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

52,950 篇 会议
1,122 篇 期刊文献
6 册 图书

馆藏范围

54,078 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

26,304 篇 工学
- 17,133 篇 计算机科学与技术...
- 9,445 篇 软件工程
- 8,117 篇 电气工程
- 3,780 篇 控制科学与工程
- 2,421 篇 信息与通信工程
- 2,394 篇 机械工程
- 1,899 篇 生物医学工程（可授...
- 1,311 篇 仪器科学与技术
- 1,054 篇 生物工程
- 777 篇 电子科学与技术（可...
- 730 篇 土木工程
- 691 篇 建筑学
- 674 篇 光学工程
- 527 篇 交通运输工程
- 486 篇 测绘科学与技术
- 387 篇 安全科学与工程
4,515 篇 理学
- 1,747 篇 数学
- 1,311 篇 物理学
- 984 篇 生物学
- 699 篇 系统科学
- 433 篇 统计学（可授理学、...
- 399 篇 化学
3,461 篇 管理学
- 2,114 篇 管理科学与工程(可...
- 1,607 篇 图书情报与档案管...
- 767 篇 工商管理
3,101 篇 医学
- 2,682 篇 临床医学
- 752 篇 基础医学(可授医学...
- 361 篇 药学(可授医学、理...
674 篇 教育学
- 660 篇 教育学
515 篇 农学
- 485 篇 作物学
342 篇 法学
189 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

34,665 篇 visualization
7,343 篇 data visualizati...
4,835 篇 training
4,314 篇 feature extracti...
2,957 篇 computational mo...
2,942 篇 three-dimensiona...
2,914 篇 cameras
2,454 篇 computer vision
2,439 篇 semantics
2,073 篇 task analysis
1,936 篇 conferences
1,622 篇 accuracy
1,315 篇 image color anal...
1,299 篇 data mining
1,284 篇 image segmentati...
1,265 篇 navigation
1,202 篇 robustness
1,189 篇 data models
1,146 篇 real-time system...
1,101 篇 shape

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...
40 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 ...
30 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
19 篇 wei liu

语言

53,556 篇 英文
281 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 54078 条记录，以下是4661-4670 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：

Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

Unified Multivariate Gaussian Mixture for Efficient Neural I...

引用

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

作者： Zhu, Xiaosu Song, Jingkuan Gao, Lianli Zheng, Feng Shen, Heng Tao Univ Elect Sci & Technol China Ctr Future Media Chengdu Sichuan Peoples R China Southern Univ Sci & Technol Shenzhen Guangdong Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Modeling latent variables with priors and hyperpriors is an essential problem in variational image compression. Formally, trade-off between rate and distortion is handled well if priors and hyperpriors precisely describe latent variables. Current practices only adopt univariate priors and process each variable individually. However, we find intercorrelations and intra-correlations exist when observing latent variables in a vectorized perspective. These findings reveal visual redundancies to improve rate-distortion performance and parallel processing ability to speed up compression. This encourages us to propose a novel vectorized prior. Specifically, a multivariate Gaussian mixture is proposed with means and covariances to be estimated. Then, a novel probabilistic vector quantization is utilized to effectively approximate means, and remaining covariances are further induced to a unified mixture and solved by cascaded estimation without context models involved. Furthermore, codebooks involved in quantization are extended to multi-codebooks for complexity reduction, which formulates an efficient compression procedure. Extensive experiments on benchmark datasets against state-of-the-art indicate our model has better rate-distortion performance and an impressive 3.18x compression speed up, giving us the ability to perform real-time, high-quality variational image compression in practice. Our source code is publicly available at https://***/xiaosu-zhu/McQuic.

关键词： visualization Image coding Codes Vector quantization Redundancy Rate-distortion Rate distortion theory

来源：评论

学校读者我要写书评

暂无评论

Advanced visualization of Power, Temperature, and Energy Metrics in HPE Cray EX Systems

Advanced Visualization of Power, Temperature, and Energy Met...

