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

4,595 篇 会议
498 册 图书
65 篇 期刊文献

馆藏范围

5,157 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,378 篇 工学
- 2,739 篇 计算机科学与技术...
- 1,816 篇 软件工程
- 723 篇 信息与通信工程
- 720 篇 光学工程
- 661 篇 电气工程
- 415 篇 生物工程
- 361 篇 控制科学与工程
- 348 篇 生物医学工程（可授...
- 236 篇 机械工程
- 223 篇 电子科学与技术（可...
- 126 篇 仪器科学与技术
- 124 篇 化学工程与技术
- 117 篇 安全科学与工程
- 96 篇 交通运输工程
- 90 篇 材料科学与工程（可...
- 68 篇 建筑学
- 58 篇 土木工程
1,680 篇 理学
- 926 篇 物理学
- 720 篇 数学
- 452 篇 生物学
- 203 篇 统计学（可授理学、...
- 120 篇 化学
- 57 篇 系统科学
491 篇 管理学
- 269 篇 图书情报与档案管...
- 242 篇 管理科学与工程(可...
- 79 篇 工商管理
439 篇 医学
- 417 篇 临床医学
- 127 篇 基础医学(可授医学...
- 89 篇 药学(可授医学、理...
60 篇 法学
- 59 篇 社会学
54 篇 农学
35 篇 教育学
31 篇 艺术学
29 篇 经济学
11 篇 文学
11 篇 军事学

主题

813 篇 computer vision
624 篇 pattern recognit...
535 篇 image processing
355 篇 image processing...
347 篇 artificial intel...
336 篇 image segmentati...
271 篇 feature extracti...
203 篇 image recognitio...
171 篇 deep learning
155 篇 computer graphic...
149 篇 computer imaging...
137 篇 face recognition
121 篇 machine learning
121 篇 object recogniti...
117 篇 convolutional ne...
115 篇 image analysis
113 篇 object detection
108 篇 information syst...
105 篇 cameras
105 篇 shape

机构

25 篇 istituto italian...
24 篇 google deepmind ...
24 篇 meta ai barcelon...
23 篇 politecnico di t...
14 篇 national center ...
14 篇 institute of ima...
10 篇 shanghai jiao to...
10 篇 tsinghua univers...
10 篇 university of ch...
10 篇 institute of aut...
9 篇 institute of ima...
9 篇 computer vision ...
8 篇 indian statistic...
8 篇 inria nancy gran...
8 篇 dalian universit...
8 篇 icube université...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 department of co...

作者

24 篇 cristian canton
24 篇 alessio del bue
24 篇 tatiana tommasi
24 篇 jordi pont-tuset
17 篇 de-shuang huang
14 篇 stefanie speidel
12 篇 wilfried philips
9 篇 paul scheunders
9 篇 h. bischof
9 篇 jie yang
9 篇 stéphane cotin
9 篇 dan popescu
9 篇 mohamed kamel
8 篇 umapada pal
8 篇 aurélio campilho
8 篇 yefeng zheng
8 篇 kok wai wong
8 篇 christian barill...
8 篇 ilias maglogiann...
8 篇 tieniu tan

语言

5,033 篇 英文
104 篇 其他
52 篇 中文

检索条件"任意字段=4th International Conference on Computer Vision, Pattern Recognition and Image Processing"

共 5158 条记录，以下是91-100 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：

the Effect of a Weighted Mean Pooling on the Performance of Convolution Neural Network 4th

The Effect of a Weighted Mean Pooling on the Performance of ...

引用

4th international conference on Intelligent Systems and pattern recognition-ISPR

作者： Shadoul, Inas Hossen, Abdulnasir Mesbah, Mostefa Al-Hmouz, Rami Sultan Qaboos Univ Dept Elect Engn Coll Engn Al Khoud Oman

ISBN: (纸本)9783031821493;9783031821509

Convolutional Neural Networks (CNNs), a deep learning application, are powerful tools particularly suited for image processing and classification applications. Pooling is a major component of CNNs and significantly influences learning. In this step, data is reduced in size through a specific algorithm or technique, resulting in the reduction of the computational load on the layers. the various pooling techniques in CNNs have specific uses, features, and effects, some desirable and others counterproductive to the training goal. Using one pooling technique can produce results that other techniques cannot. Some cases can benefit differently from different pooling techniques. this raises the question of whether combining these pooling techniques could achieve a collective positive impact, potentially leading to performance gains beyond those achievable by individual techniques used separately. A control parameter is added to optimize the selection of the pooling method or could be a weighted combination of more than one method. the results show that the presented method guarantees the same performance as a single pooling layer at least and could be improved when weighted pooling layers are involved in some datasets.

