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

52,951 篇 会议
1,122 篇 期刊文献
10 册 图书

馆藏范围

54,083 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

26,305 篇 工学
- 17,134 篇 计算机科学与技术...
- 9,446 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

34,666 篇 visualization
7,344 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

53,561 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 54083 条记录，以下是4631-4640 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：

Explainability Tools Enabling Deep Learning in Future In-Situ Real-Time Planetary Explorations

Explainability Tools Enabling Deep Learning in Future In-Sit...

引用

ieee Aerospace conference (AERO)

作者： Lundstrom, Daniel Huyen, Alexander Mevada, Arya Yun, Kyongsik Lu, Thomas Univ Southern Calif 3620 S Vermont AveKAP 104 Los Angeles CA 90089 USA CALTECH Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA CALTECH 1200 E Calif Blvd MSC 643 Pasadena CA 91125 USA

ISBN: (数字)9781665437608

ISBN: (纸本)9781665437608

Deep learning (DL) has proven to be an effective machine learning and computer vision technique. DL-based image segmentation, object recognition and classification will aid many in-situ Mars rover tasks such as path planning and artifact recognition/extraction. However, most of the Deep Neural Network (DNN) architectures are so complex that they are considered a 'black box'. In this paper, we used integrated gradients to describe the attributions of each neuron to the output classes. It provides a set of explainability tools (ET) that opens the black box of a DNN so that the individual contribution of neurons to category classification can be ranked and visualized. The neurons in each dense layer are mapped and ranked by measuring expected contribution of a neuron to a class vote given a true image label. The importance of neurons is prioritized according to their correct or incorrect contribution to the output classes and suppression or bolstering of incorrect classes, weighted by the size of each class. ET provides an interface to prune the network to enhance high-rank neurons and remove low-performing neurons. ET technology will make DNNs smaller and more efficient for implementation in small embedded systems. It also leads to more explainable and testable DNNs that can make systems easier for Validation & Verification. The goal of ET technology is to enable the adoption of DL in future in-situ planetary exploration missions.

关键词： Deep learning Space vehicles Mars visualization Neurons Neural networks Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Autonomous Mobile Robot as a Cyber-Physical System Featuring Networked Deep Learning and Control

Autonomous Mobile Robot as a Cyber-Physical System Featuring...

引用

ieee/ASME International conference on Advanced Intelligent Mechatronics (AIM)

作者： Lin, Hong-Zhi Chen, Hsin-Hung Choophutthakan, Kerk Li, Chih-Hung G. Natl Taipei Univ Technol Grad Inst Mech Engn Taipei 10608 Taiwan Natl Taipei Univ Technol Grad Inst Mfg Technol Taipei 10608 Taiwan

ISBN: (数字)9781665413084

ISBN: (纸本)9781665413084

In this article, we proposed an autonomous mobile robot (AMR) capable of conducting multiple deep learning inferences by a computing network as a Cyber-Physical System (CPS). In view of industry 4.0, a five-layered CPS architecture including Component, Intelligence, Cyber, Configuration, and Deployment was devised. Mechatronic control of the two-wheeled self-balancing AMR presents the first challenge to embedded computing, whereas multiple deep learning modules for visual navigation and localization further escalate the stake. To meet the challenge of real-time and affordable computing, we constructed an embedded cluster based on Raspberry Pi4s and Intel NCS2 for simultaneous intelligent inference and data exchange. We tested the performances of three networking methods, Network File System (NFS), Socket Server with Multiple Clients (SSMC), and ROS TOPIC (ROS-T), and reported the comparison. We also conducted a series of field tests on autonomous corridor navigation, localization, object delivery, and object pick-and-place to verify the performance of the self-balancing AMR. The results showed high success rates with sufficient spatial precision, stability, and robust loop closure. The web-based console realizes the functions of the digital twin and provides connectivity to higher-level management systems.

