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

2,536 篇 会议
235 篇 期刊文献
12 篇 学位论文
4 册 图书

馆藏范围

2,787 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,983 篇 工学
- 1,440 篇 计算机科学与技术...
- 822 篇 软件工程
- 368 篇 电气工程
- 155 篇 控制科学与工程
- 124 篇 信息与通信工程
- 86 篇 土木工程
- 82 篇 生物医学工程（可授...
- 77 篇 生物工程
- 74 篇 测绘科学与技术
- 73 篇 机械工程
- 70 篇 建筑学
- 63 篇 石油与天然气工程
- 55 篇 仪器科学与技术
- 54 篇 化学工程与技术
- 48 篇 动力工程及工程热...
- 45 篇 光学工程
- 45 篇 航空宇航科学与技...
645 篇 理学
- 274 篇 物理学
- 195 篇 数学
- 93 篇 生物学
- 88 篇 统计学（可授理学、...
- 60 篇 地球物理学
- 59 篇 化学
- 53 篇 地质学
304 篇 管理学
- 157 篇 管理科学与工程(可...
- 153 篇 图书情报与档案管...
- 64 篇 工商管理
268 篇 医学
- 228 篇 临床医学
- 55 篇 基础医学(可授医学...
48 篇 法学
- 45 篇 社会学
38 篇 教育学
30 篇 农学
11 篇 经济学
10 篇 文学
8 篇 艺术学

主题

417 篇 visualization
327 篇 data visualizati...
206 篇 visual analytics
120 篇 data mining
119 篇 data analysis
63 篇 task analysis
61 篇 big data
58 篇 data models
52 篇 information visu...
46 篇 analytical model...
46 篇 feature extracti...
43 篇 image color anal...
39 篇 training
38 篇 deep learning
37 篇 computational mo...
36 篇 time series anal...
35 篇 information anal...
34 篇 semantics
33 篇 machine learning
32 篇 navigation

机构

15 篇 vrvis res ctr au...
15 篇 univ konstanz co...
12 篇 vrvis research c...
12 篇 university of ko...
11 篇 purdue univ w la...
9 篇 hong kong univ s...
8 篇 graz univ techno...
7 篇 tu wien austria
7 篇 zhejiang univ pe...
7 篇 univ essex colch...
7 篇 mit cambridge ma...
7 篇 univ maryland co...
7 篇 univ politehn bu...
7 篇 stanford univ st...
6 篇 univ grenoble al...
6 篇 purdue universit...
6 篇 lovely professio...
6 篇 arizona state un...
6 篇 univ calif davis...
6 篇 virginia tech bl...

作者

19 篇 keim daniel a.
18 篇 schreck tobias
14 篇 hauser helwig
14 篇 matkovic kresimi...
12 篇 gracanin denis
11 篇 elmqvist niklas
10 篇 qu huamin
10 篇 ma kwan-liu
9 篇 ertl thomas
9 篇 amer-yahia sihem
9 篇 chen wei
9 篇 rundensteiner el...
8 篇 maciejewski ross
8 篇 kwan-liu ma
8 篇 ward matthew o.
8 篇 ionescu bogdan
8 篇 heer jeffrey
8 篇 hamann bernd
8 篇 chen siming
8 篇 splechtna rainer

语言

2,737 篇 英文
33 篇 其他
16 篇 中文
2 篇 葡萄牙文
2 篇 俄文
1 篇 法文

检索条件"任意字段=Conference on Visual Data Exploration and Analysis II"

共 2787 条记录，以下是31-40 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：

Scaling Multilingual visual Speech Recognition

Scaling Multilingual Visual Speech Recognition

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： K R Prajwal Sindhu Hegde Andrew Zisserman VGG University of Oxford

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

visual Speech Recognition (lip-reading) has witnessed tremendous improvements, reaching word error rates as low as 12.8 WER in English. However, the performance in other languages is lagging far behind, due to the lack of labeled multilingual video data. In this work, we reduce the performance gap with the help of three key advances: (i) introducing the largest multilingual lip-reading dataset to date, (ii) proposing a single multi-task architecture that can perform two tasks simultaneously: identify the language and transcribe the utterance, and (iii) jointly training this architecture on all the languages together, resulting in large WER improvements as opposed to training monolingual models separately. We achieve state-of-the-art performance in both visual language identification and multilingual lip-reading tasks. Moreover, our pipeline uses zero manual annotations, as all the training transcriptions are obtained using a pre-trained ASR model. We also show that our multilingual model can be readily fine-tuned for new low-resource languages on which models trained from scratch do not converge. Our data, code, and models are available at: ***/∼vgg/research/multivsr.

