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

4,593 篇 会议
498 册 图书
65 篇 期刊文献

馆藏范围

5,155 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,376 篇 工学
- 2,738 篇 计算机科学与技术...
- 1,816 篇 软件工程
- 722 篇 信息与通信工程
- 721 篇 光学工程
- 661 篇 电气工程
- 415 篇 生物工程
- 359 篇 控制科学与工程
- 348 篇 生物医学工程（可授...
- 234 篇 机械工程
- 223 篇 电子科学与技术（可...
- 125 篇 仪器科学与技术
- 122 篇 化学工程与技术
- 116 篇 安全科学与工程
- 95 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
- 721 篇 数学
- 452 篇 生物学
- 203 篇 统计学（可授理学、...
- 119 篇 化学
- 57 篇 系统科学
490 篇 管理学
- 269 篇 图书情报与档案管...
- 241 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

811 篇 computer vision
622 篇 pattern recognit...
535 篇 image processing
355 篇 image processing...
347 篇 artificial intel...
336 篇 image segmentati...
269 篇 feature extracti...
202 篇 image recognitio...
171 篇 deep learning
155 篇 computer graphic...
149 篇 computer imaging...
137 篇 face recognition
122 篇 object recogniti...
121 篇 machine learning
117 篇 convolutional ne...
114 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

5,032 篇 英文
103 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 5156 条记录，以下是441-450 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：

Design and Evaluation of a Deep Learning Model for Counting Objects in Satellite images 4

Design and Evaluation of a Deep Learning Model for Counting ...

引用

4th IEEE international conference on Data Engineering and Communication Systems, ICDECS 2024

作者： Raja Subramanian, R. Paidimarri, Nithish Navuluri, Balaji Oleti, Bobby Sai Vignesh Boogavarapu, Mohan Mahesh Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Virudhnagar India

ISBN: (纸本)9798350393354

images obtained by satellites orbiting in space of the surface of the Earth or other celestial bodies are known as satellite images. these photos are an excellent resource for a variety of applications and have several uses. Applications are of earth observation, remote sensing and GIS etc. they are essential to tackling global issues and expanding scientific knowledge, and they play a crucial part in modern technology. Automated object counting in satellite images is a computer vision and image processing technique used to identify and quantify specific objects or features within images captured by Earth-observing satellites. After performing image preparation steps like using the CNN method and reducing noise, we must then recognize objects in the picture. Object counting has wide range of applications like Urban planning development, Military and Defence etc... In essence, automatic item counting in satellite photos helps businesses and researchers effectively obtain important information and make defensible choices. It considerably improves the capacity to manage and analyse extensive geographic data for a variety of applications. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Mobile pattern display design based on Field Programmable Gate Array 4

Mobile pattern display design based on Field Programmable Ga...

引用

4th international conference on Signal processing and computer Science, SPCS 2023

作者： Zhao, Yiquan Liu, Chenyu Yang, Quan Zhang, Yuanyuan Qu, Yifei Shenyang Aerospace University Shenyang China

ISBN: (纸本)9781510672505

FPGA (Field Programmable Gate Array) is a gate array that can be programmed in real time and is widely used in the electronics industry. In this paper, a moving pattern display system based on VGA (Video Graphics Array) display is implemented by using VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) language "top-down" design and FPGA opening board and display. the system was developed with the aim of developing a portable vision protection device whose basic function is to display dynamic ICONS on the screen. Taking this paper as an example, its function is to make a 50×50 pixels white square display and move in 1024×768×60 display mode, the white square will recognize the display border and automatically bounce at the border. In the future, the display content can be modified according to needs, and the transformation of dynamic pinball games, low-power fun signs and other achievements can be completed. © 2023 SPIE.

关键词： computer hardware description languages

来源：评论

学校读者我要写书评

暂无评论

2022 4th international conference on Robotics and computer vision, ICRCV 2022

2022 4th International Conference on Robotics and Computer V...

引用

4th international conference on Robotics and computer vision, ICRCV 2022

ISBN: (纸本)9781665481700

the proceedings contain 67 papers. the topics discussed include: building extraction from high resolution remote sensing images based on improved mask R-CNN;determination of protein content of wheat using partial least squares regression based on near-infrared spectroscopy preprocessing;high-accuracy three-dimensional depth measurement using light field camera via correlation spectrum phase;spatial-temporal network data-driven multi-layer traffic knowledge graph reconstruction for dynamic prediction;semantic injection infrared and visible image fusion via a disentangled representation network;information recognition of printed quantum dots matrix image under uncorrected conditions;multiple mask enhanced transformer for robust visual tracking;research on lightweight network of human posture estimation for physical training;multi-view auto-calibration method based on human pose estimation;context-aware network for person search;and face expression recognition based on lightweight fused attention mechanism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FIDAVL: Fake image Detection and Attribution Using vision-Language Model 27th