关键词： Deep learning Location awareness visualization Mechatronics Navigation Computer architecture Supervisory control

来源：评论

学校读者我要写书评

暂无评论

MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing

MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing

引用

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

作者： Qiu, Zhaofan Yao, Ting Ngo, Chong-Wah Mei, Tao JD Explore Acad Beijing Peoples R China Singapore Management Univ Singapore Singapore

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Convolutional Neural Networks (CNNs) have been regarded as the go-to models for visual recognition. More recently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more popular. Nevertheless, it is not trivial when utilizing these newly-minted networks for video recognition due to the large variations and complexities in video data. In this paper, we present MLP-3D networks, a novel MLP-like 3D architecture for video recognition. Specifically, the architecture consists of MLP-3D blocks, where each block contains one MLP applied across tokens (i.e., token-mixing MLP) and one MLP applied independently to each token (i.e., channel MLP). By deriving the novel grouped time mixing (GTM) operations, we equip the basic token-mixing MLP with the ability of temporal modeling. GTM divides the input tokens into several temporal groups and linearly maps the tokens in each group with the shared projection matrix. Furthermore, we devise several variants of GTM with different grouping strategies, and compose each variant in different blocks of MLP-3D network by greedy architecture search. Without the dependence on convolutions or attention mechanisms, our MLP-3D networks achieves 68.5%/81.4% top-1 accuracy on Something-Something V2 and Kinetics-400 datasets, respectively. Despite with fewer computations, the results are comparable to state-of-the-art widely-used 3D CNNs and video transformers.

关键词： visualization Computer vision Three-dimensional displays Computer architecture Transformers Pattern recognition Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Compression of Ultra High Definition Image based on K-means Clustering Algorithm

Compression of Ultra High Definition Image based on K-means ...

引用

information Technology,Big Data and Artificial Intelligence (ICIBA), International conference on ieee International conference on

作者： Pengbo Wang Shanghai Zhongqiao Vocational and Technical University Shanghai China

ISBN: (数字)9798350363609

ISBN: (纸本)9798350363616

Image compression plays a key role in contemporary digital environments given the escalating influx of visual data on the Internet. In this study, the K-means clustering algorithm is adopted for Ultra High Definition (UHD) image compression. The procedures are introduced in detail, and a numerical example is provided to demonstrate the applicability of the proposed approach. The results indicate that with an appropriately assigned K value, that is, the number of clusters, the K-means can strike a good balance between the visual quality loss and file size reduction, achieving a compression ratio of 60.37. This study not only proposes an approach for UHD image compression, but also exhibits the promising potential of clustering algorithms in the field of image processing.

关键词： visualization Image coding Image resolution Clustering algorithms Big Data Internet information technology Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Wide Baseline Visual Servoing via 3D Equivariance

Self-supervised Wide Baseline Visual Servoing via 3D Equivar...

引用

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

作者： Huh, Jinwook Hong, Jungseok Garg, Suveer Park, Hyun Soo Isler, Volkan Samsung AI Ctr NY 837 Washington St New York NY 10014 USA

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

One of the challenging input settings for visual servoing is when the initial and goal camera views are far apart. Such settings are difficult because the wide baseline can cause drastic changes in object appearance and cause occlusions. This paper presents a novel self-supervised visual servoing method for wide baseline images which does not require 3D ground truth supervision. Existing approaches that regress absolute camera pose with respect to an object require 3D ground truth data of the object in the forms of 3D bounding boxes or meshes. We learn a coherent visual representation by leveraging a geometric property called 3D equivariance-the representation is transformed in a predictable way as a function of 3D transformation. To ensure that the feature-space is faithful to the underlying geodesic space, a geodesic preserving constraint is applied in conjunction with the equivariance. We design a Siamese network that can effectively enforce these two geometric properties without requiring 3D supervision. With the learned model, the relative transformation can be inferred simply by following the gradient in the learned space and used as feedback for closed-loop visual servoing. Our method is evaluated on objects from the YCB dataset, showing meaningful outperformance on a visual servoing task, or object alignment task with respect to state-of-the-art approaches that use 3D supervision. Ours yields more than 35% average distance error reduction and more than 90% success rate with 3cm error tolerance.

