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

50,693 篇 会议
1,424 册 图书
1,049 篇 期刊文献
1 篇 学位论文

馆藏范围

53,164 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,979 篇 工学
- 24,946 篇 计算机科学与技术...
- 12,662 篇 软件工程
- 5,176 篇 光学工程
- 4,776 篇 电气工程
- 4,488 篇 信息与通信工程
- 4,263 篇 机械工程
- 4,009 篇 控制科学与工程
- 2,480 篇 生物工程
- 1,737 篇 生物医学工程（可授...
- 1,583 篇 仪器科学与技术
- 1,332 篇 电子科学与技术（可...
- 795 篇 化学工程与技术
- 729 篇 安全科学与工程
- 570 篇 交通运输工程
- 389 篇 建筑学
- 339 篇 土木工程
11,923 篇 理学
- 6,487 篇 物理学
- 5,441 篇 数学
- 2,768 篇 生物学
- 1,918 篇 统计学（可授理学、...
- 804 篇 化学
- 669 篇 系统科学
5,318 篇 医学
- 5,105 篇 临床医学
- 732 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,389 篇 管理学
- 1,977 篇 图书情报与档案管...
- 1,565 篇 管理科学与工程(可...
- 487 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
439 篇 法学
- 411 篇 社会学
303 篇 农学
199 篇 教育学
167 篇 经济学
63 篇 文学
48 篇 军事学

主题

17,427 篇 computer vision
9,029 篇 pattern recognit...
4,199 篇 training
3,832 篇 feature extracti...
3,134 篇 cameras
2,879 篇 computational mo...
2,796 篇 image segmentati...
2,624 篇 visualization
2,574 篇 shape
2,536 篇 face recognition
2,176 篇 robustness
2,125 篇 computer science
1,976 篇 object detection
1,961 篇 computer archite...
1,882 篇 layout
1,855 篇 object recogniti...
1,801 篇 three-dimensiona...
1,725 篇 neural networks
1,705 篇 humans
1,700 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
135 篇 national laborat...
106 篇 univ sci & techn...
104 篇 zhejiang univers...
101 篇 shanghai jiao to...
95 篇 university of sc...
95 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...
66 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

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

语言

51,180 篇 英文
1,749 篇 其他
253 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
1 篇 法文

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

共 53167 条记录，以下是4701-4710 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：

Deep Neural Networks and Convolution Neural Network for computer vision based Crime Similarity pattern Analysis 5

Deep Neural Networks and Convolution Neural Network for Comp...

引用

5th International conference on Smart Electronics and Communication, ICOSEC 2024

作者： Monika, E. Kumar, T. Rajesh Saveetha Institue of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331504403

In today's society, preventing and mitigating crime is crucial for maintaining public safety, promoting community well-being, and ensuring the overall security of a society. Each day, criminals perpetrate thousands of crimes. In the field of law enforcement and public safety, crime pattern similarity analysis is a crucial task that aims to unearth hidden linkages and repeating behaviors inside criminal episodes. Convolutional Neural Networks (CNNs) and Deep Neural Networks (DNNs) are two concepts of advanced neural network designs that can be integrated to improve understanding and prediction of crime patterns similarity analysis. This study explores the use of CNNs and DNNs in crime pattern similarity analysis, offering a novel strategy to help law enforcement organizations understand the complex relationships in crime-related data. This research aims to improve crime prevention, investigation, and public safety by exposing hidden patterns, foreseeing upcoming trends, and enabling data-driven decision-making. It is feasible to improve the model's convergence, stability, and capacity to learn efficiently from various and complicated surveillance image data by using RMSprop as an optimizer when training CNN and DNN models for crime similarity pattern identification in computer vision applications. © 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

Deep Fusion of Appearance and Frame Differencing for Motion Segmentation

Deep Fusion of Appearance and Frame Differencing for Motion ...