FIDAVL: Fake Image Detection and Attribution Using Vision-La...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Keita, Mamadou Hamidouche, Wassim Eutamene, Hessen Bougueffa Taleb-Ahmed, Abdelmalik Hadid, Abdenour Laboratory of IEMN Univ. Polytechnique Hauts-de-France Valenciennes France Univ. Rennes INSA Rennes CNRS IETR - UMR Rennes6164 France Sorbonne Center for Artificial Intelligence Sorbonne University Abu Dhabi Abu Dhabi United Arab Emirates

ISBN: (纸本)9783031783043

We introduce FIDAVL: Fake image Detection and Attribution using a vision-Language Model. FIDAVL is a novel and efficient multitask approach inspired by the synergies between vision and language processing. Leveraging the benefits of zero-shot learning, FIDAVL exploits the complementarity between vision and language along with soft prompt-tuning strategy to detect fake images and accurately attribute them to their originating source models. We conducted extensive experiments on a comprehensive dataset comprising synthetic images generated by various state-of-the-art models. Our results demonstrate that FIDAVL achieves an encouraging average detection accuracy of 95.42% and F1-score of 95.47% while also obtaining noteworthy performance metrics, with an average F1-score of 92.64% and ROUGE-L score of 96.50% for attributing synthetic images to their respective source generation models. the source code of this work will be publicly released at https://***/Mamadou-Keita/FIDAVL. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Insulator image Dataset Generation based on Generative Adversarial Network 4

Insulator Image Dataset Generation based on Generative Adver...

引用

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

作者： Fang, Yixin Zhang, Xiangquan Cao, Hui Nie, Jianglong Chen, Zhao He, Zhouqiang School of Electrical Engineering Xi'An Jiaotong University Xi'an China State Grid Gansu Electric Power Company Lanzhou China

ISBN: (纸本)9798350326444

For the intelligent processing of power equipment, its image datasets are often required as data support. However, the collection of power equipment image datasets is limited by the location and environment, and the number of collected datasets is relatively small, which cannot provide enough data for specific applications. this paper proposes to use image generation function of generative adversarial network to generate more images of electrical equipment from existing datasets with a smaller number, thereby increasing the size of electrical equipment datasets. In this paper, the insulator dataset is mainly used for experiment. First, the model building of the generative adversarial network is carried out. this paper uses pytorch to build three network model frameworks of generative adversarial networks, namely self-attention generative adversarial network, boundary equilibrium generative adversarial network and projected generative adversarial network, and selects relevant loss function and training method according to characteristics of each model. Second, models are trained on these three GAN s for the insulator image dataset and analyze experimental results of these three models. Finally, generated results and FID scores of the three models are compared. the FID score of projected generative adversarial network is the lowest, and the quality and diversity of the generated samples are the best, indicating that this model can better learn the characteristics of images and is more suitable for the generation of power equipment datasets. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Implementation of GF-CNN for Advanced Traffic Sign recognition in Transportation Systems 4

Efficient Implementation of GF-CNN for Advanced Traffic Sign...

引用

4th IEEE international conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Valarmathy, A.S. Katyal, Ashu Narmadha, T. Bewoor, L.A. Karthigaikumar, P. Faiz, Ayaan Prince Shri Venkateshwara Padmavathy Engineering College Department of Eee Chennai127 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India School of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Vishwakarma Institute of Technology Pune India Karpagam College of Engineering Department of Electronics and Communication Engineering Coimbatore641032 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India

ISBN: (纸本)9798331518981

Traffic violations cause accidents nowadays. Traffic accidents sometimes result from disobedience of traffic signs owing to low sight, inadequate light, and lack of expertise. ADAS and ITS are the only solutions to prevent accidents. ADAS detects traffic signs and ITS recognizes images for various transport applications. ADAS and ITS can detect minor traffic signs and provide driving information to guarantee road user safety. A key function of ADAS is to inform drivers and traffic signs. One research used traffic sign detection to aid vehicle navigation and driving assistance. Overfitting in the current technique reduces traffic sign detection performance. For image analysis, this study employs Gabor filter, Grey Level Co-occurrence Matrix, and Local Optimal Oriented pattern feature extraction approaches. Our multi-threshold Otsu approach and cuckoo search method aid in segmentation. the SVM classifier performs traffic sign detection. the hybrid feature extraction approach enhances traffic sign identification by exploring the form, color, and texture of the board. Research used an enhanced CNN to recognize traffic signs. Current hybrid feature extraction approach achieves 98.97% accuracy in classifying six traffic signs, however processing time is high for multi-operations. To categorize 10 traffic signs with 99.1% accuracy, an enhanced CNN is presented. © 2024 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

ComDensE Combined Dense Embedding of Relation-aware and Common Features for Knowledge Graph Completion 26

ComDensE Combined Dense Embedding of Relation-aware and Comm...