关键词： Training visualization Error analysis Pipelines Speech recognition Manuals Signal processing Multitasking Multilingual Speech processing

来源：评论

学校读者我要写书评

暂无评论

AutoGaze: A Very Initial exploration in A SAM2-based Pipeline for Automated Eye-Object Interaction analysis in First-Person Videos

AutoGaze: A Very Initial Exploration in A SAM2-based Pipelin...

引用

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

作者： Qing Zhang Yifei Huang Jun Rekimoto The University of Tokyo Sony CSL Kyoto

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

This paper presents a novel automated workflow for analyzing eye-tracking data in first-person videos. Our system uses the Segment Anything Model 2 (SAM2) to segment and track objects, correlating them with gaze information to provide a detailed understanding of visual attention and hand-object interactions. The pipeline outputs a structured JSON file containing rich information about gaze behavior, object interactions, and their temporal relationships. We demonstrate the system’s effectiveness in a life science operational context and compare its performance with a multimodal Large Language Model (LLM) for automated annotation. Our findings highlight the potential of combining advanced computer vision techniques with LLMs for comprehensive and scalable analysis of gaze behavior in real-world scenarios.

关键词： visualization Solid modeling Three-dimensional displays Pipelines Gaze tracking Virtual reality User interfaces Life sciences Trajectory Videos

来源：评论

学校读者我要写书评

暂无评论

visual Analyze the Impact of Structural Features and Node Attributes on Collaborative Relationships 19th

Visual Analyze the Impact of Structural Features and Node...

引用

19th CCF conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Lu, Qiang Ma, Cheng Wu, Hongfeng Zhang, Gaofeng Yu, Ye School of Computer Science and Information Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China

ISBN: (纸本)9789819623754

Collaborative relationships are becoming more complex, diversified and multi-organization cross, which poses new challenges to collaborative relationship analysis. In order to analyze the effects of different structural features and node attributes on the overall cooperative relationships, and to support the exploration at the global, group and individual levels to promote the comprehensive analysis of cooperative relationships, we propose a visual analysis method based on graph contrast learning(GCL). The first step is to perturb the structural features and node attributes of the collaboration relationships through data augmentation. The second step is to use the graph convolutional network(GCN) to represent the structural features and node attributes as dense vectors in the high-dimensional vector space. The third step is to explore the influence of different structural features and node attributes through classification task outcome indicators. Based on this method, GCL4Vis, an interactive visual analysis system is designed, which is equipped with a variety of visual views to help users analyze the effects of different structural features and node attributes. Finally, this paper verified the usability and effectiveness of the GCL4Vis visual analysis system through specific case studies and structured interviews with users. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Research on Early Warning of Drug Crime Behaviors Based on data-driven Method 24

Research on Early Warning of Drug Crime Behaviors Based on D...

引用

Proceedings of the 2024 4th International conference on Big data, Artificial Intelligence and Risk Management

作者： Shaobing Wu Changmei Wang Institute of Information Security Key Laboratory of Intelligent Drug Control Yunnan Police College Kunming Yunnan China Education Ministry Key Laboratory of Advanced Technology and Preparation for Renewable Energy Materials Yunnan Normal University Kunming Yunnan China

ISBN: (纸本)9798400709753

The identification of target suspects in images and videos from multi-source heterogeneous data is a difficult task in criminal investigation. In criminal scene analysis during law enforcement, images and videos from surveillance applications and security systems play an important role in providing visual files for the scene. With the rise of big data, artificial intelligence, the Internet of Things, blockchain, and cyberspace security, it is particularly important to improve the application of computer technology in drug crime cases and achieve data-driven drug crime behavior prediction. This paper builds police subject-specific databases such as drug addicts, drug traffickers, key personnel, and fugitives, and achieves drug crime behavior prediction and warning based on identity information, facial recognition and storage and picture comparison using a combination of Python and OpenCV. It provides a useful exploration for combating Drug Crime.