引用

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

作者： Ellenfeld, Marc Moosbauer, Sebastian Cardenes, Ruben Klauck, Ulrich Teutsch, Michael Hensoldt Optron GmbH Oberkochen Germany Hensoldt Analyt GmbH Oberkochen Germany Aalen Univ Appl Sci Aalen Germany Univ Western Cape Cape Town South Africa

ISBN: (纸本)9781665448994

Motion segmentation is a technique to detect and localize class-agnostic motion in videos. This motion is assumed to be relative to a stationary background and usually originates from objects such as vehicles or humans. When the camera moves, too, frame differencing approaches that do not have to model the stationary background over minutes, hours, or even days are more promising compared to background subtraction methods. In this paper, we propose a Deep Convolutional Neural Network (DCNN) for multi-modal motion segmentation: the current image contributes with appearance information to distinguish between relevant and irrelevant motion and frame differencing captures the temporal information, which is the scene's motion independent of the camera motion. We fuse this information to receive an effective and efficient approach for robust motion segmentation. The effectiveness is demonstrated using the multi-spectral CDNet-2014 dataset that we re-labeled for motion segmentation. We specifically show that we can detect tiny moving objects significantly better compared to methods based on optical flow.

关键词： computer vision Image segmentation Three-dimensional displays Fuses Motion segmentation Cameras pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SDD: A Benchmark for Empowering Shadow Detection 7

SDD: A Benchmark for Empowering Shadow Detection

引用

7th International conference on Artificial Intelligence and Big Data (ICAIBD)

作者： Zhang, Hao Wu, You Guo, Xiaoyu Huang, Ling Ye, Hengzhou Li, Shuiwang Guilin Univ Technol Coll Comp Sci & Engn Guilin Peoples R China

ISBN: (纸本)9798350385113;9798350385106

In the field of computer vision, shadow detection has been a topic of considerable interest. Shadows encapsulate a wealth of information about the underlying light conditions and scene geometry, making them invaluable for a wide range of visual perception tasks, from understanding the physical properties of light to interpreting the structure and layout of the surrounding environment. Moreover, shadows affect image quality, thereby influencing the results of computer vision algorithms such as object detection, recognition, and tracking. Therefore, identifying and eliminating shadows contributes to improving algorithm performance. However, shadow detection research faces the challenge of scarce high-quality annotated datasets. To address this problem, we introduce a novel shadow detection dataset called Shadow Detection Dataset (SDD), consisting of 2638 images covering various scenes including urban streets, natural landscapes, and indoor spaces. Additionally, we evaluate the performance of eight state-of-the-art object detection methods on SDD to compare and reveal their effectiveness in shadow detection tasks. Through comparative experimental results, we find significant differences in the performance of different methods across various scenes, underscoring the significance of the proposed dataset in assessing the performance of shadow detection techniques. In the future, we look forward to further expanding this dataset and exploring more effective shadow detection methods to meet the growing demands of applications and advance the field. The dataset is available to the public at https://***/hhaozhang/SDD.

关键词： computer vision shadow detection evaluation dataset

来源：评论

学校读者我要写书评

暂无评论

Traffic Video Event Retrieval via Text Query using Vehicle Appearance and Motion Attributes

Traffic Video Event Retrieval via Text Query using Vehicle A...

引用

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

作者： Tien-Phat Nguyen Ba-Thinh Tran-Le Xuan-Dang Thai Nguyen, Tam, V Do, Minh N. Minh-Triet Tran Univ Sci Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam John von Neumann Inst Ho Chi Minh City Vietnam Univ Dayton Dayton OH 45469 USA Univ Illinois Urbana IL USA

ISBN: (纸本)9781665448994

Traffic event retrieval is one of the important tasks for intelligent traffic system management. To find accurate candidate events in traffic videos corresponding to a specific text query, it is necessary to understand the text query's attributes, represent the visual and motion attributes of vehicles in videos, and measure the similarity between them. Thus we propose a promising method for vehicle event retrieval from a natural-language-based specification. We utilize both appearance and motion attributes of a vehicle and adapt the COOT model to evaluate the semantic relationship between a query and a video track. Experiments with the test dataset of Track 5 in AI City Challenge 2021 show that our method is among the top 6 with a score of 0.1560.

