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4231-4240 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：

Review of Cross-Age Face recognition in Discriminative Models 8

Review of Cross-Age Face Recognition in Discriminative Model...

引用

8th International conference on Image, vision and Computing, ICIVC 2023

作者： Ermao, Liu Min, Zhi College of Computer Science and Technology Inner Mongolia Normal University Hohhot China

ISBN: (纸本)9798350335231

The purpose of cross-age face recognition is to identify people with a large age difference. It is of great significance in security, finance, fighting criminals and other fields. In order to organize the development process of Convolutional Neural Networks (CNN) in the field of cross-age face recognition, the main discriminant methods in the field in recent years are summarized. First of all, the evolution and performance of cross-age face recognition based on CNN are systematically described, and summarized. Secondly, the advantages and disadvantages of the most commonly used cross-age face recognition data sets are introduced. Finally, combined with practical application, the existing challenges and bottlenecks of discriminant models are discussed, and the future research direction of cross-age face recognition is prospected. © 2023 ieee.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Goals from Failure

Learning Goals from Failure

引用

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

作者： Epstein, Dave Vondrick, Carl Columbia Univ New York NY 10027 USA

ISBN: (纸本)9781665445092

We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct supervision. Our approach models videos as contextual trajectories that represent both low-level motion and high-level action features. Experiments and visualizations show our trained model is able to predict the underlying goals in video of unintentional action. We also propose a method to "automatically correct" unintentional action by leveraging gradient signals of our model to adjust latent trajectories. Although the model is trained with minimal supervision, it is competitive with or outperforms baselines trained on large (supervised) datasets of successfully executed goals, showing that observing unintentional action is crucial to learning about goals in video.

关键词： Visualization computer vision Psychology Predictive models Encoding Trajectory pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Long-tailed Oracle recognition Based on Attention and Multi-Expert Learning 5

Long-tailed Oracle Recognition Based on Attention and Multi-...

引用

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

作者： Yang, ZhongYuan Ibrahim, Ghalip Xu, Xuebin Yadikar, Nurbiya Ubul, Kurban School of Computer Science and Technology Xinjiang University Urumqi China School of Experimental Equipment Division Xinjiang University Urumqi China

ISBN: (纸本)9798350355925

Oracle bones, one of the earliest and most influential writing systems in China, have significantly contributed to the fields of archaeology and paleography. Despite the scarcity of oracle bone data available for scanning and the limited number of experts, the introduction of convolutional neural networks(CNNs) hasgreatly improved the efficiency and accuracy of automatic oracle bone recognition. However, issues such as data quality and category imbalance continue to constrain the development of oracle bone recognition techniques. To address these problems, this study proposes an approach based on an attention mechanism and a multi-expert learning network. First, a new attention mechanism is introduced to help the model recognize and enhance the stroke and radical regions that are critical for categorization decisions. Second, a multi-expert learning strategy integrates the decisions of multiple independently trained sub-models (experts) to achieve higher overall performance than a single model. Experimental results show that the proposed algorithm significantly improves oracle bone recognition, with an average accuracy improvement of 7.90% on the Oracle-AYNU dataset and 9.28% on the OBC306 dataset compared to the baseline model. © 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

Improving Sign Language recognition Performance Using Multimodal Data 25

Improving Sign Language Recognition Performance Using Multim...

引用

25th ieee International conference on Information Reuse and Integration for Data Science (ieee IRI)

作者： Nishimura, Tomoe Abbasi, Bahareh Calif State Univ Channel Isl Comp Sci Camarillo CA 93012 USA

ISBN: (纸本)9798350351194;9798350351187

Sign language is a language primarily used by the hearing-impaired for communication and has more than 200 variations worldwide. Communication is nearly impossible between signers of different variations. Moreover for a person with normal hearing, learning sign language can be challenging because the syntax of sign language differs from that of natural language. Translation of signs by machine learning offers potential solutions to these challenges, facilitating communication for everyone. This study attempts to enhance the performance of the existing state-of-the-art sign language translation model, Gloss attention SLT network (GASLT), through the integration of a multimodal approach. By combining RGB video with 3D pose data extracted using Mediapipe in an innovative way, our multimodal method significantly enhances the GASLT's results. We conducted two experiments involving the fusion of video and pose data with the GASLT model. These experiments led to an 18.39% improvement in the model's BLEU score compared to the original model, showcasing the effectiveness of the multimodal approach in enhancing sign translation.