关键词： visualization Image segmentation Three-dimensional displays Self-supervised learning Cameras Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration

TransDARC: Transformer-based Driver Activity Recognition wit...

引用

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

作者： Peng, Kunyu Roitberg, Alina Yang, Kailun Zhang, Jiaming Stiefelhagen, Rainer Karlsruhe Inst Technol Inst Anthropomat & Robot Karlsruhe Germany

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

Traditional video-based human activity recognition has experienced remarkable progress linked to the rise of deep learning, but this effect was slower as it comes to the downstream task of driver behavior understanding. Understanding the situation inside the vehicle cabin is essential for Advanced Driving Assistant System (ADAS) as it enables identifying distraction, predicting driver's intent and leads to more convenient human-vehicle interaction. At the same time, driver observation systems face substantial obstacles as they need to capture different granularities of driver states, while the complexity of such secondary activities grows with the rising automation and increased driver freedom. Furthermore, a model is rarely deployed under conditions identical to the ones in the training set, as sensor placements and types vary from vehicle to vehicle, constituting a substantial obstacle for real-life deployment of data-driven models. In this work, we present a novel vision-based framework for recognizing secondary driver behaviours based on visual transformers and an additional augmented feature distribution calibration module. This module operates in the latent feature-space enriching and diversifying the training set at feature-level in order to improve generalization to novel data appearances, (e.g., sensor changes) and general feature quality. Our framework consistently leads to better recognition rates, surpassing previous state-of-the-art results of the public Drive&Act benchmark on all granularity levels. Our code will be made publicly available at https://***/KPeng9510/TransDARC.

关键词： Training visualization Sensor placement Benchmark testing Transformers Robot sensing systems Calibration

来源：评论

学校读者我要写书评

暂无评论

Research and Application of LDA-Based Topic Modelling and Co-Occurrence Semantic Web Analysis

Research and Application of LDA-Based Topic Modelling and Co...

引用

Sensors, Electronics and Computer Engineering (ICSECE), ieee International conference on

作者： Ruotong Wang Communication University of China Beijing China

ISBN: (数字)9798350373646

ISBN: (纸本)9798350373653

This article focuses on two important text analysis methods, LDA topic modelling and co-occurrence semantic network analysis. Firstly, the article introduces how the LDA topic model, as an unsupervised learning tool, automatically extracts the topic structure from a large amount of unlabelled text by simulating the document-topic and topic-vocabulary generating process, providing effective support for tasks such as text categorization, information retrieval, and knowledge graph construction. Secondly, the co-occurrence semantic network analysis method is analysed in detail, which constructs a network model based on lexical co-occurrence relations, and measures the strength of association between nodes by using statistical indexes in order to reveal the semantic links between words, and then applies to the fields of lexical-semantic relation visualization, word sense disambiguation, and knowledge graph construction. Finally, the latest research progress, application scenarios and future development possibilities of the two are discussed in depth to provide comprehensive theoretical guidance and practical insights for academic research and practical applications.

关键词： Employee welfare Semantic Web Analytical models visualization Semantics Text categorization Psychology Network analyzers Knowledge graphs Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Training Object Detectors from Scratch: An Empirical Study in the Era of Vision Transformer

Training Object Detectors from Scratch: An Empirical Study i...

引用

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

作者： Hong, Weixiang Lao, Jiangwei Ren, Wang Wang, Jian Chen, Jingdong Chu, Wei Ant Grp Hangzhou Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Modeling in computer vision has long been dominated by convolutional neural networks (CNNs). Recently, in light of the excellent performances of self-attention mechanism in the language field, transformers tailored for visual data have drawn numerous attention and triumphed CNNs in various vision tasks. These vision transformers heavily rely on large-scale pre-training to achieve competitive accuracy, which not only hinders the freedom of architectural design in downstream tasks like object detection, but also causes learning bias and domain mismatch in the fine-tuning stages. To this end, we aim to get rid of the "pre-train & fine-tune" paradigm of vision transformer and train transformer based object detector from scratch. Some earlier work in the CNNs era have successfully trained CNNs based detectors without pre-training, unfortunately, their findings do not generalize well when the backbone is switched from CNNs to vision transformer. Instead of proposing a specific vision transformer based detector, in this work, our goal is to reveal the insights of training vision transformer based detectors from scratch. In particular, we expect those insights can help other researchers and practitioners, and inspire more interesting research in other fields, such as semantic segmentation, visual-linguistic pre-training, etc. One of the key findings is that both architectural changes and more epochs play critical roles in training vision transformer based detectors from scratch. Experiments on MS COCO datasets demonstrate that vision transformer based detectors trained from scratch can also achieve similar performances to their counterparts with ImageNet pre-training.

