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

15,040 篇 会议
619 册 图书
206 篇 期刊文献

馆藏范围

15,864 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

9,338 篇 工学
- 6,732 篇 计算机科学与技术...
- 3,142 篇 软件工程
- 3,114 篇 控制科学与工程
- 2,062 篇 电气工程
- 954 篇 信息与通信工程
- 862 篇 机械工程
- 817 篇 生物医学工程（可授...
- 646 篇 生物工程
- 483 篇 仪器科学与技术
- 446 篇 光学工程
- 317 篇 电子科学与技术（可...
- 247 篇 化学工程与技术
- 206 篇 力学（可授工学、理...
- 145 篇 材料科学与工程（可...
- 144 篇 土木工程
- 143 篇 安全科学与工程
- 131 篇 交通运输工程
2,667 篇 理学
- 1,538 篇 数学
- 754 篇 物理学
- 733 篇 生物学
- 656 篇 统计学（可授理学、...
- 256 篇 化学
- 231 篇 系统科学
1,416 篇 管理学
- 856 篇 管理科学与工程(可...
- 611 篇 图书情报与档案管...
- 312 篇 工商管理
982 篇 医学
- 866 篇 临床医学
- 373 篇 基础医学(可授医学...
- 226 篇 药学(可授医学、理...
227 篇 法学
- 213 篇 社会学
112 篇 经济学
92 篇 教育学
74 篇 农学
52 篇 艺术学
35 篇 文学
16 篇 军事学
1 篇 哲学

主题

1,490 篇 artificial intel...
1,407 篇 pattern recognit...
715 篇 task analysis
702 篇 feature extracti...
452 篇 robots
446 篇 data mining
386 篇 neural networks
384 篇 training
301 篇 algorithm design...
299 篇 stability analys...
291 篇 deep learning
275 篇 image segmentati...
273 篇 support vector m...
262 篇 pattern analysis
257 篇 pattern classifi...
241 篇 robot sensing sy...
235 篇 legged locomotio...
229 篇 accuracy
226 篇 machine learning
225 篇 conferences

机构

56 篇 university of ch...
53 篇 institute of art...
46 篇 school of artifi...
42 篇 univ chinese aca...
37 篇 univ chinese aca...
35 篇 shenzhen institu...
28 篇 college of artif...
27 篇 national laborat...
27 篇 chinese acad sci...
25 篇 centre for patte...
24 篇 chinese acad sci...
22 篇 institute for pa...
22 篇 institute of aut...
22 篇 harbin inst tech...
21 篇 shenzhen inst ar...
20 篇 xi'an university...
19 篇 concordia univ c...
18 篇 chinese univ hon...
17 篇 univ chinese aca...
17 篇 indian statistic...

作者

38 篇 nanning zheng
35 篇 c.y. suen
28 篇 sami haddadin
27 篇 wu xinyu
26 篇 li guanglin
25 篇 liu cheng-lin
24 篇 suen ching y.
22 篇 xinyu wu
22 篇 ryszard tadeusie...
20 篇 de-shuang huang
19 篇 shafait faisal
19 篇 marcin korytkows...
18 篇 daniela rus
17 篇 jacek m. zurada
17 篇 m. kamel
17 篇 anon
16 篇 napoli amedeo
16 篇 wang wei
16 篇 dengel andreas
15 篇 jianda han

语言

15,434 篇 英文
379 篇 其他
80 篇 中文
1 篇 西班牙文
1 篇 法文
1 篇 俄文

检索条件"任意字段=International Conference on Pattern Analysis and Intelligence Robotics"

共 15865 条记录，以下是4801-4810 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：

Empirical Evaluation of Video Surveillance based Crime and Anomaly Detection System using Hybrid Deep Learning Strategy

Empirical Evaluation of Video Surveillance based Crime and A...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), international conference on

作者： A. Kishore Kumar P. Suganthi Sakthi Saravanan. N Joel T Sathish Shanmugam Department of Robotics and Automation Sri Ramakrishna Engineering College Vattamalaipalayam Coimbatore Department of CSE Sri Sai Ram Institute of Technology Chennai Department of EEE S. A. Engineering College Chennai Department of ECE R.M.K. Engineering College Chennai Everi India Private Limited Chennai India