关键词： data-driven

来源：评论

学校读者我要写书评

暂无评论

A Critical Assessment of visual Sound Source Localization Models Including Negative Audio

A Critical Assessment of Visual Sound Source Localization Mo...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xavier Juanola Gloria Haro Magdalena Fuentes Universitat Pompeu Fabra Barcelona Spain MARL-IDM New York University New York USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The task of visual Sound Source Localization (VSSL) involves identifying the location of sound sources in visual scenes, integrating audio-visual data for enhanced scene understanding. Despite advancements in state-of-the-art (SOTA) models, we observe three critical flaws: i) The evaluation of the models is mainly focused in sounds produced by objects that are visible in the image, ii) The evaluation often assumes a prior knowledge of the size of the sounding object, and iii) No universal threshold for localization in real-world scenarios is established, as previous approaches only consider positive examples without accounting for both positive and negative cases. In this paper, we introduce extended test sets and new metrics designed to complete the current standard evaluation of VSSL models by testing them in scenarios where none of the objects in the image corresponds to the audio input, i.e. a negative audio. We consider three types of negative audio: silence, noise and offscreen. Our analysis reveals that numerous SOTA models fail to appropriately adjust their predictions based on audio input, suggesting that these models may not be leveraging audio information as intended. Additionally, we provide a comprehensive analysis of the range of maximum values in the estimated audio-visual similarity maps, in both positive and negative audio cases, and show that most of the models are not discriminative enough, making them unfit to choose a universal threshold appropriate to perform sound localization without any a priori information of the sounding object, that is, object size and visibility.

关键词： Location awareness Measurement visualization Analytical models Noise Predictive models Speech processing Standards Testing Videos

来源：评论

学校读者我要写书评

暂无评论

HS-Gen: Human-Like Handwriting Synthetic Generation—A Preliminary Investigation 27th

HS-Gen: Human-Like Handwriting Synthetic Generation—A Preli...

引用

27th International conference on Pattern Recognition, ICPR 2024

作者： Bensalah, Asma Parziale, Antonio Coccaro, Rosanna Marcelli, Angelo Fornés, Alicia Lladós, Josep Computer Vision Center Universitat Autònoma de Barcelona Barcelona Spain Computer Science Department Universitat Autònoma de Barcelona Barcelona Spain DIEM University of Salerno Via Giovanni Paolo II 132 SA Fisciano84084 Italy AI3S Unit CINI National Laboratory of Artificial Intelligence and Intelligent Systems University of Salerno SA Fisciano Italy

ISBN: (纸本)9783031876592

The application of handwriting analysis in the health field for early detection and diagnosis is limited by a lack of data, which presents a significant challenge for the implementation of deep learning-based models. To address this issue, numerous studies have focused on generating synthetic data. Current methods for generating synthetic handwriting from offline images, including generative models and geometrical techniques, fail to account for the kinematics of handwriting movements, which is critical for achieving more human-like results. To address this limitation, we propose a novel, human-like approach for the synthetic generation of handwriting or drawing from offline images. This method creates new samples by incorporating a trajectory recovery algorithm and a human-like time law generator, as well as the extraction and manipulation of kinematic parameters. The evaluation of the proposed method from both visual and kinematic perspectives demonstrates its potential applicability across a wide range of devices and handwriting styles. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Effect of Gaze visualization on Task Efficiency and User Behavior for Guidance Scenarios in Co-Located AR Collaboration

Effect of Gaze Visualization on Task Efficiency and User Beh...

引用

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

作者： Froso Sarri Katerina Mania School of Electrical & Computer Engineering Technical University of Crete Greece

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

Augmented Reality (AR)-enabled collaboration enhances contextual guidance in shared environments, where unambiguous cues are essential, for swift and accurate task completion. Gaze-based cues offer clear, non-verbal indication of intent, reducing interaction ambiguity. While prior research has studied the effectiveness of gaze-based visualization in scenarios where collaborators share the same level of knowledge, less attention has been shown to guidance scenarios, where one user provides task-related information to another. Existing studies often focus on task outcomes (e.g., completion time, error rate) without analyzing gaze data to gain further insight into user behavior and attention. This study leverages gaze-based cues as an active means of communication in guidance scenarios, assessing their impact on both task performance and user behavior through gaze data analysis. The developed system incorporates gaze-based visualizations, including dynamic representations of gaze behavior, to deliver task-critical guidance. These are compared to verbal instructions using quantitative metrics for task effectiveness and gaze analysis, alongside subjective feedback, to determine whether they reduce ambiguity and enhance collaboration. Our study showed that gaze-based visualizations significantly reduced task related errors, with contextual triggered cues offering the best balance between speed and correctness. Gaze analysis revealed that gaze-based visualizations effectively directed participants’ attention to task-relevant areas, reducing unnecessary visual exploration. Participants reported lower perceived workload in gaze-based conditions, further supporting their effectiveness in enhancing collaboration and reducing ambiguity.