关键词： Visualization computer vision Tracking conferences Urban areas Semantics pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Car recognition System Using Convolutional Neural Network 6

Car Recognition System Using Convolutional Neural Network

引用

6th International conference on Contemporary Computing and Informatics, IC3I 2023

作者： Chauhan, Shweta Kumar, Rahul Kumar, Bibek University Centre for Research and Development Chandigarh University Mohali India Vishweshwarya Group of Institutions Computer Science Engineering Delhi India

ISBN: (纸本)9798350304480

Car recognition systems have been gaining popularity in recent years due to their ability to identify the make, model, and year of cars from images. In this paper, we present the building of accurate car recognition systems by using neural networks. This paper proposes a car recognition system using the convolution neural network and VMMRdb dataset and the ResNet-152 model, which provides state-of-the-art performance in image classification tasks. The performance of the proposed model is compared with the GG16 model. The experimental results show that the developed car recognition system achieved high accuracy of 54.4% and efficiency in identifying the cars which has important applications in traffic analysis, theft prevention, and marketing research. We also compared the performance of our model with that of other state-of-the-art car recognition systems, including the popular VGG16 model. This object recognition system has practical applications in various fields, such as law enforcement, parking access control, and traffic monitoring, and can help identify stolen or wanted vehicles quickly and efficiently. © 2023 ieee.

关键词： CNNs computer vision Resnet152 Torch vision

来源：评论

学校读者我要写书评

暂无评论

End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution

End-to-End Learning for Joint Image Demosaicing, Denoising a...

引用

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

作者： Xing, Wenzhu Egiazarian, Karen Tampere Univ Computat Image Grp Tampere Finland

ISBN: (纸本)9781665445092

Image denoising, demosaicing and super-resolution are key problems of image restoration well studied in the recent decades. Often, in practice, one has to solve these problems simultaneously. A problem of finding a joint solution of the multiple image restoration tasks just begun to attract an increased attention of researchers. In this paper, we propose an end-to-end solution for the joint demosaicing, denoising and super-resolution based on a specially designed deep convolutional neural network (CNN). We systematically study different methods to solve this problem and compared them with the proposed method. Extensive experiments carried out on large image datasets demonstrate that our method outperforms the state-of-the-art both quantitatively and qualitatively. Finally, we have applied various loss functions in the proposed scheme and demonstrate that by using the mean absolute error as a loss function, we can obtain superior results in comparison to other cases.

关键词： Training Superresolution Noise reduction Switches Image restoration pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Explainable Noisy Label Flipping for Multi-Label Fashion Image Classification

Explainable Noisy Label Flipping for Multi-Label Fashion Ima...

引用

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

作者： Ferreira, Beatriz Quintino Costeira, Joao P. Gomes, Joao P. Univ Lisbon ISR IST Lisbon Portugal

ISBN: (纸本)9781665448994

In online shopping applications, the daily insertion of new products requires an overwhelming annotation effort. Usually done by humans, it comes at a huge cost and yet generates high rates of noisy/missing labels that seriously hinder the effectiveness of CNNs in multi-label classification. We propose SELF-ML, a classification framework that exploits the relation between visual attributes and appearance together with the "low-rank" nature of the feature space. It learns a sparse reconstruction of image features as a convex combination of very few images - a basis - that are correctly annotated. Building on this representation, SELF-ML has a module that relabels noisy annotations from the derived combination of the clean data. Due to such structured reconstruction, SELF-ML gives an explanation of its label-flipping decisions. Experiments on a real-world shopping dataset show that SELF-ML significantly increases the number of correct labels even with few clean annotations.

关键词： Visualization computer vision Annotations conferences Buildings pattern recognition Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Localized Triplet Loss for Fine-grained Fashion Image Retrieval

Localized Triplet Loss for Fine-grained Fashion Image Retrie...

