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

6,797 篇 会议
632 册 图书
126 篇 期刊文献

馆藏范围

7,554 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

3,891 篇 工学
- 3,084 篇 计算机科学与技术...
- 1,402 篇 软件工程
- 793 篇 电气工程
- 676 篇 信息与通信工程
- 501 篇 控制科学与工程
- 298 篇 生物工程
- 281 篇 生物医学工程（可授...
- 265 篇 机械工程
- 189 篇 光学工程
- 162 篇 电子科学与技术（可...
- 144 篇 仪器科学与技术
- 140 篇 化学工程与技术
- 59 篇 安全科学与工程
- 45 篇 材料科学与工程（可...
- 36 篇 交通运输工程
1,220 篇 理学
- 671 篇 数学
- 357 篇 物理学
- 333 篇 生物学
- 197 篇 统计学（可授理学、...
- 147 篇 化学
- 105 篇 系统科学
553 篇 管理学
- 314 篇 管理科学与工程(可...
- 255 篇 图书情报与档案管...
- 59 篇 工商管理
273 篇 医学
- 230 篇 临床医学
- 109 篇 基础医学(可授医学...
- 75 篇 药学(可授医学、理...
66 篇 法学
- 62 篇 社会学
51 篇 艺术学
- 49 篇 设计学（可授艺术学...
42 篇 农学
- 39 篇 作物学
21 篇 教育学
19 篇 文学
17 篇 经济学
5 篇 军事学

主题

3,153 篇 pattern recognit...
537 篇 feature extracti...
434 篇 artificial intel...
385 篇 neural networks
295 篇 data mining
282 篇 machine learning
233 篇 face recognition
224 篇 pattern matching
216 篇 support vector m...
203 篇 image segmentati...
195 篇 computer imaging...
194 篇 pattern classifi...
183 篇 computer science
182 篇 local binary pat...
172 篇 computational mo...
152 篇 training
147 篇 computer vision
145 篇 testing
141 篇 humans
139 篇 accuracy

机构

40 篇 school of comput...
38 篇 national laborat...
25 篇 institute of ima...
24 篇 center for resea...
24 篇 computer vision ...
22 篇 institute of ima...
22 篇 university of ch...
21 篇 department of co...
20 篇 indian statistic...
19 篇 national laborat...
19 篇 institute of com...
16 篇 tongji universit...
16 篇 chinese academy ...
15 篇 institute for pa...
14 篇 national center ...
14 篇 chinese acad sci...
14 篇 częstochowa univ...
13 篇 agh university o...
13 篇 school of electr...
12 篇 indian stat inst...

作者

35 篇 yang jie
31 篇 de-shuang huang
25 篇 tieniu tan
23 篇 umapada pal
19 篇 ryszard tadeusie...
19 篇 liang wang
18 篇 ajith abraham
17 篇 marcin korytkows...
17 篇 lu hanqing
17 篇 jacek m. zurada
17 篇 leszek rutkowski
16 篇 jie yang
16 篇 zhenan sun
16 篇 shamsuddin siti ...
16 篇 pal umapada
15 篇 wang da-han
15 篇 chew lim tan
15 篇 rafał scherer
14 篇 xu changsheng
14 篇 lotfi a. zadeh

语言

7,273 篇 英文
216 篇 其他
81 篇 中文

检索条件"任意字段=International Conference on Soft Computing and Pattern Recognition"

共 7556 条记录，以下是611-620 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：

Enhancing 3D Referential Grounding by Learning Coarse Spatial Relationships 27th

Enhancing 3D Referential Grounding by Learning Coarse Spati...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Joshi, Soham Tripathi, Aditay Gopalakrishnan, Viswanath Chakraborty, Anirban International Institute of Information Technology Bangalore India Indian Institute of Science Bengaluru India

ISBN: (纸本)9783031781124

Large-scale pre-training is commonly used in 2D referential grounding tasks owing to the easy availability of a large number of image-text pairs with corresponding bounding box annotations. However, for 3D referential grounding, the unavailability of high-quality 3D scene-text pairs with annotations poses a significant challenge. To address this issue, we leverage the large corpus of 3D scenes with bounding box annotations of object instances and design an automated strategy to synthesize scene-text data for pre-training by utilising the coarse spatial relationships between the objects in the scene without any human supervision. The proposed strategy first clusters the 3D bounding boxes and then uses these clusters to create pairwise and triplet relations between the objects in the 3D scene. We achieved improved results consistently across various top-performing methods in 3D referential grounding, when the proposed pre-training strategy is deployed. In addition to pre-training with the samples containing coarse spatial relations, we also encode semantic relationships between the bounding boxes conditioned on the language utterance, using a compatibility measure between the box features and the language utterance. To evaluate the performance of our proposed techniques, we conduct experiments on large-scale publicly available datasets, namely ScanRefer and ReferIt3D (SR3D and NR3D). Our proposed techniques can be seamlessly integrated with any off-the-shelf 3D referential grounding method. Specifically, when integrated with BUTD-DETR, we observed notable improvements of 2.2% and 1% in performance on the SR3D and NR3D datasets, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Abundant Semantic Information Module for Object Detection 2