关键词： Machine learning Convolution Neural Network (CNN) Pooling Mixed pooling image classification

来源：评论

学校读者我要写书评

暂无评论

Efficient Pest Classification Using Lightweight Neural Networks for Sustainable Pest Control 4

Efficient Pest Classification Using Lightweight Neural Netwo...

引用

4th international conference on computer Communication and Artificial Intelligence (CCAI)

作者： Yang, Jiaming Zhou, Yinghua Chongqing Univ Posts & Telecommun Coll Comp Sci & Technol Chongqing Peoples R China

ISBN: (纸本)9798350362770;9798350362763

the existence of pests and diseases threatens the agricultural production and brings serious economic losses to countries whose economy is based on agriculture. Traditional agricultural production methods require a lot of manpower to identify and detect pests and diseases, which will increase the cost of agricultural production. Now, with the development of deep learning technology, computer vision based approaches can help reduce costs and improve efficiency. through the deep learning model based on CNN, insects and pests can be accurately detected and recognized. this paper proposes an improved recognition model, MFnet, based on the lightweight deep neural network MobileNetV3. A new activation function, MLU6, is introduced in the proposed MFnet model. At the same time, we use the PolyLoss function to replace the cross-entropy loss function when training the proposed model. We also use transfer learning to improve the efficiency of network optimization and prevent overfitting through data augmentation and regularization. Ablation and comparative experiments are carried out and the IP102 pest dataset is used in the experiments. the experimental result shows that MFnet outperforms the original Mobilenetv3 and the other classic models in terms of classification accuracy, at the cost of increased number of parameters compared to the original Mobilenetv3. However, the parameter number, training time and classification time of the proposed model are still much less than those of the other classic models.

关键词： agriculture pest recognition computer vision image classification convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing pedestrian re-identification in low-light environments with multi-scale feature attention extraction network 4

Enhancing pedestrian re-identification in low-light environm...

引用

4th international conference on computer vision, Application, and Algorithm, CVAA 2024

作者： Li, Zhenghao Xiong, Jiping Li, Jiake College of Physics and Electronic Information Engineering Zhejiang Normal University Zhejiang Hangzhou China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Pedestrian re-identification has witnessed rapid development in recent years, with particular attention given to the challenges posed by complex conditions, including pedestrian re-identification in low-light environments, such as nighttime scenarios. through our experiments, it was discovered that even with image enhancement in low-light conditions, satisfactory results were not achieved. To address this challenge, this paper introduces a Multi-scale Feature Attention Extraction (MFAE) network. © 2025 SPIE.

关键词： Feature extraction image enhancement Network architectures image segmentation Education and training image processing Data modeling image restoration Lithium Pollution control

来源：评论

学校读者我要写书评

暂无评论

I2IP: image to image editing with prompt control using guided diffusion models 4

I2IP: image to image editing with prompt control using guide...

引用

4th international conference on computer vision and pattern Analysis, ICCPA 2024

作者： Cao, Yi Xiao, Zonglin Qiao, Yuming School of Mechanical and Power Engineering Shenyang University of Chemical Technology 110142 China Department of Engineering Physics Tsinghua University Beijing100084 China

ISBN: (纸本)9781510682528

Real image editing has been one of the important research topics in the field of image generation, with the proposal of diffusion model, real image editing based on the guided diffusion model has become the mainstream, which edits the original real image through different conditions (text, image, sketch et al.), and outputs the edited image that align well with input conditions. Among them, the image-based real image editing task often can only migrate the style of the reference image to the original image, which is not controllable enough and lacks the ability of fine-grained image translation. In this paper, we propose I2IP, which introduces text prompt in the image translation process to control the image translation process in a fine-grained way, to improve the generalization and refinement of the image translation algorithm. Compared to text-based real image editing, I2IP can achieve image style transfer with reference image, while compared to image-based real image editing, I2IP takes the advantage of text-based image editing and control the editing result. © 2024 SPIE.