In the realm of urban safety and security, the development of efficient and accurate crime detection systems is of paramount importance. This study presents an empirical evaluation of a cutting-edge Video Surveillance-based Crime and Anomaly Detection System (CADS) that harnesses the power of Hybrid Deep Learning, integrating Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN). CADS has been meticulously designed to detect and analyze criminal activities and abnormal behaviors in real-time video surveillance data. It employs a hybrid approach that combines the capabilities of ANN for feature extraction and pattern recognition with the temporal analysis prowess of RNN for identifying sequential anomalies. Through rigorous empirical evaluation, CADS demonstrates remarkable performance in urban crime detection scenarios. The system excels in detecting both overt and subtle criminal activities, providing valuable insights for enhanced safety measures. Notable achievements include the recognition of suspicious behaviors such as crowd contraflow, prolonged parking lot scouting, and even direct assaults. This research delves into the intricate workings of CADS, elucidating its design and implementation in Python on a Windows platform. The proposed model represents a significant advancement in the field of crime and anomaly detection when compared to existing models. In rigorous comparative evaluations, the proposed model has demonstrated its superiority by consistently outclassing all existing models, achieving an impressive accuracy rate of 97.77%. By leveraging CADS, law enforcement agencies and urban security stakeholders can proactively respond to potential threats and anomalies, ultimately contributing to safer and more secure urban environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of Efficiency of YOLO (v5 and v8) Models to Detect Potholes and Traffic Signs on Indian Roads

Comparative Analysis of Efficiency of YOLO (v5 and v8) Model...

引用

6th international conference on Computational intelligence in pattern Recognition, CIPR 2024

作者： Kamjula, Chudamani Khuteta, Umangana Tripathy, B.K. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India

ISBN: (纸本)9789819780921

Indian roads are some of the most challenging to drive on, with high traffic volumes, diverse road conditions, and a wide range of vehicles. To address the safety concerns associated with driving on these roads;the detection of traffic signs and potholes can be done using YOLO algorithms. We can detect and classify an image using the various image classification or object detection models available. This chapter aims to conduct a comparative analysis between YOLOv5 and v8 to determine which yields the most accurate results. The YOLO model is a popular object detection model known for its accuracy and speed. The You Only Look Once (YOLO) algorithm can be used to give the driver precise and timely information about potholes and traffic signs, integrated into the advanced driver-assistance systems (ADAS) available in vehicles. The system’s development involves training YOLO algorithms with a large dataset of Indian roads and diverse traffic signs sourced from Kaggle and Roboflow. This initiative has the potential to mitigate accidents by alerting drivers to potential hazards and providing real-time information for informed decision-making while driving. The proposed research aims to enhance road safety in India. To be precise, we compare the effects of two YOLO algorithms, namely YOLOv5 and YOLOv8, and show that YOLOv5 outperforms YOLOv8 by taking suitable datasets and metrics for comparison. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Road and street markings

来源：评论

学校读者我要写书评

暂无评论

Dialogue Generation for Heterogeneous Graph Neural on Networks Incorporating External Knowledge 23

Dialogue Generation for Heterogeneous Graph Neural on Networ...

引用

Proceedings of the 2023 6th international conference on Artificial intelligence and pattern Recognition

作者： Wei Guan Shuaiqian Guo Li Ma Shaanxi provincial key laboratory of network data analysis and intelligent processing Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

In recent years, with the improvement of hardware computing power and the rapid development of deep learning theory, the field of dialogue generation has also entered the era of deep learning. However, because it is difficult to generate content-rich and recovery statements by learning semantics only from dialogue corpus, many models are prone to generate responses that are weakly scalable to the topic of the input dialogue or generic responses that lack knowledge information. To address the above issues, a Heterogeneous Graph Neural Network Incorporating External Knowledge Dialogue Generation Model (HEDG) is proposed. First, we build up the external knowledge into a knowledge graph, and find the relevant external knowledge in the knowledge graph according to the entities in the input conversation according to certain rules. This external knowledge and the historical conversation context are then used as inputs to the heterogeneous graph encoder, and the conversation content and the corresponding external knowledge are represented by a Heterogeneous Graph Neural Network (HGNN). Finally, a decoder with Transformer structure as the main body is used to generate a response that is relevant to the conversation context with some knowledge extension by taking the encoded heterogeneous graphical representation as input. The experimental results show that the model has higher relevance and diversity compared with existing comparison models, and can effectively integrate external knowledge.

