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

1,926 篇 会议
24 篇 期刊文献
17 册 图书

馆藏范围

1,966 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,605 篇 工学
- 1,333 篇 计算机科学与技术...
- 466 篇 软件工程
- 250 篇 电气工程
- 235 篇 机械工程
- 186 篇 光学工程
- 178 篇 信息与通信工程
- 119 篇 控制科学与工程
- 96 篇 生物工程
- 62 篇 生物医学工程（可授...
- 41 篇 仪器科学与技术
- 38 篇 电子科学与技术（可...
- 30 篇 化学工程与技术
- 21 篇 安全科学与工程
- 18 篇 材料科学与工程（可...
- 15 篇 交通运输工程
- 13 篇 建筑学
444 篇 理学
- 257 篇 物理学
- 202 篇 数学
- 110 篇 生物学
- 57 篇 统计学（可授理学、...
- 22 篇 化学
228 篇 医学
- 200 篇 临床医学
- 26 篇 基础医学(可授医学...
- 22 篇 特种医学
137 篇 管理学
- 83 篇 图书情报与档案管...
- 60 篇 管理科学与工程(可...
- 19 篇 工商管理
27 篇 艺术学
- 27 篇 设计学（可授艺术学...
16 篇 农学
- 15 篇 作物学
15 篇 法学
- 13 篇 社会学
9 篇 教育学
7 篇 经济学
5 篇 文学
5 篇 军事学

主题

320 篇 computer vision
180 篇 pattern recognit...
119 篇 feature extracti...
82 篇 face recognition
68 篇 training
61 篇 object detection
60 篇 image segmentati...
54 篇 deep learning
51 篇 robustness
46 篇 cameras
44 篇 visualization
43 篇 semantics
38 篇 object recogniti...
37 篇 shape
35 篇 neural networks
34 篇 histograms
33 篇 image recognitio...
32 篇 support vector m...
29 篇 humans
28 篇 face detection

机构

89 篇 univ chinese aca...
67 篇 chinese acad sci...
58 篇 national laborat...
56 篇 chinese acad sci...
50 篇 univ chinese aca...
36 篇 chinese univ hon...
34 篇 university of ch...
27 篇 chinese acad sci...
25 篇 school of artifi...
23 篇 univ sci & techn...
19 篇 institute of aut...
18 篇 chinese acad sci...
17 篇 chinese univ hon...
16 篇 chinese acad sci...
16 篇 univ chinese aca...
15 篇 national laborat...
15 篇 computer vision ...
14 篇 department of in...
14 篇 chinese acad sci...
14 篇 chinese univ hon...

作者

32 篇 wang xiaogang
29 篇 lu hanqing
28 篇 tan tieniu
28 篇 wang jinqiao
23 篇 li stan z.
22 篇 pal umapada
21 篇 huang kaiqi
21 篇 lei zhen
21 篇 qiao yu
19 篇 hu weiming
18 篇 tang xiaoou
15 篇 wang liang
15 篇 chen xilin
15 篇 cheng jian
14 篇 liu jing
14 篇 tang ming
13 篇 ouyang wanli
13 篇 xilin chen
12 篇 xiaoou tang
12 篇 wen gao

语言

1,946 篇 英文
19 篇 中文
7 篇 其他
1 篇 土耳其文

检索条件"任意字段=7th Chinese Conference on Pattern Recognition and Computer Vision"

共 1967 条记录，以下是591-600 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：

Online Joint Multi-Metric Adaptation from Frequent Sharing-Subset Mining for Person Re-Identification

Online Joint Multi-Metric Adaptation from Frequent Sharing-S...

引用

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

作者： Zhou, Jiahuan Su, Bing Wu, Ying Northwestern Univ Dept Elect & Comp Engn Evanston IL 60208 USA Chinese Acad Sci Inst Software Beijing Peoples R China