关键词： Human computer interaction Measurement Hands visualization Three-dimensional displays Error analysis Collaboration data visualization Information sharing Augmented reality

来源：评论

学校读者我要写书评

暂无评论

AutoGaze: A Very Initial exploration in A SAM2-based Pipeline for Automated Eye-Object Interaction analysis in First-Person Videos

AutoGaze: A Very Initial Exploration in A SAM2-based Pipelin...

引用

2025 IEEE conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Zhang, Qing Huang, Yifei Rekimoto, Jun The University of Tokyo Japan Sony Csl Kyoto Japan

ISBN: (纸本)9798331514846

This paper presents a novel automated workflow for analyzing eye-tracking data in first-person videos. Our system uses the Segment Anything Model 2 (SAM2) to segment and track objects, correlating them with gaze information to provide a detailed understanding of visual attention and hand-object interactions. The pipeline outputs a structured JSON file containing rich information about gaze behavior, object interactions, and their temporal relationships. We demonstrate the system's effectiveness in a life science operational context and compare its performance with a multimodal Large Language Model (LLM) for automated annotation. Our findings highlight the potential of combining advanced computer vision techniques with LLMs for comprehensive and scalable analysis of gaze behavior in real-world scenarios. © 2025 IEEE.

关键词： automatic event detection egocentric video processing Eye tracking gaze movement trajectory

来源：评论

学校读者我要写书评

暂无评论

Preliminary exploration of Geotechnical data Interpretation and GIS Integration: Toward AI Implementation

Preliminary Exploration of Geotechnical Data Interpretation ...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International conference for

作者： Danah S. Al-Enezi Kuwait Institute for Scientific Research Kuwait

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

Kuwait's rapid urban expansion, driven by large-scale projects, such as AI-Mutlaa City and Silk City, highlights the need for comprehensive geotechnical data to support sustainable development. However, detailed studies on the subsurface geotechnical characteristics of the northern regions of Kuwait are lacking. This study focuses on establishing a preliminary geotechnical database, addressing challenges encountered during its development, and conducting a pilot analysis for AI-Mutlaa City. A questionnaire was distributed to geology, environmental, geotechnical, and engineering professionals to identify the challenges associated with creating the database. The survey revealed issues such as inconsistent data formats, limited access to borehole logs, and the hesitancy of private firms to share data due to security concerns. Despite these challenges, borehole data from ministries and private organizations were collected and organized using Microsoft Excel. These data formed the foundation of the geotechnical database, which was analyzed and visualized using Geographic Information System (GIS) tools. The pilot study in AI-Mutlaa City revealed predominantly dense soil layers, with significant variations in soil strength at a depth of 19.5 m, where standard penetration resistance ranged from 10 to 50 blows. These findings emphasize the variability of soil properties in the area and underscore the importance of site-specific investigations. The established geotechnical database provides valuable insights for construction planning, risk assessment, and geohazard management. Moving forward, the integration of artificial intelligence into the database is planned to enhance data processing, automate soil classification, and predict subsurface conditions in an effort to contribute to advanced geotechnical practices in Kuwait.

关键词： Surveys Technological innovation Accuracy databases Urban areas Soil properties visual databases Artificial intelligence Sustainable development Geographic information systems

来源：评论

学校读者我要写书评

暂无评论

visual data exploration and analysis ii

Visual Data Exploration and Analysis II

引用

visual data exploration and analysis ii 1995

The proceedings contain 47 papers. The topics discussed include: simulation of the fading of photographic three-color materials: a new tool for the preservation field;visualizing the anatomical-functional correlation of the human brain;3D curvilinear lattice as a tool for representing free-form surfaces;vector quantization: a tool for exploration and analysis of multivariate images;glyphs for visualizing uncertainty in environmental vector fields;4d2: a high-performance visualization tool for CFD and particle data visualization;visualization for modeling of charged particle behavior inside electromagnetic complex fields;and performance of the collaborative visualization environment (COVISE) visualization system under different conditions.

关键词：

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279页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：