occlusions and gracefully trading off drift and control cost. Our experiments on challenging, dynamic scenarios in the state-ofthe-art CARLA simulator indicate our method reduces drift up to 76.76% compared to benchmark approaches.

关键词： Location awareness visualization Simultaneous localization and mapping Laser radar Costs Navigation Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Assessing the Importance of Video visualization Timings in a Flipped Classroom Context 53

Assessing the Importance of Video Visualization Timings in a...

引用

53rd ieee ASEE Frontiers in Education International conference, FIE 2023

作者： Liz-Domínguez, Martín Caeiro-Rodríguez, Manuel Mikic-Fonte, Fernando Llamas-Nistal, Martín AtlanTTic Research Center University of Vigo Vigo36310 Spain

ISBN: (纸本)9798350336429

This Research Work-in-Progress focuses on how students make use of supporting videos provided in a flipped classroom context. More specifically, this study analyzes the academic implications of the timing of video accesses: late (during the few days preceding an exam) or early. The experiment was performed in a first-year engineering course. The course is divided into 6 splits, ranging from 2 to 4 weeks each. Every split introduces new videos and ends with an exam. Data from 90 first-year students were collected. Two main analysis tasks were undertaken: assessing the correlation between the number of videos accessed early or late and exam scores, and student clustering depending on the general timing of video accesses. Significant correlation between early accesses and exam scores was only observed on the first split. Also in this first split, 3 student groups were identified via clustering: low activity, mostly late and mostly early. Interestingly, there were significant differences in long-term performance between these groups. This is a valuable result towards the development of an early warning system, as it helps identify students at risk at a early stage. © 2023 ieee.

关键词： continuous assessment data correlation flipped classroom higher education learning analytics

来源：评论

学校读者我要写书评

暂无评论

Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning 39

Seeking Visual Discomfort: Curiosity-driven Representations ...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Aljalbout, Elie Ulmer, Maximilian Triebel, Rudolph Tech Univ Munich TUM D-80797 Munich Germany German Aerosp Ctr Ins Robot & Mechatron D-82234 Wessling Germany

ISBN: (纸本)9781728196817

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image observations. This has led to increased attention on integrating state representation learning (SRL) techniques into the RL pipeline. Work in this field demonstrates a substantial improvement in sample efficiency among other benefits. However, to take full advantage of this paradigm, the quality of samples used for training plays a crucial role. More importantly, the diversity of these samples could affect the sample efficiency of vision-based RL, but also its generalization capability. In this work, we present an approach to improve sample diversity for state representation learning. Our method enhances the exploration capability of RL algorithms, by taking advantage of the SRL setup. Our experiments show that our proposed approach boosts the visitation of problematic states, improves the learned state representation, and outperforms the baselines for all tested environments. These results are most apparent for environments where the baseline methods struggle. In simple environments, our method contributes to stabilizing the training, reducing the reward variance, and improving sample efficiency.

关键词： Representation learning Training visualization Automation Transfer learning Pipelines Reinforcement learning

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 << < 400 401 402 403 404 405 406 407 408 409 > >>

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：