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
1,418 册 图书
1,019 篇 期刊文献
1 篇 学位论文

馆藏范围

52,934 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,785 篇 工学
- 24,773 篇 计算机科学与技术...
- 12,556 篇 软件工程
- 5,155 篇 光学工程
- 4,742 篇 电气工程
- 4,428 篇 信息与通信工程
- 4,255 篇 机械工程
- 3,948 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...
3,345 篇 管理学
- 1,951 篇 图书情报与档案管...
- 1,533 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...
4,200 篇 training
3,816 篇 feature extracti...
3,128 篇 cameras
2,868 篇 computational mo...
2,780 篇 image segmentati...
2,615 篇 visualization
2,543 篇 shape
2,536 篇 face recognition
2,179 篇 robustness
2,115 篇 computer science
1,969 篇 object detection
1,966 篇 computer archite...
1,855 篇 layout
1,835 篇 object recogniti...
1,788 篇 three-dimensiona...
1,730 篇 neural networks
1,710 篇 humans
1,685 篇 image recognitio...

机构

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

作者

91 篇 van gool luc
87 篇 umapada pal
76 篇 zhang lei
64 篇 lee seong-whan
49 篇 vittorio murino
41 篇 yang yi
34 篇 nassir navab
33 篇 li xin
33 篇 jie yang
32 篇 loy chen change
32 篇 liu yang
31 篇 escalera sergio
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

50,670 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 52937 条记录，以下是4551-4560 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：

TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text

TextOCR: Towards large-scale end-to-end reasoning for arbitr...

引用

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

作者： Singh, Amanpreet Peng, Guan Toh, Mandy Huang, Jing Galuba, Wojciech Hassner, Tal Facebook AI Res Menlo Pk CA 94025 USA

ISBN: (纸本)9781665445092

A crucial component for the scene text based reasoning required for TextVQA and TextCaps datasets involve detecting and recognizing text present in the images using an optical character recognition (OCR) system. The current systems are crippled by the unavailability of ground truth text annotations for these datasets as well as lack of scene text detection and recognition datasets on real images disallowing the progress in the field of OCR and evaluation of scene text based reasoning in isolation from OCR systems. In this work, we propose TextOCR, an arbitrary-shaped scene text detection and recognition with 900k annotated words collected on real images from TextVQA dataset. We show that current state-of-the-art text-recognition (OCR) models fail to perform well on TextOCR and that training on TextOCR helps achieve state-of-the-art performance on multiple other OCR datasets as well. We use a TextOCR trained OCR model to create PixelM4C model which can do scene text based reasoning on an image in an end-to-end fashion, allowing us to revisit several design choices to achieve new state-of-the-art performance on TextVQA dataset.

关键词： Training computer vision Image recognition Text recognition Optical feedback Optical imaging Cognition

来源：评论

学校读者我要写书评

暂无评论

Translation of Air-Written Baybayin Using Optical Flow in Complex Background

Translation of Air-Written Baybayin Using Optical Flow in Co...

引用

2024 ieee Region 10 conference, TENCON 2024

作者： Ariel V. Villespin, Justine Angelo Magana, Michael Joseph U. Manlises, Cyrel O. School of Electrical Electronics and Computer Engineering Mapua University Manila1002 Philippines

ISBN: (纸本)9798350350821

Motion tracking plays a vital role in computer vision, yet its use in real-time script translation, particularly in complex environments, remains underexplored. This study compares the effectiveness of two optical flow methods - Lucas-Kanade and Farneback - for real-time translation of air-written Baybayin characters in challenging backgrounds. The system utilizes Color Thresholding for background subtraction, optical flow for motion tracking, and a combination of Tesseract OCR with a Gated Recurrent Unit (GRU) model for character translation. Results show that the Lucas-Kanade method achieved a significantly higher accuracy of 82%, outperforming Farneback's 44%, which struggled with delayed tracking and incomplete character formation due to its higher computational demands. Lucas-Kanade's smoother and more reliable motion tracking allowed for more accurate character recognition, even in environments with complex backgrounds and variable lighting conditions. These findings demonstrate that Lucas-Kanade is the more effective optical flow method for real-time Baybayin translation, making it a promising approach for future applications in script recognition and translation tasks in dynamic environments. © 2024 ieee.

关键词： Motion tracking

来源：评论

学校读者我要写书评

暂无评论

Explore Image Deblurring via Encoded Blur Kernel Space

Explore Image Deblurring via Encoded Blur Kernel Space

引用

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

作者： Phong Tran Anh Tuan Tran Quynh Phung Minh Hoai VinAI Res Hanoi Vietnam VinUniversity Hanoi Vietnam SUNY Stony Brook Stony Brook NY 11790 USA

ISBN: (纸本)9781665445092

This paper introduces a method to encode the blur operators of an arbitrary dataset of sharp-blur image pairs into a blur kernel space. Assuming the encoded kernel space is close enough to in-the-wild blur operators, we propose an alternating optimization algorithm for blind image deblurring. It approximates an unseen blur operator by a kernel in the encoded space and searches for the corresponding sharp image. Unlike recent deep-learning-based methods, our system can handle unseen blur kernel, while avoiding using complicated handcrafted priors on the blur operator often found in classical methods. Due to the method's design, the encoded kernel space is fully differentiable, thus can be easily adopted in deep neural network models. Moreover, our method can be used for blur synthesis by transferring existing blur operators from a given dataset into a new domain. Finally, we provide experimental results to confirm the effectiveness of the proposed method. The code is available at https://***/VinAIResearch/blur-kernelspace-exploring.

