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

973 篇 会议
72 册 图书
26 篇 期刊文献

馆藏范围

1,071 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

660 篇 工学
- 448 篇 计算机科学与技术...
- 358 篇 软件工程
- 100 篇 电气工程
- 56 篇 信息与通信工程
- 47 篇 控制科学与工程
- 38 篇 光学工程
- 34 篇 机械工程
- 29 篇 建筑学
- 28 篇 土木工程
- 23 篇 测绘科学与技术
- 17 篇 仪器科学与技术
- 12 篇 力学（可授工学、理...
- 12 篇 化学工程与技术
- 11 篇 环境科学与工程（可...
- 11 篇 生物工程
- 10 篇 生物医学工程（可授...
- 9 篇 电子科学与技术（可...
187 篇 理学
- 75 篇 数学
- 57 篇 物理学
- 35 篇 系统科学
- 20 篇 统计学（可授理学、...
- 17 篇 地理学
- 14 篇 生物学
- 13 篇 化学
150 篇 医学
- 147 篇 临床医学
105 篇 管理学
- 79 篇 图书情报与档案管...
- 38 篇 管理科学与工程(可...
- 19 篇 工商管理
15 篇 法学
- 14 篇 社会学
10 篇 教育学
- 10 篇 教育学
8 篇 农学
6 篇 艺术学
5 篇 经济学
1 篇 文学

主题

404 篇 visualization
112 篇 data visualizati...
52 篇 feature extracti...
50 篇 complexity theor...
42 篇 training
35 篇 information visu...
27 篇 three-dimensiona...
27 篇 data mining
27 篇 computational mo...
26 篇 semantics
22 篇 artificial intel...
20 篇 accuracy
19 篇 databases
19 篇 machine learning
18 篇 information syst...
18 篇 image segmentati...
18 篇 image color anal...
18 篇 measurement
17 篇 computer applica...
17 篇 correlation

机构

7 篇 university of gi...
7 篇 visus university...
5 篇 school of automa...
5 篇 polytechnic inst...
5 篇 national cims en...
5 篇 school of mechat...
5 篇 westfalische wil...
5 篇 univ leipzig ima...
4 篇 shanghai jiao to...
4 篇 swiss federal in...
4 篇 university of sy...
4 篇 department of co...
4 篇 university of ca...
4 篇 univ southern de...
3 篇 friedrich alexan...
3 篇 lisa-istia unive...
3 篇 linnaeus univers...
3 篇 tsinghua univers...
3 篇 univ potsdam fac...
3 篇 fraunhofer igd d...

作者

12 篇 linsen lars
11 篇 lin zhang
10 篇 tianyuan xiao
9 篇 scheuermann geri...
7 篇 ertl thomas
7 篇 weiskopf daniel
7 篇 minrui fei
6 篇 josé braz
6 篇 doellner juergen
6 篇 nadia magnenat-t...
6 篇 burch michael
6 篇 scheibel willy
5 篇 limberger daniel
5 篇 mateu sbert
5 篇 feixas miquel
5 篇 shiwei ma
5 篇 molchanov vladim...
5 篇 paul richard
5 篇 kerren andreas
4 篇 blascheck tanja

语言

1,050 篇 英文
14 篇 中文
11 篇 其他
1 篇 葡萄牙文

检索条件"任意字段=Conference on Information Visualization Theory and Applications"

共 1071 条记录，以下是91-100 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：

Multi-Scale Detail Enhancement Network for Image Super-Resolution 26

Multi-Scale Detail Enhancement Network for Image Super-Resol...

引用

26th International conference on Pattern Recognition / 8th International Workshop on Image Mining - theory and applications (IMTA)

作者： Wang, Sen Zheng, Jin Beihang Univ Beijing Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Deep convolutional neural networks (CNNs) are widely used in single image super-resolution (SISR) and provide remarkable performance. However, most existing CNN-based super-resolution (SR) models focus mainly on designing deep or wide architecture and neglect intended detail enhancement, thereby hindering the CNN representational capacity. To resolve this problem, we propose a multi-scale detail enhancement network (MS-DEN) for SISR. Specifically, we introduce a multi-scale detail extraction module (MS-DEM), which first converts features into a 3-channel simulation image, and then, directly extracts detail information from the simulation image space. Furthermore, we concatenate the 3-channel image and extracted detail image to generate detail-guided features. Subsequently, we propose a multi-context channel attention module (MC-CAM) to relatively better fuse local and global features, and enhance features containing discontinuous detail information. With detail enhancement, MS-DEN can restore highly accurate details and lead to performance improvement. Numerous experiments show that our MS-DEN achieves competitive performance against the state-of-the-art methods.