引用

2024 International conference on Cluster Computing

作者： Lavanya, L. Ceballos, Stefan Hewlett Packard Enterprise HPC AI & Labs Houston TX 77389 USA

ISBN: (纸本)9798350383461;9798350383454

High-Performance Computing (HPC) environments often consist of clusters with numerous nodes that vary in hardware configurations. These nodes, which can number in the hundreds or thousands, each play a crucial role in the overall computational power and efficiency of the HPC cluster. The diversity in hardware configurations among these nodes introduces a significant level of complexity in displaying this data in an understandable format. Grafana was already established in HPE Performance Cluster Manager (HPCM) as a graphical display for metrics, but no Grafana solutions existed that could display thousands of nodes. An in-house plugin for Grafana was developed that allowed thousands of nodes to be represented as small colored rectangles. The HPE Clusterview Grafana plugin was designed to be as generic as possible, allowing a variety of metrics from varying data sources to be displayed with the same plugin. This flexibility enabled it to be used to create dashboards not only for metrics such as power usage and temperature, but also for the state of nodes and the results of benchmarking software. The physical layout of the data center could also be mirrored in the dashboards thanks to this built-in flexibility. All these attributes together played a significant role in reducing cluster bring-up times. However, despite its adaptability, the initial setup of a Grafana panel of the HPE Clusterview plugin still required manual configuration, which could be time-consuming and susceptible to human error. Prior to this method, there was a significant human-in-the-loop overhead to customize these dashboards with specific regex for each HPC system. A developer was required to manually configure each panel for each customer's cluster based on the layout of the data center and server placements. Our solution intelligently detects the hardware type of each cluster and subsequently configures the HPE Clusterview panels accordingly. This automation not only streamlines the setup pr

关键词： grafana clusterview hpcm exascale monitoring dashboards

来源：评论

学校读者我要写书评

暂无评论

SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization

SCS-Co: Self-Consistent Style Contrastive Learning for Image...

引用

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

作者： Hang, Yucheng Xia, Bin Yang, Wenming Liao, Qingmin Tsinghua Univ Shenzhen Int Grad Sch Beijing Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Image harmonization aims to achieve visual consistency in composite images by adapting a foreground to make it compatible with a background. However, existing methods always only use the real image as the positive sample to guide the training, and at most introduce the corresponding composite image as a single negative sample for an auxiliary constraint, which leads to limited distortion knowledge, and further causes a too large solution space, making the generated harmonized image distorted. Besides, none of them jointly constrain from the foreground self-style and foreground-background style consistency, which exacerbates this problem. Moreover, recent region-aware adaptive instance normalization achieves great success but only considers the global background feature distribution, making the aligned foreground feature distribution biased. To address these issues, we propose a self-consistent style contrastive learning scheme (SCS-Co). By dynamically generating multiple negative samples, our SCS-Co can learn more distortion knowledge and well regularize the generated harmonized image in the style representation space from two aspects of the foreground self-style and foreground-background style consistency, leading to a more photorealistic visual result. In addition, we propose a background-attentional adaptive instance normalization (BAIN) to achieve an attention-weighted background feature distribution according to the foreground-background feature similarity. Experiments demonstrate the superiority of our method over other state-of-the-art methods in both quantitative comparison and visual analysis.

关键词： Training visualization Computer vision Distortion Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

edge-SR: Super-Resolution For The Masses 22

edge-SR: Super-Resolution For The Masses

引用

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

作者： Michelini, Pablo Navarrete Lu, Yunhua Jiang, Xingqun BOE Technol Grp Co Ltd Beijing Peoples R China

ISBN: (纸本)9781665409155

Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On one hand, the current trend in Edge-AI chips shows a promising future in this direction, with rapid development of hardware that can run deep-learning tasks efficiently. On the other hand, in image SR only few architectures have pushed the limit to extreme small sizes that can actually run on edge devices at realtime. We explore possible solutions to this problem with the aim to fill the gap between classic upscalers and small deep learning configurations. As a transition from classic to deep-learning upscaling we propose edge-SR (eSR), a set of one-layer architectures that use interpretable mechanisms to upscale images. Certainly, a one-layer architecture cannot reach the quality of deep learning systems. Nevertheless, we find that for high speed requirements, eSR becomes better at trading-off image quality and runtime performance. Filling the gap between classic and deep-learning architectures for image upscaling is critical for massive adoption of this technology. It is equally important to have an interpretable system that can reveal the inner strategies to solve this problem and guide us to future improvements and better understanding of larger networks.

关键词： Deep learning Image quality visualization Runtime Image edge detection Superresolution Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Exploring Frequency Adversarial Attacks for Face Forgery Detection

Exploring Frequency Adversarial Attacks for Face Forgery Det...