关键词： Dialogue Generation External Knowledge Heterogeneous Graph Neural Network Knowledge Graph

来源：评论

学校读者我要写书评

暂无评论

Application study of oil pipe entity recognition combined with Deep Reinforcement Learning 23

Application study of oil pipe entity recognition combined wi...

引用

Proceedings of the 2023 6th international conference on Artificial intelligence and pattern Recognition

作者： Wei Guan Shijie Liu Li Ma Shaanxi provincial key laboratory of network data analysis and intelligent processing Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

Aiming at the problems of inaccurate extraction of entity feature information and mislabeling of recognition results in the construction of knowledge graphs in the field of oil pipe failure using traditional methods, this paper proposes a research method of BERT-BiLSTM-CRF named entity recognition combined with deep reinforcement learning. The method firstly uses the BERT (Bidirectional encoder representations from transformers) pre-training model to obtain the word vectors of the input sequence semantics; secondly, the trained word vectors are fed into the bi-directional long short- term memory network (BiLSTM) to further obtain contextual features and output the maximum probability sequence annotation results according to the labeling rules of conditional random fields (CRF) and sequence decoding ability; finally, the BERT-BiLSTM-CRF model is supplemented with the deep reinforcement learning-based labeling Finally, the BERT-BiLSTM-CRF-DRL model is added to the BERT-BiLSTM-CRF model to form the framework of named entity recognition model in oil pipe failure domain. The model is compared with other 2 named entity recognition models on a self-built oil pipe data-set, and the experimental results show that the accuracy, recall and F1 values of the model reach 90.5%, 92.7% and 91.9%, respectively, and the entity recognition is better than the other 2 models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion of Multiple Spatial Networks Derived from Complex-Valued fMRI Data via CNN Classification

Fusion of Multiple Spatial Networks Derived from Complex-Val...

引用

international Joint conference on Neural Networks (IJCNN)

作者： Niu, Yan-Wei Zhang, Chao-Ying Qiu, Yue Lin, Qiu-Hua Sui, Jing Calhoun, Vince D. Dalian Univ Technol Sch Informat & Commun Engn Dalian 116024 Peoples R China Univ Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Emory Univ Triinst Ctr Translat Res Neuroimaging & Data Sci Georgia State Univ Georgia Inst Technol Atlanta GA USA

ISBN: (纸本)9780738133669

Convolutional neural network (CNN) can achieve better classification by using independent component analysis (ICA) components derived from complex-valued fMRI data than from magnitude-only fMRI data due to incorporating additional phase information. However, thus far magnitude slices of only a single brain network (i.e. spatial component) has been used in the classification. This study aims to take advantages of multiple ICA components in providing rich information and to provide a conclusion for efficient multiple-component fusion. More precisely, we present three fusion approaches: 1) averaging multiple ICA components as inputs of a single-component CNN, 2) concatenating features of multiple single-component CNN, and 3) averaging predictive probabilities of multiple single-component CNN. We evaluate the proposed methods using resting-state fMRI data collected from 42 schizophrenia patients and 40 healthy controls. Experimental results show that all three fusion approaches can improve classification accuracy compared to the single-component CNN, and the first approach performs the best. No matter which fusion method is used, we reach the same conclusion that four-component fusion is sufficient to obtain satisfying performance, and two-component fusion yields higher improvement and better performance than the singlecomponent classification, especially when using components having good accuracy for single-component CNN classification.