关键词： sign language computer vision transformer Mediapipe multimodal

来源：评论

学校读者我要写书评

暂无评论

Analysing Digits with Sequential Convolutional Neural Networks and Adam Optimizer

Analysing Digits with Sequential Convolutional Neural Networ...

引用

2024 ieee International conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Agarwal, Muskan Gill, Kanwarpartap Singh Malhotra, Sonal Devliyal, Swati Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science & Engineering Graphic Era Hill University Uttarakhand Dehradun248002 India Computer Science & Engineering Graphic Era Deemed to Be University Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350382693

Numerical analysis is the focus of this study, which employs the Adam optimizer in conjunction with CNNs. computer vision and deep learning have enabled exact number recognition, which is crucial for many current applications such as optical character recognition and automated document processing. The chosen Sequential CNN design is perfect for efficient feature representation and extraction of basic services because of its pooling and convolutional layers. The Adam optimizer's ability to adjust the learning rate makes model training more efficient and speeds up convergence. Improving the model's accuracy is the main focus of the study. This may be achieved by methods such as regularisation, data augmentation, and hyperparameter tuning. Using assessment tools such as confusion matrices and classification reports, you may find out everything about the model's strengths and weaknesses. The model's capacity to produce and adapt to new numerical data sets is proven as it undergoes training, evaluation, and optimisation. The positive outcomes achieved by integrating a well-designed Sequential CNN with the Adam optimizer demonstrate the method's applicability to digit identification issues. This paper contributes to the ongoing discussion in computer vision and machine learning by exploring the complexities of digit analysis utilising Sequential CNNs and the Adam optimizer. The study does more than just establish a social solid foundation for accurate number identification;it also paves the way for future advancements in the broader area of AI applications as it shows a perfect precision. © 2024 ieee.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A computer vision Framework for Enhanced Object Detection Using ConvNeXt-YOLO Architecture with Multi-Scale Signal Processing 7

A Computer Vision Framework for Enhanced Object Detection Us...

引用

7th International conference on Automation Electronics and Electrical Engineering

作者： Jiang, Bojun Lin, Zekai Li, Zhuoyuan Jia, Ce Lu, Haiyang Northeastern Univ Shenyang Peoples R China Liaoning Tech Univ Coll Min Fuxin Peoples R China Liaoning Geol Engn Vocat Coll Dandong Peoples R China

ISBN: (纸本)9798350377040;9798350377033

We propose a comprehensive computer vision framework that integrates multi-scale signal processing with an enhanced ConvNeXt-YOLO architecture for robust object detection. Our framework addresses three critical challenges in visual recognition: multi-scale feature representation, signal quality enhancement, and model generalization. The framework implements a sophisticated signal processing pipeline for image preprocessing. Initially, we develop an adaptive resolution normalization algorithm that maintains consistent feature quality across varying input dimensions. Subsequently, we design a context-aware Gaussian filtering mechanism that optimizes the signal-to-noise ratio while preserving essential feature characteristics. These preprocessing techniques significantly enhance the framework's capability to extract discriminative features and maintain computational stability. To optimize the learning process, we introduce a systematic data augmentation strategy incorporating both geometric and signal-level transformations. Our approach combines predetermined rotation sampling (90 degrees, 180 degrees, 270 degrees) with continuous-space ROI augmentation during inference. This hybrid strategy enables the framework to achieve rotation invariance and enhanced generalization capabilities, particularly beneficial for complex object detection scenarios. The core innovation lies in our architectural integration of ConvNeXt with YOLO. We redesign the feature extraction backbone using hierarchical ConvNeXt blocks, enabling efficient multi-scale feature learning. The cross-branch information fusion mechanism, coupled with our signal-aware design, substantially improves the model's representational capacity. Experimental results on standard computer vision benchmarks demonstrate superior performance, achieving state-of-the-art accuracy (improvement of X%) and recall rates (improvement of Y%) compared to conventional approaches.

关键词： computer vision Framework Multi-scale Signal Processing Deep Learning Architecture ConvNeXt-YOLO Integration Feature Fusion Advanced Object Detection Semi-supervised Learning Object Summary

来源：评论

学校读者我要写书评

暂无评论

A Face recognition Security Alarm Method Based on Embedded Artificial Intelligence Chip

A Face Recognition Security Alarm Method Based on Embedded A...