关键词： Deep learning computer vision Codes Design methodology Gray-scale Image restoration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Multi-Crops Classification Using Deep Learning Method For Pesticide Spraying in Sustainable Agriculture 2

A Real-Time Multi-Crops Classification Using Deep Learning M...

引用

2nd ieee International conference on Recent Advances in Information Technology for Sustainable Development, ICRAIS 2024

作者： Nagaraja Hebbar, N. Bhat, Sandeep Mokshashree, M.N. Srinivas University S.I.T AI and DS Research Scholar Mangaluru India S.I.T CSE Mangaluru India S.I.T AI and DS Mangaluru India

ISBN: (纸本)9798350354461

The incorporation of state-of-the-art technologies, such as deep learning algorithms and computer vision, has paved the path for a revolutionary approach to precision agriculture, enabling farmers to reduce the environmental effects of pesticide application while simultaneously increasing crop yields. Researchers can create reliable computer vision systems that can precisely identify and classify various crop varieties in real time by utilizing deep learning techniques. Furthermore, the use of Convolutional Neural Networks (CNNs) in the field of plant image recognition and classification has been investigated, indicating the efficacy of deep learning-based methods in maximizing crop *** suggested system classifies various crop varieties in the field in real time by utilizing deep learning techniques. This entails using massive crop picture datasets to train CNN models so they can recognize different crops accurately under varying settings. With the ability to classify data in real-time, pesticide spraying equipment may be dynamically adjusted to ensure accurate application that is customized to meet the unique requirements of individual crop types. © 2024 ieee.

关键词： CNN computer vision Deep learning Multi-class

来源：评论

学校读者我要写书评

暂无评论

Few-shot Image Generation via Cross-domain Correspondence

Few-shot Image Generation via Cross-domain Correspondence

引用

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

作者： Ojha, Utkarsh Li, Yijun Lu, Jingwan Efros, Alexei A. Lee, Yong Jae Shechtman, Eli Zhang, Richard Adobe Res San Jose CA 95110 USA Univ Calif Davis Davis CA 95616 USA Univ Calif Berkeley Berkeley CA USA

ISBN: (纸本)9781665445092

Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity information from source to target. We propose to preserve the relative similarities and differences between instances in the source via a novel cross-domain distance consistency loss. To further reduce overfitting, we present an anchor-based strategy to encourage different levels of realism over different regions in the latent space. With extensive results in both photorealistic and non-photorealistic domains, we demonstrate qualitatively and quantitatively that our few-shot model automatically discovers correspondences between source and target domains and generates more diverse and realistic images than previous methods.

关键词： Training computer vision Image synthesis Computational modeling pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Ensembled Real-Time Hand-Gesture recognition using CNN 15

An Ensembled Real-Time Hand-Gesture Recognition using CNN

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Kavitha, M.N. Saranya, S.S. Prasad, M. Kaviyarasu, S. Ragunath, N. Rahul, P. Kongu Engineering College Department of Computer Science and Design Tamilnadu Erode India PSG Institute of Technology and Applied Research Department of Computer Science and Engineering Tamilnadu Coimbatore India Controller of Examinations Tamilnadu Namakkal India Kongu Engineering College Bachelor of Science - Information Systems Tamilnadu Erode India

ISBN: (纸本)9798350370249

Hand sign recognition is a vital technology in the human-computer interaction, enabling individuals to communicate with machines naturally and effectively. An innovative approach for real-time hand sign identification with the help of CNN and OpenCV is introduced with the fusion of computer vision and deep learning that can accurately interpret and classify an extensive range of hand signs and gestures. This research contributes significantly to the fields of computer vision and human-computer interaction, offering a practical and efficient solution for hand sign recognition. The combination of CNN and OpenCV presents a promising avenue for enhancing accessibility and communication, especially in environments where verbal communication is limited or non-existent. The model is trained with multiple data so that the system can recognize the hand gestures more precisely. Pre-trained architectures like ResNet and MobileNet are combined with the CNN model using ensemble learning and the performance is improved when compared to all the three CNN architectures individually. The ensemble model provides better accuracy of 96 %. The potential applications of this technology are vast, from assisting the hearing-impaired in understanding sign language to more immersive and intuitive interactions. Overall, the approach holds the promise of bridging the gap between human gestures and machine understanding, opening new doors for meaningful interactions between individuals and intelligent systems. © 2024 ieee.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Transfer in Residual Networks for Clinical Image Partitioning

Cross-Domain Transfer in Residual Networks for Clinical Imag...

