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

50,499 篇 会议
1,420 册 图书
1,018 篇 期刊文献
1 篇 学位论文

馆藏范围

52,935 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,784 篇 工学
- 24,773 篇 计算机科学与技术...
- 12,555 篇 软件工程
- 5,155 篇 光学工程
- 4,739 篇 电气工程
- 4,428 篇 信息与通信工程
- 4,255 篇 机械工程
- 3,950 篇 控制科学与工程
- 2,475 篇 生物工程
- 1,729 篇 生物医学工程（可授...
- 1,579 篇 仪器科学与技术
- 1,305 篇 电子科学与技术（可...
- 793 篇 化学工程与技术
- 697 篇 安全科学与工程
- 541 篇 交通运输工程
- 379 篇 建筑学
- 331 篇 土木工程
11,835 篇 理学
- 6,437 篇 物理学
- 5,401 篇 数学
- 2,762 篇 生物学
- 1,910 篇 统计学（可授理学、...
- 797 篇 化学
- 668 篇 系统科学
5,301 篇 医学
- 5,094 篇 临床医学
- 727 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,346 篇 管理学
- 1,951 篇 图书情报与档案管...
- 1,534 篇 管理科学与工程(可...
- 480 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
428 篇 法学
- 401 篇 社会学
298 篇 农学
197 篇 教育学
163 篇 经济学
63 篇 文学
49 篇 军事学

主题

17,316 篇 computer vision
8,990 篇 pattern recognit...
4,198 篇 training
3,815 篇 feature extracti...
3,129 篇 cameras
2,870 篇 computational mo...
2,774 篇 image segmentati...
2,620 篇 visualization
2,551 篇 shape
2,538 篇 face recognition
2,166 篇 robustness
2,118 篇 computer science
1,969 篇 object detection
1,960 篇 computer archite...
1,859 篇 layout
1,841 篇 object recogniti...
1,802 篇 three-dimensiona...
1,726 篇 neural networks
1,704 篇 humans
1,686 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
135 篇 national laborat...
107 篇 univ sci & techn...
104 篇 zhejiang univers...
100 篇 shanghai jiao to...
94 篇 university of sc...
94 篇 microsoft resear...
85 篇 zhejiang univ pe...
84 篇 shanghai ai lab ...
74 篇 school of comput...
69 篇 computer vision ...
68 篇 peking univ peop...
68 篇 chinese acad sci...
65 篇 chinese univ hon...
63 篇 institute of inf...
62 篇 google res mount...
61 篇 univ oxford oxfo...
59 篇 univ toronto on
57 篇 swiss fed inst t...

作者

91 篇 van gool luc
87 篇 umapada pal
76 篇 zhang lei
64 篇 lee seong-whan
50 篇 vittorio murino
42 篇 yang yi
34 篇 nassir navab
33 篇 li xin
33 篇 jie yang
32 篇 liu yang
31 篇 escalera sergio
31 篇 loy chen change
30 篇 ling haibin
30 篇 h. bischof
29 篇 zhou jie
29 篇 vasconcelos nuno
29 篇 jan-michael frah...
28 篇 blumenstein mich...
28 篇 hanqing lu
27 篇 jia yunde

语言

50,671 篇 英文
2,031 篇 其他
246 篇 中文
22 篇 土耳其文
4 篇 西班牙文
2 篇 日文
2 篇 葡萄牙文
2 篇 俄文

检索条件"任意字段=IEEE Conference on Computer Vision and Pattern Recognition"

共 52938 条记录，以下是4251-4260 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：

Eloquence in Silence: A Boon for Speech and Hearing Impaired Community

Eloquence in Silence: A Boon for Speech and Hearing Impaired...