引用

26th international conference on pattern recognition / 8th international Workshop on image Mining - theory and Applications (IMTA)

作者： Kim, Minsang Baek, Seungjun Kakao Enterprise Seongnam South Korea Korea Univ Seoul South Korea

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Real-world knowledge graphs (KG) are mostly incomplete. the problem of recovering missing relations, called KG completion, has recently become an active research area. Knowledge graph (KG) embedding, a low-dimensional representation of entities and relations, is the crucial technique for KG completion. Convolutional neural networks in models such as ConvE, SACN, InteractE, and RGCN achieve recent successes. this paper takes a different architectural view and proposes ComDensE which combines relation-aware and common features using dense neural networks. In the relation-aware feature extraction, we attempt to create relational inductive bias by applying an encoding function specilic to each relation. In the common feature extraction, we apply the common encoding function to all input embeddings. these encoding functions are implemented using dense layers in ComDensE. ComDensE achieves the state-of-the-art performance in the link prediction in terms of MRR, HIT@1 on FB15k-237 and HIT@1 on WN18RR compared to the previous baseline approaches. We conduct an extensive ablation study to examine the effects of the relation-aware layer and the common layer of the ComDensE. Experimental results illustrate that the combined dense architecture as implemented in ComDensE achieves the best performance.

关键词： computer vision Computational modeling Neural networks computer architecture Feature extraction Encoding Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Research on Automobile Braking Performance Testing System Based on image processing Technology 4

Research on Automobile Braking Performance Testing System Ba...

引用

4th international conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2022

作者： Ma, Ruilin Tianjin University of Technology School of Management Tianjin China

ISBN: (纸本)9781665463997

To enable cars to brake when encountering emergencies and reduce casualties and property losses, the state needs to test the braking performance of vehicles on time. this paper designs an image processing-based automotive braking performance testing system, which adopts the displacement measurement principle of computer vision, pre-processes the image, purifies the multi-constrained feature points for the SURF feature point algorithm, effectively eliminates the wrong matching points, locates and extracts the region of interest, and realizes the target feature point tracking, to measure the braking parameters. the image processing algorithm was tested under three different test environments, and it was concluded that the parameters should be more accurate when performing vehicle braking performance testing in an environment where the road is ordinarily free of cracks, the camera is 20CM above ground height and braking at 20Km/h - 40Km/h initial speed. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Chunking of Setswana noun and verb phrases 4

Chunking of Setswana noun and verb phrases

引用

4th IEEE international conference on pattern recognition and Machine Learning, PRML 2023

作者： Malema, Gabofetswe Motlhanka, Moffat Okgetheng, Boago University of Botswana Department of Computer Science Gaborone Botswana

ISBN: (纸本)9798350324303

Identification of sentence constituents such as phrases, clauses, objects, and subjects in natural language processing is one of the pre-processing phases that make it possible to do other complex tasks such as information retrieval, and syntax analysis. the task is usually achieved through chunking which does not necessarily identify the internal structure of the constituent. the main goal of the chunking task is the identification of the start and end of a constituent. the identification of Setswana sentence constituents has not been widely studied. Verb and noun phrases have been used in previous studies to identify indirect relatives. However, there was no detailed investigation of the identification of these phrases. the focus was on indirect relatives. In this study, we use a rule-based approach to identify verb and noun phrases in a given sentence. the structure of these phrases is used to form patterns and rules which are used to identify the beginning and end of phrases. this approach shows that verb and noun phrases have a regular structure that can be represented by regular expressions or patterns. the proposed chunker identifies phrases and their internal structure. Furthermore, the chunker identifies nested phrases consisting of other phrases, qualificatives, and adverbs. the proposed tool has a recall of 74%, precision of 74%, and F-score of 74%. the tool fails in some cases due to challenges in the identification of sub-structures such as qualificatives clauses and phrases. A detailed analysis of the results shows that phrases have ambiguity which leads to incorrect chunking of phrases. © 2023 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

StableTalk: Advancing Audio-to-Talking Face Generation with Stable Diffusion and vision Transformer 27th

StableTalk: Advancing Audio-to-Talking Face Generation with...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Nazarieh, Fatemeh Kittler, Josef Rana, Muhammad Awais Kanojia, Diptesh Feng, Zhenhua School of Computer Science and Electronic Engineering University of Surrey Guildford United Kingdom Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Institute for People-Centred AI University of Surrey Guildford United Kingdom School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (纸本)9783031781711

Audio-to-talking face generation stands at the forefront of advancements in generative AI. It bridges the gap between audio and visual representations by generating synchronized and realistic talking faces. Despite recent progress, the lack of realism in animated faces, asynchronous audio-lip movements, and computational burden remain key barriers to practical applications. To address these challenges, we introduce a novel approach, StableTalk, leveraging the emerging capabilities of Stable diffusion models and vision Transformers for Talking face generation. We also integrate the Re-attention mechanism and adversarial loss to improve the consistency of facial animations and synchronization with a given audio input. More importantly, the computational efficiency of our method has been notably enhanced by optimizing operations within the latent space and dynamically adjusting the focus on different parts of the visual content based on the provided conditions. Our experimental results demonstrate the superiority of StableTalk over the existing approaches in image quality, audio-lip synchronization, and computational efficiency. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Animation

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 << < 41 42 43 44 45 46 47 48 49 50 > >>

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：