Abundant Semantic Information Module for Object Detection

引用

2nd international conference on Algorithms, High Performance computing and Artificial Intelligence, AHPCAI 2022

作者： Wu, Taida Li, Qishen Li, Qiufeng Gao, Jun School of Information Engineering Nanchang Hangkong University Jiangxi Nanchang China School of Software Nanchang Hangkong University Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China Jiangxi Nanchang China

ISBN: (纸本)9798350334784

Nowadays, with the high-speed iteration of convolution neural network, the efficient object detector emerges one after another. As an important branch of computer vision, object detection aims to detect where and what the object is. However, nowadays, many detector cannot extract abundant semantic information to discriminate the location and size of the objects, resulting in poor performance of the network. In this paper, a new module is proposed, named Abundant Semantic Information Module (ASIM), to enrich and expand the semantic information of the object with more and larger receptive fields. In ASIM, we blend the extracted feature maps to different degrees with different blending factors and fuse them so that all object information is given full attention. Compared to the baseline method, a wealth of experiments show that our module has achieved a significant performance improvement. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Computation Caching in Mobile Convolutional Neural Network Inference

Computation Caching in Mobile Convolutional Neural Network I...

引用

IEEE international conference on Performance, computing and Communications (IPCCC)

作者： James Mariani Li Xiao Department of Computer Science Michigan State University

ISBN: (数字)9798350367942

ISBN: (纸本)9798350367959

Computer vision on smartphones is commonly achieved through the use of convolutional neural networks (CNNs). CNNs offer accurate image recognition, but struggle with latency when run with resource constraints. Current work in mobile CNNs aim to improve the latency on mobile devices through techniques such as quantization, model compression, early-exit, caching, etc. While these methods can improve the overall latency of image recognition, they also sacrifice significant accuracy. This problem is compounded by the wide range of pre-trained CNNs that have been released over the past decade. Many of these useful CNNs were developed before innovations that improved the efficiency of CNNs. Anyone attempting to use a CNN trained many years ago may be out of *** this paper, we introduce a computation caching scheme paired with early-exit strategies to improve the latency of CNNs on smartphones. Our system has both offline and online components. The offline system is used to find patterns in CNN execution, which are stored on the device. The online component reviews the current state of a CNN execution, determines if it matches a saved pattern, and can choose to forgo the full CNN execution and return a classification immediately. This system improves the speed of image recognition on any smartphone. It also requires no modification to the CNN, and no CNN training, meaning that it can be applied to any CNN that you can find, including many developed years ago. Our system achieves an average latency reduction of 17% while maintaining strong accuracy.

关键词： Training Technological innovation Computer vision Image recognition Accuracy Quantization (signal) Reviews Convolutional neural networks Smart phones pattern matching

来源：评论

学校读者我要写书评

暂无评论

引用

13th international Joint conference on Computational Intelligence (IJCCI) / 13th international conference on Evolutionary Computation Theory and Applications (ECTA)

作者： Baldini, Luca Martino, Alessio Rizzi, Antonello Univ Roma La Sapienza Dept Informat Engn Elect & Telecommun Via Eudossiana 18 I-00184 Rome Italy Italian Natl Res Council Inst Cognit Sci & Technol ISTC CNR Via San Martino della Battaglia 44 I-00185 Rome Italy LUISS Univ Dept Business & Management Viale Romania 32 I-00197 Rome Italy

ISBN: (纸本)9789897585340

Graph embedding is an established and popular approach when designing graph-based pattern recognition systems. Amongst the several strategies, in the last ten years, Granular computing emerged as a promising framework for structural pattern recognition. In the late 2000's, symbolic histograms have been proposed as the driving force in order to perform the graph embedding procedure by counting the number of times each granule of information appears in the graph to be embedded Similarly to a bag-of-words representation of a text corpora, symbolic histograms have been originally conceived as integer-valued vectorial representation of the graphs. In this paper, we propose six 'relaxed' versions of symbolic histograms, where the proper dissimilarity values between the information granules and the constituent parts of the graph to be embedded are taken into account, information which is discarded in the original symbolic histogram formulation due to the hard-limited nature of the counting procedure. Experimental results on six open-access datasets of fully-labelled graphs show comparable performance in terms of classification accuracy with respect to the original symbolic histograms (average accuracy shift ranging from -7% to +2%), counterbalanced by a great improvement in terms of number of resulting information granules, hence number of features in the embedding space (up to 75% less features, on average).

