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

18,700 篇 会议
1,406 篇 期刊文献
713 册 图书
59 篇 学位论文
1 篇 科技报告

馆藏范围

20,880 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

12,292 篇 工学
- 9,562 篇 计算机科学与技术...
- 4,627 篇 软件工程
- 3,225 篇 电气工程
- 2,846 篇 信息与通信工程
- 1,588 篇 生物工程
- 1,409 篇 控制科学与工程
- 1,206 篇 光学工程
- 1,141 篇 生物医学工程（可授...
- 710 篇 电子科学与技术（可...
- 548 篇 机械工程
- 431 篇 仪器科学与技术
- 298 篇 化学工程与技术
- 296 篇 材料科学与工程（可...
- 240 篇 网络空间安全
- 237 篇 安全科学与工程
- 220 篇 动力工程及工程热...
4,759 篇 理学
- 2,312 篇 物理学
- 1,759 篇 生物学
- 1,435 篇 数学
- 446 篇 统计学（可授理学、...
- 372 篇 化学
- 245 篇 系统科学
1,815 篇 医学
- 1,551 篇 临床医学
- 598 篇 基础医学(可授医学...
- 363 篇 药学(可授医学、理...
1,573 篇 管理学
- 947 篇 管理科学与工程(可...
- 706 篇 图书情报与档案管...
- 240 篇 工商管理
216 篇 农学
- 193 篇 作物学
201 篇 教育学
- 195 篇 教育学
140 篇 法学
61 篇 经济学
42 篇 文学
25 篇 军事学
14 篇 艺术学
3 篇 哲学
2 篇 历史学

主题

3,530 篇 neural networks
2,894 篇 artificial neura...
2,442 篇 convolutional ne...
1,841 篇 deep learning
1,570 篇 feature extracti...
1,485 篇 image processing
1,428 篇 training
1,332 篇 artificial intel...
914 篇 image segmentati...
911 篇 accuracy
696 篇 machine learning
619 篇 deep neural netw...
604 篇 neurons
574 篇 computational mo...
461 篇 image recognitio...
451 篇 image classifica...
415 篇 computer archite...
413 篇 computer vision
402 篇 signal processin...
384 篇 object detection

机构

48 篇 chitkara univers...
27 篇 univ chinese aca...
23 篇 tsinghua univers...
20 篇 school of comput...
19 篇 university of el...
19 篇 university of ch...
18 篇 university of sc...
18 篇 poznan univ life...
18 篇 nanyang technolo...
17 篇 shanghai jiao to...
16 篇 xidian univ sch ...
15 篇 school of comput...
15 篇 school of electr...
14 篇 hendisli&#x011f
14 篇 tsinghua univ pe...
13 篇 tongji universit...
13 篇 institute of aut...
13 篇 school of comput...
13 篇 beijing institut...
12 篇 shanghai jiao to...

作者

19 篇 de-shuang huang
16 篇 ryszard tadeusie...
16 篇 marcin korytkows...
15 篇 jacek m. zurada
11 篇 madani kurosh
11 篇 li yang
11 篇 liu yang
11 篇 liu ying
11 篇 ngoc thanh nguye...
10 篇 wang lei
10 篇 wang jing
10 篇 jun wang
9 篇 li xin
9 篇 haijun zhang
9 篇 gill kanwarparta...
9 篇 tianyong hao
9 篇 jun zhang
9 篇 li li
9 篇 shuzhi sam ge
9 篇 kok wai wong

语言

19,066 篇 英文
1,472 篇 其他
242 篇 中文
174 篇 土耳其文
7 篇 德文
5 篇 西班牙文
4 篇 法文
3 篇 俄文
2 篇 葡萄牙文
1 篇 日文

检索条件"任意字段=Conference on Applications of Artificial Neural Networks in Image Processing"

共 20880 条记录，以下是4941-4950 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：

Quantum-Trained Convolutional neural Network for Deepfake Audio Detection

Quantum-Trained Convolutional Neural Network for Deepfake Au...

引用

Acoustics, Speech, and Signal processing Workshops (ICASSPW), IEEE International conference on

作者： Chu-Hsuan Abraham Lin Chen-Yu Liu Samuel Yen-Chi Chen Kuan-Cheng Chen Centre for Quantum Engineering Science and Technology (QuEST) Imperial College London London UK Department of Electrical and Electronic Engineering Imperial College London London UK Graduate Institute of Applied Physics National Taiwan University Taipei Taiwan Wells Fargo New York NY USA

ISBN: (数字)9798331519315

ISBN: (纸本)9798331519322

The rise of deepfake technologies has posed significant challenges to privacy, security, and information integrity, particularly in audio and multimedia content. This paper introduces a Quantum-Trained Convolutional neural Network (QT-CNN) framework designed to enhance the detection of deepfake audio, leveraging the computational power of quantum machine learning (QML). The QT-CNN employs a hybrid quantum-classical approach, integrating Quantum neural networks (QNNs) with classical neural architectures to optimize training efficiency while reducing the number of trainable parameters. Our method incorporates a novel quantum-to-classical parameter mapping that effectively utilizes quantum states to enhance the expressive power of the model, achieving up to 70% parameter reduction compared to classical models without compromising accuracy. Data pre-processing involved extracting essential audio features, label encoding, feature scaling, and constructing sequential datasets for robust model evaluation. Experimental results demonstrate that the QT-CNN achieves comparable performance to traditional CNNs, maintaining high accuracy during training and testing phases across varying configurations of QNN blocks. The QT framework’s ability to reduce computational overhead while maintaining performance underscores its potential for real-world applications in deepfake detection and other resource-constrained scenarios. This work highlights the practical benefits of integrating quantum computing into artificial intelligence, offering a scalable and efficient approach to advancing deepfake detection technologies.