引用

2023 ieee International conference on Sensors, Electronics and computer Engineering, ICSECE 2023

作者： Lv, Tianwen Zhejiang University of Technology Computer Science and Technology Hangzhou310058 China

ISBN: (纸本)9798350313734

In the aspect of intelligence, we try to use computer vision technology to analyze the face recognition information collected by the camera, so as to achieve the functions of early warning, prevention and active monitoring, so as to achieve the goal of completing the monitoring task instead of people. Therefore, this paper has carried out further research on this, and the experimental test results show that the recognition rate of this algorithm in ORL face database can be as high as 94.7%, and the recognition rate in Yale face database can also be as high as 85.3%. It is better than the other two algorithms. It can be seen that the recognition rate of the algorithm in this paper is the highest in the test results of two face databases. It can be seen that the embedded face recognition system has a certain robustness to the light changes in real life while accurately recognizing the face image. The face recognition stage based on embedded AI(Artificial Intelligence) chip extracts the features of the face image to be recognized, and compares them with the features of the trained samples stored on the disk, ensuring the user's autonomy in use. At the same time, the embedded AI chip can realize timely awareness and judgment of the recognition results, increasing the security privacy and reliability. © 2023 ieee.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Deep Classifiers Consistent with Fine-Grained Novelty Detection

Learning Deep Classifiers Consistent with Fine-Grained Novel...

引用

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

作者： Cheng, Jiacheng Vasconcelos, Nuno Univ Calif San Diego Dept Elect & Comp Engn San Diego CA 92103 USA

ISBN: (纸本)9781665445092

The problem of novelty detection in fine-grained visual classification (FGVC) is considered. An integrated understanding of the probabilistic and distance-based approaches to novelty detection is developed within the framework of convolutional neural networks (CNNs). It is shown that softmax CNN classifiers are inconsistent with novelty detection, because their learned class-conditional distributions and associated distance metrics are unidentifiable. A new regularization constraint, the class-conditional Gaussianity loss, is then proposed to eliminate this unidentifiability, and enforce Gaussian class-conditional distributions. This enables training Novelty Detection Consistent Classifiers (NDCCs) that are jointly optimal for classification and novelty detection. Empirical evaluations show that NDCCs achieve significant improvements over the state-of-the-art on both small- and large-scale FGVC datasets.

关键词： Measurement Training Visualization computer vision Probabilistic logic pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

PCGAUNet: Pixel Correlation and Gaussian Attention Driven Network for Text Segmentation 27th

PCGAUNet: Pixel Correlation and Gaussian Attention Driven Ne...

引用

27th International conference on pattern recognition, ICPR 2024

作者： Roy, Ayush Palaiahnakote, Shivakumara Pal, Umapada Antonacopoulos, Apostolos Ramachandra, Raghavendra Computer Vision and Pattern Recognition Indian Statistical Institute Kolkata India School of Science Engineering and Environment University of Salford Manchester United Kingdom Norwegian University of Science and Technology Trondheim Norway

ISBN: (纸本)9783031784460

Text-line segmentation is still considered challenging for complex background scene images. The success of text detection and recognition depends on the success of the text segmentation. This study presents a new method for text segmentation to facilitate reliable detection and recognition. Therefore, we introduce a new model called Pixel Correlation and Gaussian Attention Driven Network (PCGAUNet) for text segmentation. To extract pixel correlation, we modified the MultiResUnet architecture, which leverages pixel-wise correlation to effectively highlight foreground pixels. In addition, the proposed model utilizes the prior spatial statistics of bottleneck features to create a learnable Gaussian distribution, which guides the decoder for accurate text segmentation. Experimental results on three standard scene text segmentation datasets, ICDAR13 FST, Total Text, and COCO-TS, show that the proposed model outperforms existing methods. Furthermore, the results for the underwater dataset UTS-55 show that our model is robust and generic. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Checkerboard Context Model for Efficient Learned Image Compression

Checkerboard Context Model for Efficient Learned Image Compr...

引用

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

作者： He, Dailan Zheng, Yaoyan Sun, Baocheng Wang, Yan Qin, Hongwei SenseTime Res Hong Kong Peoples R China

ISBN: (纸本)9781665445092

For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process must be done in a strict scan order, which breaks the parallelization. We propose a parallelizable checkerboard context model (CCM) to solve the problem. Our two-pass checkerboard context calculation eliminates such limitations on spatial locations by re-organizing the decoding order. Speeding up the decoding process more than 40 times in our experiments, it achieves significantly improved computational efficiency with almost the same rate-distortion performance. To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.

关键词： computer vision Image coding Computational modeling Redundancy Rate-distortion Decoding pattern recognition

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 << < 420 421 422 423 424 425 426 427 428 429 > >>

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：