关键词： image processing Diffusion image restoration Semantics image segmentation Process control Reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Chaotic Convolutional Long Short-Term Memory Network for Respiratory Motion Prediction 4

Chaotic Convolutional Long Short-Term Memory Network for Res...

引用

4th international conference on image processing and vision Engineering, IMPROVE 2024

作者： Ghasemi, Narges Nabavi, Shahabedin Moghaddam, Mohsen Ebrahimi Shekofteh, Yasser Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran Department of Computer Science Viterbi School of Engineering University of Southern California United States

ISBN: (纸本)9789897586934

One of the challenges of treating lung tumors in radiation therapy is the patient's respiratory movements during the treatment, which lead to tumor motion. the goal of respiratory motion prediction is to predict the movements of lung tissues and lung tumors during the breathing cycle. Predicting respiratory movements allows radiation to be directed only at the tumor, minimizing exposure to healthy tissue and reducing the risk of side effects. Using 4D CT images, we can find the next position of the lung tumor and make a 4D radiation therapy plan. As obtaining 4D CT scans is harmful to the patient due to radiation, the aim of this study is to construct a 4D CT during a respiratory cycle using only a 3D image. In this paper, a Chaotic Convolutional Long Short-Term Memory network is proposed, which utilizes chaotic features in respiratory signals to predict pulmonary movements more accurately. the innovation of this method is paying attention to chaotic features of respiratory signals, which leads to better interpretability of the presented model. the obtained results show that the proposed method has a higher learning speed and better performance compared to previous models, which generate 4D CT scans. Copyright © 2024 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Radiotherapy

来源：评论

学校读者我要写书评

暂无评论

A Moving Target Tracking Technology for Intelligent Police Based on Kalman Filter Method 4

A Moving Target Tracking Technology for Intelligent Police B...

引用

4th international conference on computer vision, image and Deep Learning, CVIDL 2023

作者： Dang, Longfei Yang, Miao Yi, Kai Si, Binghe Sichuan Police College Intelligent Policing Key Laboratory of Sichuan Province LuZhou China Sichuan Police College Department of Computer Science and Technology LuZhou China Sichuan Police College Department of Criminal Technology LuZhou China

ISBN: (纸本)9798350326444

Video image analysis mainly involves the analysis and processing of moving image sequences, which usually involves several processes such as motion detection, object classification, object tracking, and behavior understanding and description. Among them, moving object detection and tracking are at the bottom level of the entire visual monitoring system, and are the most basic methods in video image analysis. they are the foundation for various subsequent advanced processing. this article proposes a target detection and tracking algorithm based on Kalman filtering, which can effectively detect and track moving objects, providing a more efficient technical means for detecting and tracking target suspects in the era of big data. © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Remote Sensing image recognition Model for Ships 4

A Deep Learning-Based Remote Sensing Image Recognition Model...

引用

4th IEEE international conference on Power, Electronics and computer Applications, ICPECA 2024

作者： Li, Pingchi School of Information Engineering Wuhan University of Technology Wuhan China

ISBN: (纸本)9798350359589

With the rapid development of remote sensing technology, remote sensing satellite image datasets have become an important resource for research, providing rich data for the acquisition of surface information. However, for vessel detection and identification, it is usually very difficult to distinguish the background of the picture from the vessel in high-resolution optical images, which leads to a large number of false alarm problems. In this study, we aim to solve the problem of vessel image classification in remote sensing images by using a dataset containing 20,000 images. In this paper, bilateral filter is chosen as the filtering method to maximize the clarity of vessel edges. In this paper, rotation and flipping are mainly chosen to enhance the images. In this paper, the Convolutional Neural Network (CNN) model and the Transformer classification model VIT are constructed respectively, and their performance is evaluated. And the performance of the two models is compared by training on different sized datasets. When the number of datasets is 2.0× 104, the recognition accuracy of Transformer classification model VIT is higher than 90.2%, which effectively solves the problem of vessel recognition in remote sensing images. © 2024 IEEE.