关键词： Convolutional neural network (CNN) independent component analysis (ICA) complex-valued fMRI data multiple-component fusion schizophrenia

来源：评论

学校读者我要写书评

暂无评论

CAB-Net: Channel Attention Block Network for Pathological Image Cell Nucleus Segmentation 11th

CAB-Net: Channel Attention Block Network for Pathological Im...

引用

11th international conference on Image and Graphics, ICIG 2021

作者： Li, Meixuan Fan, Huijie Yang, Dawei School of Information Technology and Engineering Shenyang Ligong University Liaoning Shenyang110159 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China

ISBN: (纸本)9783030873578

In histopathological image analysis, cell nucleus segmentation plays an important role in the clinical analysis and diagnosis of cancer. However, due to the different morphology of cells, uneven staining and the existence of a large number of dense nuclei, it is still challenging to accurately segment the nucleus. In order to learn more specific key feature information during the training process, this paper proposed a network model called the CAB-Net that uses channel attention to enhance the learning of feature information on each channel. The network uses the channel attention mechanism to extract the key features in each channel, generates weights to judge the importance of the features, and then weights them into the original image. This aims to strengthen the extraction of key information, thereby generating a more characteristic feature map, and enabling the model to make more accurate judgments. We added a boundary smoothness constraint, in order to better identify cell nuclei with unclear boundaries and achieve more accurate cell nucleus segmentation. The experimental results show that the method in this paper achieves good performance on the cell segmentation data set. © 2021, Springer Nature Switzerland AG.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Counter-Misdirection in Behavior-based Multi-robot Teams **Research supported by the National Science Foundation under CNS EAGER grant #1848653.

Counter-Misdirection in Behavior-based Multi-robot Teams **R...

引用

IEEE international conference on intelligence and Safety for robotics (ISR)

作者： Shengkang Chen Ronald C. Arkin Electrical and Computer Engineering Interactive Computing Georgia Institute of Technology Atlanta GA USA

When teams of mobile robots are tasked with different goals in a competitive environment, misdirection and counter-misdirection can provide significant advantages. Researchers have studied different misdirection methods but the number of approaches on counter-misdirection for multi-robot systems is still limited. In this work, a novel counter-misdirection approach for behavior-based multi-robot teams is developed by deploying a new type of agent: counter-misdirection agents (CMAs). These agents can detect the misdirection process and “push back” the misdirected agents collaboratively to stop the misdirection process. This approach has been implemented not only in simulation for various conditions, but also on a physical robotic testbed to study its effectiveness. It shows that this approach can stop the misdirection process effectively with a sufficient number of CMAs. This novel counter-misdirection approach can potentially be applied to different competitive scenarios such as military and sports applications.

关键词： conferences Safety Multi-robot systems Mobile robots Task analysis Sports

来源：评论

学校读者我要写书评

暂无评论

Adaptive Scaling for Archival Table Structure Recognition 16th

Adaptive Scaling for Archival Table Structure Recognition

引用

16th IAPR international conference on Document analysis and Recognition (ICDAR)

作者： Li, Xiao-Hui Yin, Fei Zhang, Xu-Yao Liu, Cheng-Lin Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit 95 Zhongguancun East Rd Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing Peoples R China

ISBN: (纸本)9783030865498

Table detection and structure recognition from archival document images remain challenging due to diverse table structures, complex document layouts, degraded image qualities and inconsistent table scales. In this paper, we propose an instance segmentation based approach for archival table structure recognition which utilizes both foreground cell content and background ruling line information. To overcome the influence from inconsistent table scales, we design an adaptive image scaling method based on average cell size and density of ruling lines inside each document image. Different from previous multi-scale training and testing approaches which usually slow down the speed of the whole system, our adaptive scaling resizes each image to a single optimal size which can not only improve overall model performance but also reduce memory and computing overhead on average. Extensive experiments on cTDaR 2019 Archival dataset show that our method can outperform the baselines and achieve new state-of-the-art performance, which demonstrates the effectiveness and superiority of the proposed method.