关键词： visualization Fuses Superresolution Feature extraction Image restoration Data mining Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Audio and Video-based Emotion Recognition using Multimodal Transformers 26

Audio and Video-based Emotion Recognition using Multimodal T...

引用

26th International conference on Pattern Recognition / 8th International Workshop on Image Mining - theory and applications (IMTA)

作者： John, Vijay Kawanishi, Yasutomo RIKEN Guardian Robot Project R IH Wako Saitama Japan

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Emotion recognition, an important research problem in human-robot interactions, is primarily achieved by extracting human emotions from audio and visual data. State-of-the-art performance is reported by audio-visual sensor fusion algorithms using deep learning models such as CNN, RNN, and LSTM. However, the RNN and LSTM are shown to be limited in handling the long-term dependencies over the entire input sequence. In this work, we propose to improve the performance of audio-visual emotion recognition using a novel transformer-based model, containing three transformer branches, named multimodal transformers. The three transformer branches, in our work, compute the audio self-attention, the video self-attention, and the audio-video cross attention. The self-attention branches identify the most relevant information in the audio and video input, while the cross-attention branch identifies the most relevant audio-video interactive information. The relevant information from these three branches report the best performance in our ablation study. We also propose a novel temporal embedding scheme, termed block embedding, to add the temporal information to the visual feature, derived from the multiple frames in the video. The proposed architecture is validated using the RAVDESS, CREMA-D, and SAVEE audio-visual public datasets. A detailed ablation study and comparative analysis with baseline models is performed. The results show that the proposed multi-modal transformer framework is better than the baseline methods.

关键词： Deep learning Emotion recognition visualization Computational modeling Human-robot interaction Computer architecture Sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Sketch Based Image Retrieval Using Graph Transformer 26

Zero-Shot Sketch Based Image Retrieval Using Graph Transform...

引用

26th International conference on Pattern Recognition / 8th International Workshop on Image Mining - theory and applications (IMTA)

作者： Gupta, Sumrit Chaudhuri, Ushasi Banerjee, Biplab Kumar, Saurabh Indian Inst Technol Mumbai Maharashtra India Univ Illinois Champaign IL USA Osaka Univ Osaka Japan

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

The performance of a zero-shot sketch-based image retrieval (ZS-SBIR) task is primarily affected by two challenges. The substantial domain gap between image and sketch features needs to be bridged, while at the same time the side information has to be chosen tactfully. Existing literature has shown that varying the semantic side information greatly affects the performance of ZS-SBIR. To this end, we propose a novel graph transformer based zero-shot sketch-based image retrieval (GTZSR) framework for solving ZS-SBIR tasks which uses a novel graph transformer to preserve the topology of the classes in the semantic space and propagates the context-graph of the classes within the embedding features of the visual space. To bridge the domain gap between the visual features, we propose minimizing theWasserstein distance between images and sketches in a learned domain-shared space. We also propose a novel compatibility loss that further aligns the two visual domains by bridging the domain gap of one class with respect to the domain gap of all other classes in the training set. Experimental results obtained on the extended Sketchy, TU-Berlin, and QuickDraw datasets exhibit sharp improvements over the existing state-of-the-art methods in both ZS-SBIR and generalized ZS-SBIR.

关键词： Training Bridges visualization Image retrieval Semantics Transformers Topology

来源：评论

学校读者我要写书评

暂无评论

Dynamic SLAM Based on Neural Network and Depth information

Dynamic SLAM Based on Neural Network and Depth Information

引用

Fully Actuated System theory and applications (CFASTA), conference on

作者： Aoqiang Liu Shu Yang Yuan Fan School of Electrical Engineering and Automation Anhui University Hefei P. R. China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

In the current Simultaneous Localization and Mapping (SLAM) framework, it is assumed that the environment remains static, meaning no changes in objects are detected. However, in real-world scenarios, encountering a dynamic environment where objects exhibit movement is inevitable. To address this issue, and we incorporate real-time object detection network You Only Look Once (YOLO) into our system to detect dynamic objects and mitigate their impact. Our approach utilizes an RGBD camera and develops an algorithm based on depth information to effectively distinguish between background and dynamic objects. By integrating an object detection thread into ORB-SLAM3, our system identifies dynamic objects within the environment while proposing a novel depth weight selection algorithm to maximize the number of static feature points for improved data associations. Finally, we evaluate tracking accuracy using publicly available TUM and BONN datasets.