引用

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

作者： Jia, Shuai Ma, Chao Yao, Taiping Yin, Bangjie Ding, Shouhong Yang, Xiaokang Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China Tencent Youtu Lab Shenzhen Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Various facial manipulation techniques have drawn serious public concerns in morality, security, and privacy. Although existing face forgery classifiers achieve promising performance on detecting fake images, these methods are vulnerable to adversarial examples with injected imperceptible perturbations on the pixels. Meanwhile, many face forgery detectors always utilize the frequency diversity between real and fake faces as a crucial clue. In this paper, instead of injecting adversarial perturbations into the spatial domain, we propose a frequency adversarial attack method against face forgery detectors. Concretely, we apply discrete cosine transform (DCT) on the input images and introduce a fusion module to capture the salient region of adversary in the frequency domain. Compared with existing adversarial attacks (e.g. FGSM, PGD) in the spatial domain, our method is more imperceptible to human observers and does not degrade the visual quality of the original images. Moreover, inspired by the idea of meta-learning, we also propose a hybrid adversarial attack that performs attacks in both the spatial and frequency domains. Extensive experiments indicate that the proposed method fools not only the spatial-based detectors but also the state-ofthe-art frequency-based detectors effectively. In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.

关键词： visualization Face recognition Frequency-domain analysis Perturbation methods Computational modeling Detectors Transforms

来源：评论

学校读者我要写书评

暂无评论

Generating Descriptive Explanations of Machine Learning Models Using LLM

Generating Descriptive Explanations of Machine Learning Mode...

引用

ieee International conference on Big Data

作者： Andrew Pang Hyeju Jang Shiaofen Fang Horace Greeley High School NY Luddy School of Informatics Computing and Engineering Indiana University Indianapolis

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Machine learning algorithms play a pivotal role in a wide range of Artificial Intelligence (AI) applications. Explaining the results and behavior of a machine learning model, however, remains a challenge. In this paper, we present a new approach to the explanation of machine learning models using a large language model (LLM). In this work, we seek natural language descriptions of the behavioral patterns of a machine learning model by a combination of prompting and model sampling. A subspace sampling technique is developed to generate ML model outputs using partial features in a user defined space. A projective visualization method is employed to guide the sampling process, including user-directed interactive sampling and feature-based sampling, so that an optimal amount of information can be provided to the LLM to ensure accurate and concise natural language explanations. Two public datasets, a student performance dataset and a weather dataset, were used to test our approach under various conditions.

关键词： visualization Systematics Machine learning algorithms Large language models Natural languages Machine learning Big Data Data models Human in the loop Meteorology

来源：评论

学校读者我要写书评

暂无评论

Unveiling Real-Life Effects of Online Photo Sharing 22

Unveiling Real-Life Effects of Online Photo Sharing

引用

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

作者： Nguyen, Van-Khoa Popescu, Adrian Deshayes-Chossart, Jerome Univ Paris Saclay CEA List F-91120 Palaiseau France

ISBN: (纸本)9781665409155

Social networks give free access to their services in exchange for the right to exploit their users' data. Data sharing is done in an initial context which is chosen by the users. However, data are used by social networks and third parties in different contexts which are often not transparent. In order to unveil such usages, we propose an approach which focuses on the effects of data sharing in impactful real-life situations. Focus is put on visual content because of its strong influence in shaping online user profiles. The approach relies on three components: (1) a set of visual objects with associated situation impact ratings obtained by crowdsourcing, (2) a corresponding set of object detectors for mining users' photos and (3) a ground truth dataset made of 500 visual user profiles which are manually rated per situation. These components are combined in LERVUP, a method which learns to rate visual user profiles in each situation. LERVUP exploits a new image descriptor which aggregates object ratings and object detections at user level and an attention mechanism which boosts highly-rated objects to prevent them from being overwhelmed by low-rated ones. Performance is evaluated per situation by measuring the correlation between the automatic ranking of profile ratings and a manual ground truth. Results indicate that LERVUP is effective since a strong correlation of the two rankings is obtained. A practical implementation of the approach in a mobile app which raises user awareness about shared data usage is also discussed.

关键词： Crowdsourcing visualization Computer vision Correlation Social networking (online) Object detection Manuals

来源：评论

学校读者我要写书评

暂无评论

MERLOT RESERVE: Neural Script Knowledge through Vision and Language and Sound

MERLOT RESERVE: Neural Script Knowledge through Vision and L...