ISBN: (纸本)9781728171685

Person Re-IDentification (P-RID), as an instance-level recognition problem, still remains challenging in computer vision community. Many P-RID works aim to learn faithful and discriminative features/metrics from offline training data and directly use them for the unseen online testing data. However, their performance is largely limited due to the severe data shifting issue between training and testing data. therefore, we propose an online joint multi-metric adaptation model to adapt the offline learned P-RID models for the online data by learning a series of metrics for all the sharing-subsets. Each sharing-subset is obtained from the proposed novel frequent sharing-subset mining module and contains a group of testing samples which share strong visual similarity relationships to each other. Unlike existing online P-RID methods, our model simultaneously takes both the sample-specific discriminant and the set-based visual similarity among testing samples into consideration so that the adapted multiple metrics can refine the discriminant of all the given testing samples jointly via a multi-kernel late fusion framework. Our proposed model is generally suitable to any offline learned P-RID baselines for online boosting, the performance improvement by our model is not only verified by extensive experiments on several widely-used P-RID benchmarks (CUHK03, Market 1501, DukeMTMC-reID and MSMTI7) and state-of-the-art P-RID baselines but also guaranteed by the provided in-depth theoretical analyses.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Face recognition System with Feature Fusion for Rehabilitation Robots in Healthcare

Face Recognition System with Feature Fusion for Rehabilitati...

引用

International conference on computer and Communications (ICCC)

作者： Amna Bhutto Linsen Xu Ammara Sattar Hefei Institute of physical science Chinese Academy of sciences Hefei China / P. R. China University of Science and Technology of China Hefei China/ P. R. China Mechatronic Engineering Hohai University China Harbin Engineering University Harbin China

ISBN: (纸本)9781665409513

Face recognition is a research problem across multiple disciplines such as computer vision, pattern recognition, artificial intelligence, psychology, healthcare etc. At present, the rehabilitation centers in hospitals are dependent on the nursing staff with no implementation of rehabilitation automation. In this study of face detection, a facial expression recognition system was developed which can be useful for robots of rehabilitation nursing beds. this article mainly researches two aspects: face image feature extraction and classifier design. Since many low-resolution face images are often encountered in actual environments (such as surveillance), if you use traditional methods to directly extract image features, the results are often not satisfactory. For the influence of face recognition results, this paper proposes a feature fusion extraction method based on KNN with LDA(Fisherfaces) and PCA (eigenfaces). First, the original image (low resolution) is decomposed into three different resolution images, and then the three images are used as the basis for the position to extract facial features, then LDA and PCA are used to perform preliminary analysis to obtain reduced dimensional reduction features. Finally use the K-nearest neighbor classifier to perform classification prediction. Study compares KNN-LDA with KNN-PCA with different distances of KNN algorithm.

关键词： Image resolution Face recognition Surveillance Medical services Rehabilitation robotics Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

AI Improving the Lives of Physically Disabled 1

引用

12th International conference on Soft Computing and pattern recognition, SoCPaR 2020 and 16th International conference on Information Assurance and Security, IAS 2020

作者： Madaan, Hemshree Gupta, Shubham Bharati Vidyapeeth’s College of Engineering New Delhi110063 India

ISBN: (数字)9783030736897

ISBN: (纸本)9783030736880

Physical disability is one of the significant concerns that hamper individuals to access the web easily. Most of the physically disabled people cannot use technology because of the limitation of accessibility tools and techniques. It is required that the websites should be made compliant with the requirements of every citizen in a country;that’s why they should cater to the needs of the differently-abled citizens as well. Features have to be introduced in the websites so that they are easy to use, readily accessible, understandable, and convenient to everyone including best practices/standards and global innovation techniques. At times, accessibility is confused with providing solutions to disabled people, but the fact is accessibility is not only for differently-abled people, but it’s also there for everyone. the matter is every person needs accessibility and uses it when in need. © 2021, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

I-MMCCN: Improved MMCCN for RGB-T Crowd Counting of Drone Images 7

I-MMCCN: Improved MMCCN for RGB-T Crowd Counting of Drone Im...

引用

7th IEEE International conference on Network Intelligence and Digital Content, IC-NIDC 2021

作者： Zhang, Binyu Du, Yunhao Zhao, Yanyun Wan, Junfeng Tong, Zhihang Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System and Network Culture

ISBN: (纸本)9781665405829

Crowd counting is a critical technique in many artificial intelligent applications, such as security monitoring and automatic transportation management. However, due to the variations in object scales, illumination and image quality, crowd counting from drone images is full of challenges. To fully delve the information hidden in the multi-modal RGB-T images shot by drones for crowd counting, we proposed a hard examples mining module and a novel Block Mean Absolute Error loss (BMAE) to improve Multi-Modal Crowd Counting Network (MMCCN). With the local structural supervision introduced by BMAE loss, the network can incorporate local spatial correlation within each block and focus on the local pattern of people. Besides, BMAE is more similar to the evaluation metrics. By combining our proposed hard example mining module and BMAE loss with MMCCN, we obtain our Improved MMCCN, named as I-MMCCN. Experiments on the DroneRGBT dataset verify the effectiveness of our I-MMCCN. It achieves 1.01 MAE and 1.48 RMSE lower than MMCCN on DroneRGBT validation set. © 2021 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Performance Evaluation of Loss Functions for Deep Face recognition 7th

A Performance Evaluation of Loss Functions for Deep Face Rec...