引用

2024 International conference on computer, Electronics, Electrical Engineering and their Applications, IC2E3 2024

作者： Singh, Gourav Rawatrawat, Ranvir SinghPrateek Singh Agarwal, Vansh Manwal, Manika Purohit, Kamlesh Chandra Graphic Era Hill University Computer Science and Engg Department Dehradun India

ISBN: (纸本)9798350388534

Deaf and dumb individuals mostly utilize Eloquence in Silence to communicate with each other and within their own communities. Because they are mute, people in this language communicate with hand gestures. Eloquence in Silence recognition is the process of identifying hand motions and carries on until equivalent hand signals are translated into text or speech. Eloquence in Silence hand motions can be categorized as either static or dynamic in this context. Though recognition of static hand gestures is easier than that of dynamic hand gestures, both types of recognition are crucial to the community of humans. By developing Deep Neural Network designs, specifically Convolutional Neural Network designs, the model can be trained to recognize hand motions. Deep Learning computer vision is then employed to detect and interpret hand gestures using these trained models. © 2024 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-View Graph Attention Complementary based Brain Networks Analysis for Brain Diseases Diagnosis 2

Multi-View Graph Attention Complementary based Brain Network...

引用

2nd International conference on pattern recognition, Machine vision and Intelligent Algorithms, PRMVIA 2024

作者： Li, Chaojun Li, Shengrong Zhu, Qi Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China

ISBN: (纸本)9798350389746

The integration of functional and structural imaging data significantly enhances the analysis of brain networks, which is essential for diagnosing brain disorders. Existing methods primarily focus on merging feature spaces across modalities. However, vector-based approaches do not preserve the topology of the brain network, while traditional graph-based methods limit information aggregation, thereby impeding the effective extraction of complementary information and topological features. In our research, we introduce an innovative approach by combining functional magnetic resonance Imaging (fMRI) and diffusion tensor imaging (DTI) techniques to diagnose epilepsy. Our framework intelligently combines diverse brain network aggregation methods to capture complementary topological features. Initially, we construct multimodal brain networks and employ multi-channel graph neural networks to extract topological features. Secondly, we integrate an attention-based system to merge feature embeddings from different brain networks dynamically and craft a loss function to highlight the prominent features among different aggregation approaches. Finally, we classify the integrated features using a multi-layer perceptron (MLP). Experimental evaluation of an epilepsy dataset from Jinling Hospital demonstrates a significant improvement in diagnosis performance compared to several advanced diagnostic methods. © 2024 ieee.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Workpiece Positioning Based on Stereo Matching 7

Research on Workpiece Positioning Based on Stereo Matching

引用

7th International conference on Electrical, Mechanical and computer Engineering, ICEMCE 2023

作者： Yue, Jie Zhang, Ning Yin, Xinyan College of Mechanical Engineering Xijing University Xi'an China

ISBN: (纸本)9798350382877

With the proposal of Made in China 2025, the integration of industrial robots and machine vision technology on automated manufacturing production lines will further improve the degree of industrial automation. Conventional monocular vision guidance robot can only deal with two-dimensional problems, but can not solve the three-dimensional problem of workpiece positioning under complex conditions. Therefore, a workpiece recognition system based on binocular vision is proposed. Binocular stereo vision system is a kind of technology that imitates the principle of human binocular vision. The images obtained by two cameras are matched in stereo, so as to realize the perception and recognition of three-dimensional scenes. Stereo matching refers to finding the corresponding points between two images obtained by binocular vision system, so as to calculate the position and shape of the object in three-dimensional space. Its accuracy and efficiency directly affect the performance of the system. This paper aims to study the stereo matching problem in binocular stereo vision system, and improve the accuracy and robustness of stereo matching by analyzing and improving the stereo matching algorithm. © 2023 ieee.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Contrastive Learning for pattern-Generalizable Image Corruption Detection

Hierarchical Contrastive Learning for Pattern-Generalizable ...

引用

ieee/CVF International conference on computer vision (ICCV)

作者： Feng, Xin Xu, Yifeng Lu, Guangming Pei, Wenjie Harbin Inst Technol Shenzhen Peoples R China