关键词： YOLO visualization Simultaneous localization and mapping Accuracy Target tracking Heuristic algorithms Instruction sets

来源：评论

学校读者我要写书评

暂无评论

TRC-Unet: Transformer Connections for Near-infrared Blurred Image Segmentation 26

TRC-Unet: Transformer Connections for Near-infrared Blurred ...

引用

26th International conference on Pattern Recognition / 8th International Workshop on Image Mining - theory and applications (IMTA)

作者： Wang, Jiazhe Osamu, Yoshie Shimizu, Koichi Waseda Univ Sch Informat Prod & Syst Fukuoka Japan Waseda Univ Fukuoka Japan Xidian Univ Sch Optoelect Engn Xian Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Imaging blood vessel networks is useful in many biomedical applications, such as injection-assist, cancer detection, various surgery, and vein identification. In NIR (near-infrared) transillumination imaging, we can visualize the subcutaneous blood vessel network. However, such images are severely blurred by the strong scattering of body tissue, and it remains challenging for most models to accurately segment these blurred images. In addition, the convolution operation in the deep learning approach means that it extracts a mixture of blurred edges and clear centers, resulting in gradual distortion during upsampling. In this paper, we propose a novel and efficient deep learning model called TRC-Unet for segmenting blurred NIR images. The transformer connection (TRC) block extracts global spatial information from different scales by adaptively suppressing scattering and increasing the clarity of features. Our proposed transformer feature fusion (TFF) module closes the gap between the highly semantic feature maps of CNN and the adaptive fuzzy transformer output to enable a precise reconstruction of the segmentation. We evaluated TRC-Unet on both a simulated blurred DRIVE dataset and a NIR vessel dataset, and we achieved competitive results. (i.e., 83.86% Dice score on DRIVE and an average boost of 4.6% on simulated images at different depths).

关键词： Deep learning Image segmentation visualization Veins Scattering Surgery Transformers

来源：评论

学校读者我要写书评

暂无评论

18th International Joint conference on Computer Vision, Imaging and Computer Graphics theory and applications, VISIGRAPP 2023

18th International Joint Conference on Computer Vision, Imag...

引用

18th International Joint conference on Computer Vision, Imaging and Computer Graphics theory and applications, VISIGRAPP 2023

ISBN: (纸本)9783031667428

The proceedings contain 17 papers. The special focus in this conference is on Computer Vision, Imaging and Computer Graphics theory and applications. The topics include: Epipolar Equation Weighting for Accurate Camera Motion from Two Consecutive Frames;Absolute-ROMP: Recovering Multi-person 3D Poses and Shapes with Absolute Scales from a Single RGB Image;semi-supervised Task Aware Image-to-Image Translation;deep Detection Dreams: Enhancing visualization Tools for Single Stage Object Detectors;approaches to Face Verification Through Attribute-Based Attention;towards Fast Detection and Classification of Moving Objects;ST-SACLF: Style Transfer Informed Self-attention Classifier for Bias-Aware Painting Classification;attention to Emotions: Body Emotion Recognition In-the-Wild Using Self-attention Transformer Network;linking Data Separation, Visual Separation, Classifier Performance Using Multidimensional Projections;using Cockpit Interactions for Implicit Eye-Tracking Calibration in a Flight Simulator;evaluation of Flexible Structured Light Calibration Using Circles;GPS-Enhanced RGB-D-IMU Calibration for Accurate Pose Estimation;application of Contrast Driven Color-Class Assignment to Four Categorical Data visualization Diagrams;measuring and Interpreting the Quality of 3D Projections of High-Dimensional Data;visualizing Military Operations: Extended Geospatial-Temporal Survey.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Replication Study on Glanceable visualizations: Comparing Different Stimulus Sizes on a Laptop Computer 16

A Replication Study on Glanceable Visualizations: Comparing ...

引用

16th International Joint conference on Computer Vision, Imaging and Computer Graphics theory and applications (VISIGRAPP) / 12th International conference on information visualization theory and applications (IVAPP)

作者： Blascheck, Tanja Isenberg, Petra Univ Stuttgart Stuttgart Germany Univ Paris Saclay INRIA CNRS Paris France

ISBN: (纸本)9789897584886

We replicated a smartwatch perception experiment on the topic of glanceable visualizations. The initial study used a setup that involved showing stimuli on an actual smartwatch attached to a wooden stand and a laptop to run and log the experiment and communicate with the smartwatch. In our replication we wanted to test whether a much simpler setup that involved showing the same stimuli on a laptop screen with similar pixel size and density would lead to similar results. We also extended the initial study by testing to what extent the size of the stimulus played a role for the results. Our results indicate that the general trends observed in the original study mostly held also on the larger display, with only a few differences in certain conditions. Yet, participants were slower on the large display. We also found no evidence of a difference for the two different stimulus display sizes we tested. Our study, thus, gives evidence that simulating smartwatch displays on laptop screens with similar resolution and pixel size might be a viable alternative for smartwatch perception studies with visualizations.