引用

7th National conference on computer vision, pattern recognition, Image Processing, and Graphics, NCVPRIPG 2019

作者： Srivastava, Yash Murali, Vaishnav Dubey, Shiv Ram Computer Vision Group Indian Institute of Information Technology Chittor Sri CityA.P. India

ISBN: (纸本)9789811586965

Face recognition is one of the most widely publicized feature in the devices today and hence represents an important problem that should be studied with the utmost priority. As per the recent trends, the Convolutional Neural Network (CNN) based approaches are highly successful in many tasks of computer vision including face recognition. the loss function is used on the top of CNN to judge the goodness of any network. In this paper, we present a performance comparison of different loss functions such as Cross-Entropy, Angular Softmax, Additive-Margin Softmax, ArcFace and Marginal Loss for face recognition. the experiments are conducted with two CNN architectures namely, ResNet and MobileNet. Two widely used face datasets namely, CASIA-Webface and MS-Celeb-1M are used for the training and benchmark Labeled Faces in the Wild (LFW) face dataset is used for the testing. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

chinese Verb-Object Collocation Knowledge Graph Construction and Application 7th

Chinese Verb-Object Collocation Knowledge Graph Construction...

引用

7th International conference on Artificial Intelligence and Security, ICAIS 2021

作者： Zhao, Yuhang Li, Yi Shao, Yanqiu School of Information Science Beijing Language and Culture University Beijing100083 China Print Media Language Branch Beijing100083 China

ISBN: (纸本)9783030786144

Verb is the core of a sentence. It can not only reflect the syntactic structure and semantic framework of the whole sentence, but also restrict the nominal elements which co-exist with them. they play a significant role in sentence. Verb-Object Collocation has received more and more attention owing to its high frequency, complexity and flexibility of using. Domestic researches on verb object collocation mainly focus on automatic recognition and construction of corresponding collocation knowledge base. Nevertheless, most of the existing Verb-Object Collocation knowledge base lacks semantic information and classification information. thus, the application scenarios will be greatly limited. It cannot meet the semantic needs of natural language processing, either. In view of this situation, this paper deeply analyzes the semantic relationship of Verb-Object Collocation, and uses the related technology of knowledge graph to construct a Verb-Object Collocation Knowledge Graph, which obtains 40704 specific examples of Verb-Object Collocation and 20000 extraction templates of Verb-Object Collocation. At the same time, this paper constructs a Verb-Object Collocation Knowledge Graph to manage and maintain our knowledge through two parts: ontology layer and data layer. Finally, the effectiveness of the Verb-Object Collocation Knowledge Graph is verified on the task of entity recognition. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Gradient Analysis of Loss Function Based on System Balance 3rd

Gradient Analysis of Loss Function Based on System Balance

引用

3rd chinese conference on pattern recognition and computer vision (PRCV)

作者： Xia, Suman Cheng, Cheng Wang, Haoyuan Wang, Xuguang Chinese Acad Sci Suzhou Inst Nanotech & Nanobion SINANO Suzhou Peoples R China

ISBN: (纸本)9783030606350;9783030606367

In recent years, deep learning has been widely used in various fields of social life. the theoretical understanding on how it works also makes people curious. In this paper we treat features of sample as points in multidimensional space and gradients as stress between these points. In this system we can prove that the property "strong convexity" we defined is a sufficient condition for softmax loss function to converge to a good model. We also showed an example to estimate the capacity of features of fixed dimensions. During the proof we can see that the convergence process could be divided into two stages. In the first stage the strong convexity is formed. In the second stage this property stably guide the features to the ideal place.

关键词： Loss function Deep learning theory

来源：评论

学校读者我要写书评

暂无评论

NSRL: Named Entity recognition with Noisy Labels via Selective Review Learning 6th

NSRL: Named Entity Recognition with Noisy Labels via Selecti...