关键词： Convolutional neural networks Deep learning image processing Remote sensing images

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Face Landmark Detection Techniques 4

A Comparison of Face Landmark Detection Techniques

引用

4th international conference on Computation, Automation and Knowledge Management, ICCAKM 2023

作者： Chandel, Ritika Bhowmick, Rajnandini Hariharan, U. Apex Institute of Technology Chandigarh University Punjab India

ISBN: (纸本)9798350393248

A lot of higher-order computer vision applications, like face recognition and facial expression analysis, depend on the precise detection of landmarks inside facial pictures. Although landmark localization is a straightforward and intuitive operation for humans, for it to be replicated in machines, it has taken multiple years of research, giving rise to large number of high-quality image data sets, and an abrupt increase in the processing capacity of computers to attain near-human proficiency. While recognizing physical characteristics on a face, such as types of noses, is an intuitive and ordinary task for human vision, it has proven to be quite tough for computer vision, as it has not profited from millennia of evolution. Although facial images generally have similar content, common variations in pose, lighting, facial expression, and facial features can give rise to a multitude of problems for many computer vision systems, leading to substantial errors and mistakes in the task of computer vision face landmarking accuracy. In this study, we examine the two facial landmark identification techniques already in use-the Mediapipe Face Landmarker and Dlib's 68-point face landmark detection algorithm-to determine the conditions in which each method performs best. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Emotion recognition system using CNN and open CV 4th

Emotion recognition system using CNN and open CV

引用

4th international conference on Computational Methods in Science and Technology, ICCMST 2024

作者： Singla, Ishdeep Raj, Pritam Raj, Ayush Vaibhav, Vibhanshu Charishma, Triukula Computer Science and Engineering Chandigarh University Punjab Gharuan India

ISBN: (纸本)9781032911571

Understanding facial expressions is crucial for effective non-verbal communication. Solely relying on spoken words without considering facial cues leads to an incomplete understanding. Traditionally, humans were the exclusive interpreters of facial expressions, but technological progress has now extended this capability to computers [9]. this document acts as a comprehensive guide for facial expression recognition software employing OpenCV, Keras, Tensorflow, & CNN. through Python programming, an algorithm has been developed to perform real-time detection, extraction, & evaluation of facial expressions for automated emotion recognition [10]. Essential facial features are examined to detect expressions, utilizing variations within these features to recognize different emotions. Machine learning algorithms are utilized to train models on diverse image datasets for emotion categorization [11]. the paper explores the live, real-time classification of face expression into 7 universal human emotions— Angry, Disgust, Fear, Happy, Neutral, Sad, & Surprise—using a vision system specifically designed for emotion recognition. © 2025 the Author(s).

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Person Re-identification through Low-Light image Enhancement 12th

Improving Person Re-identification Through Low-Light Image E...

引用

12th international conference on pattern recognition Applications and Methods (ICPRAM)

作者： Santana, Oliverio J. Lorenzo-Navarro, Javier Freire-Obregon, David Hernandez-Sosa, Daniel Castrillon-Santana, Modesto Univ Las Palmas Gran Canaria SIANI Las Palmas Gran Canaria Spain

ISBN: (纸本)9783031547256;9783031547263

Person re-identification (ReID) is a popular area of research in the field of computer vision. Despite the significant advancements achieved in recent years, most of the current methods rely on datasets containing subjects captured with good lighting under static conditions. ReID presents a significant challenge in real-world sporting scenarios, such as long-distance races that take place over varying lighting conditions, ranging from bright daylight to night-time. Unfortunately, increasing the exposure time on the capture devices to mitigate low-light environments is not a feasible solution, as it would result in blurry images due to the motion of the runners. this paper surveys several low-light image enhancement methods and finds that including an image pre-processing step in the ReID pipeline before extracting the distinctive body features of the subjects can lead to significant improvements in performance.

关键词： computer vision Person re-identification Sporting event Ultra-trail running In the wild dataset Low-light image enhancement

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 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：