引用

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

作者： Zellers, Rowan Lu, Jiasen Lu, Ximing Yu, Youngjae Zhao, Yanpeng Salehi, Mohammadreza Kusupati, Aditya Hessel, Jack Farhadi, Ali Choi, Yejin Univ Washington Paul G Allen Sch Comp Sci & Engn Seattle WA 98195 USA Allen Inst Artificial Intelligence Seattle WA USA Univ Edinburgh Edinburgh Midlothian Scotland

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce MERLOT RESERVE, a model that represents videos jointly over time - through a new training objective that learns from audio, subtitles, and video frames. Given a video, we replace snippets of text and audio with a MASK token;the model learns by choosing the correct masked-out snippet. Our objective learns faster than alternatives, and performs well at scale: we pretrain on 20 million YouTube videos. Empirical results show that MERLOT RESERVE learns strong multimodal representations. When finetuned, it sets state-of-the-art on Visual Commonsense Reasoning (VCR), TVQA, and Kinetics-600;outperforming prior work by 5%, 7%, and 1.5% respectively. Ablations show that these tasks benefit from audio pretraining - even VCR, a QA task centered around images (without sound). Moreover, our objective enables out-of-the-box prediction, revealing strong multimodal commonsense understanding. In a fully zero-shot setting, our model obtains competitive results on four video tasks, even outperforming supervised approaches on the recently proposed Situated Reasoning (STAR) benchmark. We analyze why audio enables better vision-language representations, suggesting significant opportunities for future research. We conclude by discussing ethical and societal implications of multimodal pretraining.

关键词： Training Representation learning visualization Ethics Video on demand Navigation Stars

来源：评论

学校读者我要写书评

暂无评论

LIVE-ITS: LSH-based Interactive visualization Explorer for Large-Scale Incomplete Time Series

LIVE-ITS: LSH-based Interactive Visualization Explorer for L...

引用

ieee International conference on Big Data

作者： Hongjie Chen Aaron D. Beachnau Panos Thomas Pranav Maneriker Josh Kimball Ryan A. Rossi Dolby Labs. Atlanta USA Adobe Research San Jose USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Recent advances in time series research have created a significant demand for better time series visualization techniques, especially for large-scale datasets that contain millions of time series or more. In this paper, we consider a common use scenario where analysts aim to identify representative time series from a large collection. These representative time series generalize as many time series as possible and can be used for downstream tasks. Building a visualization system for this scenario involves many challenges, including visualizing, selecting, and highlighting a subset of time series from the overall dataset. Moreover, the potential for time series to be incomplete due to missing records adds an extra layer of difficulty. To address these challenges, we propose a novel visualization system, called the Locality Sensitive Hashing-based Interactive visualization Explorer for large-scale Incomplete Time Series (LIVE-ITS). On the frontend, LIVE-ITS allows analysts to interact with the system and select representative time series in areas of interest. In the backend, LIVE-ITS not only selects an optimal subset that represents as many time series as possible, but also achieves the best possible time complexity. Experiments on both synthetic dataset and real-world datasets show that LIVE-ITS exhibits high partition accuracy and high response efficiency, further validating the effectiveness of our proposed visualization system.

关键词： Accuracy Runtime Scalability Time series analysis Buildings Data visualization Big Data Labeling Time complexity Synthetic data

来源：评论

学校读者我要写书评

暂无评论

MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering

MuKEA: Multimodal Knowledge Extraction and Accumulation for ...

引用

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

作者： Ding, Yang Yu, Jing Liu, Bang Hu, Yue Cui, Mingxin Wu, Qi Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Univ Montreal Montreal PQ Canada Mila Quebec AI Inst Montreal PQ Canada Univ Adelaide Adelaide SA Australia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only knowledge bases, which merely contain facts expressed by first-order predicates or language descriptions while lacking complex but indispensable multimodal knowledge for visual understanding. How to construct vision-relevant and explainable multimodal knowledge for the VQA scenario has been less studied. In this paper, we propose MuKEA to represent multimodal knowledge by an explicit triplet to correlate visual objects and fact answers with implicit relations. To bridge the heterogeneous gap, we propose three objective losses to learn the triplet representations from complementary views: embedding structure, topological relation and semantic space. By adopting a pre-training and fine-tuning learning strategy, both basic and domain-specific multimodal knowledge are progressively accumulated for answer prediction. We outperform the state-of-the-art by 3.35% and 6.08% respectively on two challenging knowledge-required datasets: OK-VQA and KRVQA. Experimental results prove the complementary benefits of the multimodal knowledge with existing knowledge bases and the advantages of our end-to-end framework over the existing pipeline methods. The code is available at https://***/AndersonStra/MuKEA.

关键词： Bridges visualization Computer vision Codes Computational modeling Knowledge based systems Semantics

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 << < 463 464 465 466 467 468 469 470 471 472 > >>

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：