引用

6th China conference on Knowledge Graph and Semantic Computing (CCKS)

作者： Huang, Xiusheng Chen, Yubo Liu, Kang Xie, Yuantao Sun, Weijian Zhao, Jun Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Huawei Technol Co Ltd Shenzhen Peoples R China

ISBN: (纸本)9789811664717;9789811664700

Named entity recognition (NER) is a task of identifying both types and spans in the sentences. Previous works always assume that the NER datasets are correctly annotated. However, not all samples help with generalization. there are many noisy samples from a variety of sources (e.g., weak, pseudo, or distant annotations). Meanwhile existing methods are prone to cause error propagation in self-training process because of ignoring the overfitting, and becomes particularly challenging. In this paper, we propose a robust Selective Review Learning (NSRL) framework for NER task with noisy labels. Specifically, we design a Status Loss Function (SLF) which helps the model review the previous knowledge continuously when learning new knowledge, and prevents model from overfitting noisy samples in self-training process. In addition, we propose a novel Confidence Estimate Mechanism (CEM), which utilizes the difference between logit values to identify positive samples. Experiments on four distant supervision datasets and two real-world datasets show that the NSRL significantly outperforms previous methods.

关键词： Overfitting Self-training Status loss function Confidence estimation

来源：评论

学校读者我要写书评

暂无评论

Multi-view 3D Human Physique Dataset Construction For Robust Digital Human Modeling of Natural Scenes 22

Multi-view 3D Human Physique Dataset Construction For Robust...

引用

Proceedings of the 8th International conference on Communication and Information Processing

作者： Weitao Lin Jiguang Zhang Zhaohui Zhang Shibiao Xu Hao Xu Xiaopeng Zhang School of Artificial Intelligence University of Chinese Academy of Sciences China and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Shen Si Technology (PSYAI) Co. LTD China

ISBN: (纸本)9781450397100

A large number of diverse data sets are necessary for networks to predict human body parameters and reconstruct 3D body models from images. Due to the high cost of motion capture and body scanning, high precision pose and body shape parameters are difficult to obtain. Meanwhile, existing datasets cannot meet the requirements in terms of diversity, size, and data accuracy for practical applications. Inspired by the construction schemes of various datasets, we design and construct a large multi-view 3D human body reconstruction dataset (3DMVHumanBP) with more types of supervised data. By recording the different poses of 25 women and 25 men in a green screen laboratory from six perspectives, we constructed a complete large multi-view 3D body posture dataset containing 340, 000 images. It is worth noting that, we innovatively propose a body dimension prior to the constrained human parametric model construction strategy to provide high-precision ground truth parameters of the human body SMPL models. In addition, we also designed a dense UV data generation method based on human body boundary and mask mapping to provide high-quality dense UV data, which more closely fits the features of the human images. It makes up for the defect that few existing data sets can only provide sparse UV data. In the experiment, the effectiveness and advantages of the data set constructed by us in network training are verified. Compared with the training of existing datasets, the mainstream network models trained on our datasets can significantly improve their prediction accuracy and robustness, thanks to the monitoring data of multiple kinds of high-precision human model parameters provided by 3DMVHumanBP. We hope that the human body dataset construction scheme we designed can provide ideas for building large-scale high precision human body datasets in the future.

关键词： body modeling deep learning computer vision human dataset

来源：评论

学校读者我要写书评

暂无评论

Topic Knowledge Acquisition and Utilization for Machine Reading Comprehension in Social Media Domain 20

Topic Knowledge Acquisition and Utilization for Machine Read...

引用

20th China National conference on Computational Linguistics, CCL 2021

作者： Tian, Zhixing Zhang, Yuanzhe Liu, Kang Zhao, Jun National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9783030841850

In this paper, we focus on machine reading comprehension in social media. In this domain, one normally posts a message on the assumption that the readers have specific background knowledge. therefore, those messages are usually short and lacking in background information, which is different from the text in the other domain. thus, it is difficult for a machine to understand the messages comprehensively. Fortunately, a key nature of social media is clustering. A group of people tend to express their opinion or report news around one topic. Having realized this, we propose a novel method that utilizes the topic knowledge implied by the clustered messages to aid in the comprehension of those short messages. the experiments on TweetQA datasets demonstrate the effectiveness of our method. © 2021, Springer Nature Switzerland AG.

关键词： Social networking (online)

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197页 << < 56 57 58 59 60 61 62 63 64 65 > >>

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：