关键词： Archival document Table detection Table structure recognition Adaptive scaling

来源：评论

学校读者我要写书评

暂无评论

32nd international conference on Database and Expert Systems Applications, DEXA 2021

32nd International Conference on Database and Expert Systems...

引用

32nd international conference on Database and Expert Systems Applications, DEXA 2021

ISBN: (纸本)9783030864712

The proceedings contain 68 papers. The special focus in this conference is on Database and Expert Systems Applications. The topics include: Sarcasm Detection for Japanese Text Using BERT and Emoji;Sigmalaw PBSA - A Deep Learning Model for Aspect-Based Sentiment analysis for the Legal Domain;BERT-Based Sentiment analysis: A Software Engineering Perspective;a Stochastic Block Model Based Approach to Detect Outliers in Networks;Medical-Based Text Classification Using FastText Features and CNN-LSTM Model;diversified pattern Mining on Large Graphs;EHUCM: An Efficient Algorithm for Mining High Utility Co-location patterns from Spatial Datasets with Feature-specific Utilities;BERT-Based Multi-Task Learning for Aspect-Based Opinion Mining;GPU-Accelerated Vertex Orbit Counting for 5-Vertex Subgraphs;subgroup Discovery with Consecutive Erosion on Discontinuous Intervals;efficient Discovery of Partial Periodic-Frequent patterns in Temporal Databases;database Framework for Supporting Retention Policies;internal Data Imputation in Data Warehouse Dimensions;purging Data from Backups by Encryption;improving Quality of Ensemble Technique for Categorical Data Clustering Using Granule Computing;Online Optimized Product Quantization for Dynamic Database Using SVD-Updating;querying Collections of Tree-Structured Records in the Presence of Within-Record Referential Constraints;Dealing with Plethoric Answers of SPARQL Queries;feature Selection and Software Defect Prediction by Different Ensemble Classifiers;traffic Flow Prediction Through the Fusion of Spatial-Temporal Data and Points of Interest;Fast SQL/Row pattern Recognition Query Processing Using Parallel Primitives on GPUs;predicting Student Performance in Experiential Education;log-Based Anomaly Detection with Multi-Head Scaled Dot-Product Attention Mechanism;enhancing Scan Matching Algorithms via Genetic Programming for Supporting Big Moving Objects Tracking and analysis in Emerging Environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fight Detection in Crowd Scenes Based on Deep Spatiotemporal Features 2

Fight Detection in Crowd Scenes Based on Deep Spatiotemporal...

引用

3rd international conference on Artificial intelligence, robotics and Control (AIRC)

作者： Almazroey, Alaa Atallah Jarraya, Salma Kammoun King Abdulaziz Univ Fac Comp & Informat Technol Comp Sci Dept Jeddah Saudi Arabia Univ Sfax MIR CL Lab Sfax Sfax Tunisia

ISBN: (纸本)9781450389266

Over the last few decades, remarkable growths of distributing surveillance cameras have been noticed in privet and public facilities. Therefore, with a growing demand for security and to ensure public safety. An intelligent automated approach is essential for on-spot violence and fight detection as it would save the time and cost of manual fight detection from monitor screens. In this research, we propose a supervised deep learning-based approach to detect fight actions from crowd video scenes. By extracting the keyframes from video frames using the cosine similarity algorithm, using them to compute optical flow values of the magnitudes, orientation and velocity. Afterward, using these values to construct four 2D templates, which are supplied to the pre-trained network to extract deep spatiotemporal features. Finally, applying the Neighborhood Component analysis (NCA) feature selection method, and the Vector Support Machine (SVM) classifier, to generate a model that able to identify fighting behavior from crowd video scenes. Three different public datasets, the Hockey dataset, Movies dataset and Violent-Flows dataset, were used to evaluate the proposed method. The efficiency of the proposed method outperformed other state-of-the-art methods in terms of accuracy and the required time for fight detection to be executed.

关键词： Deep Learning Fight Detection Keyframe Selection Neighborhood Component analysis Surveillance Videos

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 << < 477 478 479 480 481 482 483 484 485 486 > >>

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：