引用

2024 ieee International conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Mingshuo Jin, Keyan Bao, Wenzhuo Chen, Zhenghan Macao Polytechnic University Faculty of Applied Sciences China Xinjiang University College of Software Shayibak District China Jilin University College of Computer Science and Technology Chaoyang District China Microsoft Danling District China

ISBN: (纸本)9798350386226

The accurate recognition and comprehensive understanding of medical images depicting human tissue represent a central focus in computer vision research. Many tasks within medical imaging rely on deep neural networks, particularly those with U-shaped architectures and skip connections. The advancement of computer vision technologies demands the application of convolutional neural networks (CNNs). Despite progress, two major challenges remain in medical image processing: (1) developing a model framework with low computational complexity that allows for efficient inference without compromising accuracy, and (2) designing a model with strong generalization capabilities across various datasets derived from patients with differing pathologies, thereby mitigating domain shift challenges. In response to the first issue, we propose a novel unsupervised domain adaptation method utilizing Interoperable Batch Normalization (IBN) to integrate multiple channels within deep neural networks, enhancing adversarial domain adaptation. Our experimental evaluation on the Hubmap and Synapse multiorgan segmentation datasets reveals that the proposed RRUNet model achieves superior performance compared to existing methods, setting a new standard in the domain. © 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

SuperMix: Supervising the Mixing Data Augmentation

SuperMix: Supervising the Mixing Data Augmentation

引用

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

作者： Dabouei, Ali Soleymani, Sobhan Taherkhani, Fariborz Nasrabadi, Nasser M. West Virginia Univ Morgantown WV 26506 USA

ISBN: (纸本)9781665445092

This paper presents a supervised mixing augmentation method termed SuperMix, which exploits the salient regions within input images to construct mixed training samples. SuperMix is designed to obtain mixed images rich in visual features and complying with realistic image priors. To enhance the efficiency of the algorithm, we develop a variant of the Newton iterative method, 65x faster than gradient descent on this problem. We validate the effectiveness of SuperMix through extensive evaluations and ablation studies on two tasks of object classification and knowledge distillation. On the classification task, SuperMix provides comparable performance to the advanced augmentation methods, such as AutoAugment and RandAugment. In particular, combining SuperMix with RandAugment achieves 78.2% top-1 accuracy on ImageNet with ResNet50. On the distillation task, solely classifying images mixed using the teacher's knowledge achieves comparable performance to the state-of-the-art distillation methods. Furthermore, on average, incorporating mixed images into the distillation objective improves the performance by 3.4% and 3.1% on CIFAR-100 and ImageNet, respectively. The code is available at https://***/alldbi/SuperMix.

关键词： Training Visualization computer vision Codes Computational modeling pattern recognition Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Detecting Feet's Bending patterns With Smart Insoles 5

Detecting Feet's Bending Patterns With Smart Insoles

引用

5th ieee International conference on pattern recognition and Machine Learning, PRML 2024

作者： Zhong, Yuchen Ying, Qijun Cai, Xiaohui dept. of Computer Science and Technology Hefei China dept. of Data Science Hefei China

ISBN: (纸本)9798350355925

Foot bending is a basic component of walking. Although bending is important for foot-ground interaction and ensures the speed and balance of the whole walking cycle, there is still no practical method for recording and analyzing foot bending under everyday scenarios. In this study we propose to use a smart insole, with two embedded Inertial Measurement Units, to acquire the movements of the fore-foot and the hind-foot and deduce the bending, represented by the bending point's position. We use the deep learning approach to estimate the bending position and its changes during different walking patterns. On the dataset containing 8 test subjects and 6 walking patterns, our method can achieve an overall mean absolute error accuracy of 2.58 cm. The smart insole can be with the subject all the day, bring in a new method for continuous foot bending monitoring. © 2024 ieee.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

PREDATOR: Registration of 3D Point Clouds with Low Overlap

PREDATOR: Registration of 3D Point Clouds with Low Overlap

引用

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

作者： Huang, Shengyu Gojcic, Zan Usvyatsov, Mikhail Wieser, Andreas Schindler, Konrad Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9781665445092

We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. Its key novelty is an overlap-attention block for early information exchange between the latent encodings of the two point clouds. In this way the subsequent decoding of the latent representations into per-point features is conditioned on the respective other point cloud, and thus can predict which points are not only salient, but also lie in the overlap region between the two point clouds. The ability to focus on points that are relevant for matching greatly improves performance: PREDATOR raises the rate of successful registrations by more than 20% in the low-overlap scenario, and also sets a new state of the art for the 3DMatch benchmark with 89% registration recall.

关键词： Convolutional codes Solid modeling computer vision Three-dimensional displays Image matching computer architecture Encoding

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 << < 452 453 454 455 456 457 458 459 460 461 > >>

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：