引用

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

作者： D'Innocente, Antonio Garg, Nikhil Zhang, Yuan Bazzani, Loris Donoser, Michael Sapienza Univ Rome Rome Italy Amazon Munich Germany Amazon Seattle WA USA

ISBN: (纸本)9781665448994

Fashion retrieval methods aim at learning a clothing-specific embedding space where images are ranked based on their global visual similarity with a given query. However, global embeddings struggle to capture localized fine-grained similarities between images, because of aggregation operations. Our work deals with this problem by learning localized representations for fashion retrieval based on local interest points of prominent visual features specified by a user. We introduce a localized triplet loss function that compares samples based on corresponding patterns. We incorporate random local perturbation on the interest point as a key regularization technique to enforce local invariance of visual representations. Due to the absence of existing fashion datasets to train on localized representations, we introduce FashionLocalTriplets, a new high-quality dataset annotated by fashion specialists that contains triplets of women's dresses and interest points. The proposed model outperforms state-of-the-art global representations on FashionLocalTriplets.

关键词： Visualization computer vision Annotations Perturbation methods conferences Image retrieval pattern recognition

来源：评论

学校读者我要写书评

暂无评论

3D Spatial recognition without Spatially Labeled 3D

3D Spatial Recognition without Spatially Labeled 3D

引用

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

作者： Ren, Zhongzheng Misra, Ishan Schwing, Alexander G. Girdhar, Rohit Facebook AI Res Menlo Pk CA 94025 USA Univ Illinois Urbana IL 61801 USA

ISBN: (纸本)9781665445092

We introduce WyPR, a Weakly-supervised framework for Point cloud recognition, requiring only scene-level class tags as supervision. WyPR jointly addresses three core 3D recognition tasks: point-level semantic segmentation, 3D proposal generation, and 3D object detection, coupling their predictions through self and cross-task consistency losses. We show that in conjunction with standard multiple-instance learning objectives, WyPR can detect and segment objects in point cloud data without access to any spatial labels at training time. We demonstrate its efficacy using the ScanNet and S3DIS datasets, outperforming prior state of the art on weakly-supervised segmentation by more than 6% mIoU. In addition, we set up the first benchmark for weakly-supervised 3D object detection on both datasets, where WyPR outperforms standard approaches and establishes strong baselines for future work.

关键词： Training Couplings computer vision Three-dimensional displays Semantics Object detection pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Denoising and recognition of Handwritten Characters Using Deblur GAN-CNN 4

A Hybrid Approach for Denoising and Recognition of Handwritt...

引用

4th ieee International conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Bharati, P. Vijaya Vignan's Institute of Engineering for Women Department of Computer Science and Engineering India

ISBN: (纸本)9798331518981

Handwritten Character recognition (HCR) is a critical area of research within pattern recognition and artificial intelligence, with applications spanning from document digitization, optical character recognition (OCR), and handwriting analysis. Despite significant technological advancements, accurate recognition of handwritten characters remains challenging due to variations in writing styles, sizes, and inherent *** paper presents a novel approach to HCR, utilizing a combination of Deblur Generative Adversarial Networks (GAN) and Convolutional Neural Networks (CNN) to effectively address these challenges. Unlike traditional deblurring methods, which often introduce artifacts or blur the edges of characters, Deblur GAN is specifically trained to enhance the clarity of handwritten images while preserving essential character features. This allows the subsequent CNN to extract more accurate and discriminative features, leading to improved character *** extensive experimentation on benchmark datasets such as MNIST, an approach that significantly outperforms the existing methods is demonstrated in terms of recognition accuracy, particularly in scenarios involving blurred or indistinct handwriting. These findings highlight the potential of integrating deblurring techniques with deep learning models to address persistent challenges in handwritten character recognition, paving the way for enhanced automation and efficiency in text analysis tasks. © 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

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 << < 467 468 469 470 471 472 473 474 475 476 > >>

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：