关键词： Structural pattern recognition Supervised Learning Embedding Spaces Granular computing Graph Edit Distances Graph Embedding

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Machine Learning for Advanced pattern recognition in Biometric Security Systems

Blockchain and Machine Learning for Advanced Pattern Recogni...

引用

international conference on Contemporary computing and Informatics (IC3I)

作者： K Mayuri B S Smitha Ginni Nijhawan Bolleddu Devananda Rao Shubhi Gupta Ali Albawi Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad Telangana India New Horizon College of Engineering Bangalore India Lovely Professional University Phagwara Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India Amity School of Engineering Technology Amity University Greater Noida Uttar Pradesh India Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

Blockchain and machine learning allow biometric security systems to recognize complex patterns. This study analyzes how two unique technologies may improve fingerprint system safety and reliability. To demonstrate blockchain and machine learning in biometrics. The main reason for this study is that fingerprint protection is becoming more important in today’s digital world. There needs to be strong name verification right away because there is more sensitive data and privacy issues. Traditional biometric systems have come a long way, but there are still problems with data security, privacy, and being able to grow. This study suggests important worries about how blockchain technology and machine learning might be able to improve pattern recognition, make security measures stricter, make data unchangeable, and reach the level of scalability needed for widespread use. Upon careful study of related approaches and works, biometric security could be improved by combining the decentralized and unchangeable record of blockchain with the pattern recognition abilities of machine learning. Ten important ways are looked at, and each one has its own pros and cons. A trio of CNNs, SVMs, and RNNs are used in the method we suggest. The suggested blockchain and machine learning fusion is shown to be better in a detailed analysis. The study ends with compared tables that show the parameters and performance evaluations of $\mathbf{1 0}$ similar systems.

关键词： Performance evaluation Data privacy Scalability Machine learning Transforms Fingerprint recognition Blockchains Security Reliability Protection

来源：评论

学校读者我要写书评

暂无评论

Swin Transformer with Multi-Scale Residual Attention for Semantic Segmentation of Remote Sensing Images 11

Swin Transformer with Multi-Scale Residual Attention for Sem...

引用

11th international conference on computing and pattern recognition, ICCPR 2022

作者： Lin, Yuanyang Wang, Da-Han Wu, Yun Zhu, Shunzhi Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9781450397056

Semantic segmentation of remote sensing images usually faces the problems of unbalanced foreground-background, large variation of object scales, and significant similarity of different classes. The FCN-based fully convolutional encoder-decoder architecture seems to have become the standard for semantic segmentation, and this architecture is also prevalent in remote sensing images. However, because of the limitations of CNN, the encoder cannot obtain global contextual information, which is extraordinarily important to the semantic segmentation of remote sensing images. By contrast, in this paper, the CNN-based encoder is replaced by Swin Transformer to obtain rich global contextual information. Besides, for the CNN-based decoder, we propose a multi-level connection module (MLCM) to fuse high-level and low-level semantic information to help feature maps obtain more semantic information and use a multi-scale upsample module (MSUM) to join the upsampling process to recover the resolution of images better to get segmentation results preferably. The experimental results on the ISPRS Vaihingen and Potsdam datasets demonstrate the effectiveness of our proposed method. © 2022 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Intricacy of CNN and RL with Substantiation of CNN Model in Simulated Self-Driving Environment

Intricacy of CNN and RL with Substantiation of CNN Model in ...

引用

Cognitive computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), international conference on

作者： Trilok Kumar Saini Akanksha Maurya Devanshu Dhyani Anju Saini Defence Electronics Applications Laboratory DRDO Dehradun India Dept. of Computer Science and Engg. Graphic Era Deemed to be University Dehradun India Dept. of Mathematics Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Machine Learning (ML) has emerged as a technological revolution that has incarnated advancements across various domains. Incorporating machine learning in technology opens a new paradigm for technology innovation. The convolutional Neural Networks (CNNs) paradigm of machine learning technique has a remarkable capacity to automatically extract significant characteristics from inputs. The key attributes of CNN make it indispensable in disciplines like pattern recognition and computer vision. This paper explores the architecture and functioning of CNNs, emphasizing their unique attributes which contribute to their superior performance in complex tasks. Building on the foundation of CNNs, the study also explores Reinforcement Learning (RL), a technique that empowers agents to learn optimal policies through interaction with an environment. By implementing the CNN technique, this paper investigates the potential of the CNN model in autonomous systems, particularly in self-driving vehicles. A CNN model is employed to demonstrate the effectiveness of these techniques. The results highlight the model's ability and the improvements to accurately classify and predict outcomes, underscoring the practical applicability of CNNs in real-world scenarios.