关键词： Glanceable visualization Quantitative Evaluation Desktop Smartwatch Display Size Perception

来源：评论

学校读者我要写书评

暂无评论

Development of Educational Software SSP for Speech Signal Processing

Development of Educational Software SSP for Speech Signal Pr...

引用

information Science and Education (ICISE-IE), International conference on

作者： Jinyan Hu Yumei Gong Haihua Yu Shaojing Song School of Computer and Information Engineering Shanghai Polytechnic University Shanghai China

ISBN: (数字)9798331506766

ISBN: (纸本)9798331506773

The speech signal processing course emphasizes both theory and practice in the field of electronic information. Its extensive content and rich applications have brought great challenges to teaching. Therefore, the design of an educational software for speech signal processing is of great significance to help students understand the basic principles and applications of speech signal processing. Based on the MATLAB platform, this paper designs a software named SSP for speech signal processing, which can realize the functions of speech signal sampling, time domain analysis, frequency domain analysis, feature extraction, speech enhancement and quantization coding. It enables students to better master the knowledge of speech signal processing through an intuitive, friendly and interactive visual human-computer interface. After using this educational software, students' learning enthusiasm is improved, and their cognition and understanding of speech signal processing are also significantly enhanced.

关键词： Technological innovation visualization Software design Speech coding Education Signal processing Speech enhancement Software MATLAB Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Contrastive Distillation for Instructional Activity Anticipation 26

Cross-modal Contrastive Distillation for Instructional Activ...

引用

26th International conference on Pattern Recognition / 8th International Workshop on Image Mining - theory and applications (IMTA)

作者： Yang, Zhengyuan Liu, Jingen Huang, Jing He, Xiaodong Mei, Tao Xu, Chenliang Luo, Jiebo Univ Rochester Dept Comp Sci Rochester NY 14627 USA JD AI Res Beijing Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

In this study, we aim to predict the plausible future action steps given an observation of the past and study the task of instructional activity anticipation. Unlike previous anticipation tasks that aim at action label prediction, our work targets at generating natural language outputs that provide interpretable and accurate descriptions of future action steps. It is a challenging task due to the lack of semantic information extracted from the instructional videos. To overcome this challenge, we propose a novel knowledge distillation framework to exploit the related external textual knowledge to assist the visual anticipation task. However, previous knowledge distillation techniques generally transfer information within the same modality. To bridge the gap between the visual and text modalities during the distillation process, we devise a novel cross-modal contrastive distillation (CCD) scheme, which facilitates knowledge distillation between teacher and student in heterogeneous modalities with the proposed crossmodal distillation loss. We evaluate our method on the Tasty Videos dataset. CCD improves the anticipation performance of the visual-alone student model by a large margin of 40.2% relatively in BLEU4. Our approach also outperforms the stateof-the-art approaches by a large margin.

关键词： Charge coupled devices visualization Semantics Natural languages Benchmark testing Data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Backward recursive Class Activation Map refinement for high resolution saliency map 26

Backward recursive Class Activation Map refinement for high ...

引用

26th International conference on Pattern Recognition / 8th International Workshop on Image Mining - theory and applications (IMTA)

作者： Englebert, Alexandre Cornu, Olivier de Vleeschouwer, Christophe UCLouvain Informat & Commun Technol Elect & Appl Math ICTEA Louvain La Neuve Belgium UCLouvain Clin Univ St Luc UCL Neuro Musculo Skeletal Lab NMSK Serv Chirurg Orthop ed & Traumatol Brussels Belgium

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

The need for Explainable AI is increasing with the development of deep learning. The saliency maps derived from convolutional neural networks generally fail in localizing with accuracy the image features justifying the network prediction. This is because those maps are either low-resolution as for CAM, or smooth as for perturbation-based methods, or do correspond to a large number of widespread peaky spots as for gradient-based approaches. In contrast, our work proposes to combine the information from earlier network layers with the one from later layers to produce a high resolution Class Activation Map that is competitive with the previous art in term of insertion-deletion faithfulness metrics, while outperforming it in term of precision of class-specific features localization.

关键词： Measurement Location awareness Deep learning Backpropagation visualization Image resolution Art

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108页 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：