关键词： Training Computer vision visualization Semantics Detectors Object detection Transformers

来源：评论

学校读者我要写书评

暂无评论

MoESR: Blind Super-Resolution using Kernel-Aware Mixture of Experts 22

MoESR: Blind Super-Resolution using Kernel-Aware Mixture of ...

引用

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

作者： Emad, Mohammad Peemen, Maurice Corporaal, Henk Eindhoven Univ Technol Eindhoven Netherlands Thermo Fisher Sci Bleiswijk Netherlands

ISBN: (纸本)9781665409155

Modern deep learning super-resolution approaches have achieved remarkable performance where the low-resolution (LR) input is a degraded high-resolution (HR) image by a fixed known kernel i.e. kernel-specific super-resolution (SR). However, real images often vary in their degradation kernels, thus a single kernel-specific SR approach does not often produce accurate HR results. Recently, degradationaware networks are introduced to generate blind SR results for unknown kernel conditions. They can restore images for multiple blur kernels. However, they have to compromise in quality compared to their kernel-specific counterparts. To address this issue, we propose a novel blind SR method called Mixture of Experts Super-Resolution (MoESR), which uses different experts for different degradation kernels. A broad space of degradation kernels is covered by kernel-specific SR networks (experts). We present an accurate kernel prediction method (gating mechanism) by evaluating the sharpness of images generated by experts. Based on the predicted kernel, our most suited expert network is selected for the input image. Finally, we fine-tune the selected network on the test image itself to leverage the advantage of internal learning. Our experimental results on standard synthetic datasets and real images demonstrate that MoESR outperforms state-of-the-art methods both quantitatively and qualitatively. Especially for the challenging x4 SR task, our PSNR improvement of 0.93 dB on the DIV2KRK dataset is substantial(1).

关键词： Degradation Training visualization Surveillance Microscopy Superresolution Prediction methods

来源：评论

学校读者我要写书评

暂无评论

Robust Region Feature Synthesizer for Zero-Shot Object Detection

Robust Region Feature Synthesizer for Zero-Shot Object Detec...

引用

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

作者： Huang, Peiliang Han, Junwei Cheng, De Zhang, Dingwen Northwestern Polytech Univ Sch Automat Brain & Artificial Intelligence Lab Xian Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Sch Telecommun Engn Xian Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image. In this study, we reveal the core challenges in this research area: how to synthesize robust region features (for unseen objects) that are as intra-class diverse and inter-class separable as the real samples, so that strong unseen object detectors can be trained upon them. To address these challenges, we build a novel zero-shot object detection framework that contains an Intra-class Semantic Diverging component and an Inter-class Structure Preserving component. The former is used to realize the one-to-more mapping to obtain diverse visual features from each class semantic vector, preventing miss-classifying the real unseen objects as image backgrounds. While the latter is used to avoid the synthesized features too scattered to mix up the inter-class and foreground-background relationship. To demonstrate the effectiveness of the proposed approach, comprehensive experiments on PASCAL VOC, COCO, and DIOR datasets are conducted. Notably, our approach achieves the new state-of-the-art performance on PASCAL VOC and COCO and it is the first study to carry out zero-shot object detection in remote sensing imagery.

关键词： visualization Computer vision Synthesizers Semantics Object detection Detectors Feature extraction

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 << < 460 461 462 463 464 465 466 467 468 469 > >>

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：