关键词： Computer vision Technological innovation Computational modeling Biological system modeling Neural networks Reinforcement learning Predictive models pattern recognition Convolutional neural networks Accidents

来源：评论

学校读者我要写书评

暂无评论

Audio Encryption Using AES and Cellular Automata

Audio Encryption Using AES and Cellular Automata

引用

international conference on computing and Networking Technology (ICCNT)

作者： Amireddy Shashank Reddy Dishan Narsimhachari Achar Madithilveedu Sheethal Mol Niharika Panda Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Securing digital audio data during any transmission or storage is essential for ensuring privacy and confidentiality. Traditional encryption techniques like Advanced Encryption Standard (AES) offer high security, but they might be vulnerable to attacks that exploit encrypted data patterns. Cellular automata, on the other hand, exhibit complex and challenging behavior, making them attractive for introducing additional layers of security in encryption schemes. However, integrating these techniques effectively remains a challenge. This paper addresses this gap by proposing a novel audio encryption system that combines the features of AES and cellular automata. A pseudo-random number sequence produced by Rule 30, a chaotic cellular automaton rule, is XOR-ed with the AES-encrypted audio data. This disrupts potential pattern recognition attempts, significantly enhancing the overall security of the encryption process. The system operates on WAV format audio files and ensures the confidentiality and integrity of the data by preventing unauthorized access and manipulation. We evaluate the effectiveness of our approach by comparing the characteristics of original and encrypted audio files. The results demonstrate significant alterations in the audio data, rendering it unintelligible without the decryption key. Additionally, the system utilizes the well-established AES algorithm, maintaining efficiency during encryption and decryption. This system defeats other methods in terms of security, complexity, and computational efficiency making this a reliable and efficient method for securing audio data transmission and storage where audio privacy is essential.

关键词： Data privacy Automata Transforms Rendering (computer graphics) Encryption pattern recognition Computational efficiency Reliability Data communication Standards

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Vietnamese Speech recognition Platforms 21

Evaluation of Vietnamese Speech Recognition Platforms

引用

5th international conference on Machine Learning and soft computing, ICMLSC 2021

作者： Diep, Hai Thanh Nguyen, Thi-My-Thanh Le, Bich Ngoc Dao, Quy Xuan Eastern International University Viet Nam

ISBN: (纸本)9781450387613

The purpose of this paper is to evaluate the performance of Vietnamese speech recognition systems provided by top Vietnamese companies such as Vais, Vtcc, Fpt, and Google. This paper presents the results in applying Vietnamese automatic speech recognition systems in news, interview, and music domains. We use recorded audios as inputs to compare the performance of Vietnamese automatic speech recognition systems by calculating Word Error Rate. Vais and Viettel obtain good results in news and interview domains while Google has good results in the music domain. The results demonstrated that all the providers Vais, Viettel, Google, and Fpt achieve good results but Vais is more dominant. © 2021 Association for computing Machinery. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Language-agnostic speech anger identification 44

Language-agnostic speech anger identification

引用

44th international conference on Telecommunications and Signal Processing (TSP)

作者： Saitta, Alessandra Ntalampiras, Stavros Univ Milan Dept Comp Sci Milan Italy

ISBN: (纸本)9781665429337

Following the constantly increasing adoption of affective computing based solutions, this paper investigates the feasibility of multilingual anger identification. To this end, we formed such a corpus by suitably combining seven different datasets representing five different languages, i.e. English, German, Italian, Urdu, and Persian. After analyzing the diverse characteristics of the datasets, we designed four classification algorithms, namely Support Vector Machine, Decision Tree-based Bagging scheme, Convolutional Neural Network, and Convolutional Recurrent Neural Network. Such classification mechanisms are trained on appropriate features extracted from time and/or frequency domains, while speech data have been balanced considering every diverse characteristic incorporated in the datasets (language, sex, acted, etc.). Our findings render multilingual anger identification feasible since the proposed audio pattern recognition methodology based on Mel-spectrograms and CRNN achieved quite satisfactory identification rates.

关键词： speech emotion recognition multilingual emotion recognition audio pattern recognition deep learning

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 << < 58 59 60 61 62 63 64 65 66 67 > >>

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：