ISBN: (纸本)9798350307184

Effective image restoration with large-size corruptions, such as blind image inpainting, entails precise detection of corruption region masks which remains extremely challenging due to diverse shapes and patterns of corruptions. In this work, we present a novel method for automatic corruption detection, which allows for blind corruption restoration without known corruption masks. Specifically, we develop a hierarchical contrastive learning framework to detect corrupted regions by capturing the intrinsic semantic distinctions between corrupted and uncorrupted regions. In particular, our model detects the corrupted mask in a coarse-to-fine manner by first predicting a coarse mask by contrastive learning in low-resolution feature space and then refines the uncertain area of the mask by high-resolution contrastive learning. A specialized hierarchical interaction mechanism is designed to facilitate the knowledge propagation of contrastive learning in different scales, boosting the modeling performance substantially. The detected multi-scale corruption masks are then leveraged to guide the corruption restoration. Detecting corrupted regions by learning the contrastive distinctions rather than the semantic patterns of corruptions, our model has well generalization ability across different corruption patterns. Extensive experiments demonstrate following merits of our model: 1) the superior performance over other methods on both corruption detection and various image restoration tasks including blind inpainting and watermark removal, and 2) strong generalization across different corruption patterns such as graffiti, random noise or other image content. Codes and trained weights are available at https://***/xyfJASON/HCL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

recognition and Analysis of Glass Subsurface Defects by Integrating Machine vision and Image Processing Technology 5

Recognition and Analysis of Glass Subsurface Defects by Inte...

引用

5th International conference on computers, Information Processing and Advanced Education, CIPAE 2024

作者： Lin, Chen Ling, Xiong Luo, Guangming Wuhan University of Science and Technology Wuhan China Changli Glass Honghu Co. Ltd Wuhan China

ISBN: (纸本)9798331527662

Machine vision and computer image processing technologies are widely used in the metallurgical industry, especially in recognizing and analyzing defects in glass. High surfaces of planer surface and quality in the glass and metal manufacturing sector primarily require automated and performance visual detection, and inspection systems and algorithms are constantly improving. This article, therefore, seeks to comprehensively recognize and analyze glass subsurface defects through the integration of image processing technologies and machine vision. According to the algorithm's properties and the image features typified in the process, the defects of identified glass components are primarily classified based on determining the cause and the optical features of characteristics exhibited. Given the nature of varied and detected effects determined mainly by the classifiers, an improved accuracy level was notable, and a reduction of the computational complexity was evident following the use of machine vision and image processing technologies. © 2024 ieee.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN

Focus on Content not Noise: Improving Image Generation for N...

引用

ieee/CVF International conference on computer vision (ICCV)

作者： Utz, Jonas Weise, Tobias Schlereth, Maja Wagner, Fabian Thies, Mareike Gu, Mingxuan Uderhardt, Stefan Breininger, Katharina Friedrich Alexander Univ Erlangen Nuremberg Dept Artificial Intelligence Biomed Engn Erlangen Germany FAU Erlangen Nurnberg Pattern Recognit Lab Erlangen Germany FAU Erlangen Nurnberg Dept Med Rheumatol & Immunol 3 Erlangen Germany FAU Erlangen Nurnberg Deutsch Zentrum Immuntherapie Erlangen Germany FAU Erlangen Nurnberg Exploratory Res Unit Opt Imaging Ctr Erlangen Erlangen Germany

ISBN: (纸本)9798350307443

Annotating nuclei in microscopy images for the training of neural networks is a laborious task that requires expert knowledge and suffers from inter- and intra-rater variability, especially in fluorescence microscopy. Generative networks such as CycleGAN can inverse the process and generate synthetic microscopy images for a given mask, thereby building a synthetic dataset. However, past works report content inconsistencies between the mask and generated image, partially due to CycleGAN minimizing its loss by hiding shortcut information for the image reconstruction in high frequencies rather than encoding the desired image content and learning the target task. In this work, we propose to remove the hidden shortcut information, called steganography, from generated images by employing a low pass filtering based on the discrete cosine transform (DCT). We show that this increases coherence between generated images and cycled masks and evaluate synthetic datasets on a downstream nuclei segmentation task. Here we achieve an improvement of 5.4 percentage points in the F1-score compared to a vanilla CycleGAN. Integrating advanced regularization techniques into the CycleGAN architecture may help mitigate steganography-related issues and produce more accurate synthetic datasets for nuclei segmentation.

关键词： cycle gan data generation dct fluorescence microscopy nuclei segmentation steganography synthetic data

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Instance Segmentation using Probabilistic Embeddings

Point Cloud Instance Segmentation using Probabilistic Embedd...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhang, Biao Wonka, Peter KAUST Thuwal Saudi Arabia

ISBN: (纸本)9781665445092

In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.

关键词： Image segmentation computer vision Uncertainty Three-dimensional displays Semantics Gaussian distribution Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Knowledge Distillation

Multi-Label Knowledge Distillation

引用

ieee/CVF International conference on computer vision (ICCV)

作者： Yang, Penghui Xie, Ming-Kun Zong, Chen-Chen Feng, Lei Niu, Gang Sugiyama, Masashi Huang, Sheng-Jun Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China MIIT Key Lab Pattern Anal & Machine Intelligence Nanjing Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore RIKEN Ctr Adv Intelligence Project Tokyo Japan Univ Tokyo Tokyo Japan

ISBN: (纸本)9798350307184

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning. However, these methods can hardly be extended to the multi-label learning scenario, where each instance is associated with multiple semantic labels, because the prediction probabilities do not sum to one and feature maps of the whole example may ignore minor classes in such a scenario. In this paper, we propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems;on the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings. Experimental results on multiple benchmark datasets validate that the proposed method can avoid knowledge counteraction among labels, thus achieving superior performance against diverse comparing methods. Our code is available at: https://***/penghui-yang/L2D.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language and vision Assistant Model for Multi Camera Appearance Features 24

Leveraging Large Language and Vision Assistant Model for Mul...

引用

13th International conference on Computing and pattern recognition, ICCPR 2024

作者： Zeilerbauer, Oliver Mohebbi, Mohammad Reza Doeller, Mario Christian-Doppler-Gesellschaft Tyrol Kufstein Austria Fachhochschule Kufstein Tirol Bildungs GmbH University of applied sciences Tyrol Kufstein Austria Department of Computer Science University of Passau Passau Bavaria Germany

ISBN: (纸本)9798400717482

The existing vision-based tracking solutions, such as DeepSORT and SMILEtrack, base their feature sets on visual features extracted from a single camera using Convolutional Neural Networks (CNNs) or through similarity learning modules. Even if it works well in a general practical setting under normal environmental configurations, it poses serious challenges when it comes to a multi-camera setting, where illumination, angle of view, and occlusions may vary significantly. To address these limitations, we present a novel framework that uses the Large Language and vision Assistant (LLaVA), a multimodal model that processes visual and textual inputs. This is because Large Language and vision Assistant (LLaVA) can better undertake uniform feature extraction across heterogeneous camera views, considering language context during the perception of visual data. The proposed framework utilises consistent visual feature descriptions generated from image snippets and incorporates mechanisms to handle hallucinations;hence, object re-identification across cameras is more reliable. When such visual descriptions are layered with spatial location data, tracking and identification of multiple objects in crowded and complex situations become more accurate. For that, the system allows much better flexibility and robustness of the tracking systems, resulting in better performance over traditional methods in real multi-camera applications. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Immediate Applicability of Pose Estimation for Sign Language recognition

Evaluating the Immediate Applicability of Pose Estimation fo...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Moryossef, Amit Tsochantaridis, Ioannis Dinn, Joe Camgoez, Necati Cihan Bowden, Richard Jiang, Tao Rios, Annette Muller, Mathias Ebling, Sarah Bar Ilan Univ Ramat Gan Israel Google Mountain View CA 94043 USA Univ Surrey Guildford Surrey England Univ Zurich Zurich Switzerland

ISBN: (纸本)9781665448994

Sign languages are visual languages produced by the movement of the hands, face, and body. In this paper, we evaluate representations based on skeleton poses, as these are explainable, person-independent, privacy-preserving, low-dimensional representations. Basically, skeletal representations generalize over an individual's appearance and background, allowing us to focus on the recognition of motion. But how much information is lost by the skeletal representation? We perform two independent studies using two state-of-the-art pose estimation systems. We analyze the applicability of the pose estimation systems to sign language recognition by evaluating the failure cases of the recognition models. Importantly, this allows us to characterize the current limitations of skeletal pose estimation approaches in sign language recognition.

关键词： Analytical models Visualization computer vision Assistive technology Face recognition conferences Pose estimation

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 << < 422 423 424 425 426 427 428 429 430 431 > >>

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：