关键词： Training Deepfakes Quantum computing Accuracy neural networks Signal processing Feature extraction Convolutional neural networks Speech processing Testing

来源：评论

学校读者我要写书评

暂无评论

The Method of Industrial Internet image Super-resolution Based on Transformer 16

The Method of Industrial Internet Image Super-resolution Bas...

引用

16th IEEE International conference on Signal processing (ICSP)

作者： Liu, Lin Yu, Yingjie Wang, Juncheng Jin, Yi Zeng, Yuqiao China Automot Technol & Res Ctr Co Ltd Automot Data China Tianjin Co Ltd Tianjin Peoples R China Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China

ISBN: (数字)9781665460569

ISBN: (纸本)9781665460569

As a fundamental task in the field of computer vision, super-resolution reconstruction has a wide range of applications on the industrial Internet. However, most of the existing super-resolution reconstruction methods are based on convolutional neural networks for feature extraction, which have the problems of low model representation efficiency and insufficient explanation of the extraction process, which limit the performance of the model in industrial Internet scenarios. In recent years, although transformers have been proposed to solve the above problems well and achieve good results in image classification tasks, there is still room for improvement in the adaptability of super-resolution reconstruction tasks. Therefore, in this paper, an improved transformer-based image super-resolution reconstruction model is designed to effectively improve the performance of the image super-resolution reconstruction model. Experiments show that the adaptation of the Transformer mechanism on the super-resolution reconstruction task in this paper can practically improve the performance of the model on public datasets and industrial Internet scenario datasets.

关键词： Super-resolution Reconstruction Transformer Technologies Industrial Internet

来源：评论

学校读者我要写书评

暂无评论

Paddy Yield Estimation by Identifying Disease Affected Region

Paddy Yield Estimation by Identifying Disease Affected Regio...

引用

International conference on Mobile networks and Wireless Communications (ICMNWC)

作者： Hugar, Sharanamma M. Waheed, Mohammed Abdul Sharnbasva Univ Dept CSE Kalaburagi India VTU CPGS RO Dept CSE Kalaburagi India

ISBN: (纸本)9780738146379

In the Indian economy, Agriculture is considered one of the strongest pillars. Agriculture sector contributes significantly in our country, and it provides employability to many people live in a rural area. In our work, various methods of image processing are utilized for detecting healthy or unhealthy paddy leaves. This paper aims to carry out image analysis & classification methods to detect paddy leaf diseases and classification. We have built a system using image processing for identifying spots in paddy images by applying segmentation techniques. This system mainly includes four components: pre-processing, segmentation to extract the infected region by adopting FCM and SLIC algorithm, Feature Extraction using statistical Gray-Level Co-Occurrence Matrix (GLCM) features, and color features are extracted using HSV planes. Finally, Classification is made by using an artificial neural network (ANN).

关键词： Fuzzy C Mean (FCM) Clustering Simple Linear Iterative Clustering (SLIC) Gray Level Co-Occurrence Matrix (GLCM) HSV Plane artificial neural Network (ANN)

来源：评论

学校读者我要写书评

暂无评论

Analysis and Application of Multispectral Data for Water Segmentation Using Machine Learning

Analysis and Application of Multispectral Data for Water ...

引用

International conference on Computer Vision and Machine Intelligence, CVMI 2022

作者： Gupta, Shubham Uma, D. Hebbar, R. PES University KA Bangaluru560085 India Regional Remote Sensing Centre–South ISRO KA Bengaluru560037 India

ISBN: (纸本)9789811978661

Monitoring water is a complex task due to its dynamic nature, added pollutants, and land build-up. The availability of high-resolution data by Sentinel-2 multispectral products makes implementing remote sensing applications feasible. However, overutilizing or underutilizing multispectral bands of the product can lead to inferior performance. In this work, we compare the performances of ten out of the thirteen bands available in a Sentinel-2 product for water segmentation using eight machine learning algorithms. We find that the shortwave-infrared bands (B11 and B12) are the most superior for segmenting water bodies. B11 achieves an overall accuracy of 71 % while B12 achieves 69 % across all algorithms on the test site. We also find that the Support Vector Machine (SVM) algorithm is the most favorable for single-band water segmentation. The SVM achieves an overall accuracy of 69 % across the tested bands over the given test site. Finally, to demonstrate the effectiveness of choosing the right amount of data, we use only B11 reflectance data to train an artificial neural network, BandNet. Even with a basic architecture, BandNet is proportionate to known architectures for semantic and water segmentation, achieving a 92.47 mIOU on the test site. BandNet requires only a fraction of the time and resources to train and run inference, making it suitable to be deployed on web applications to run and monitor water bodies in localized regions. Our codebase is available at https://***/IamShubhamGupto/BandNet. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Deepfake image and Video Detection Using Deep Learning Algorithms

Deepfake Image and Video Detection Using Deep Learning Algor...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International conference on

作者： Srivanth Srinivasan Nischitha P Akshita Chavan Mohana Artificial Intelligence & Machine Learning Engineering RV College of Engineering® Bengaluru India Computer Science & Engineering (Cyber Security) RV College of Engineering® Bengaluru India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Deep learning (DL) algorithms are swiftly finding applications in computer vision and natural language processing. Nonetheless, they can also be employed for creating convincing deepfakes, which are challenging to distinguish from reality. The advancements in image and video technology and tools, especially on social media platforms, potentially lead to misuse for malicious purposes like blackmail or defamation. To tackle this issue, several group of researchers tried upon spreading or creating awareness on real or fake data. The proposed approach involves combining Deepfake generation using GANs and Autoencoders with a Deepfake detection method. The aim of this initiative is exclusively to combat disinformation and online fraud for the welfare of the general population. Deepfakes, products of AI, have become increasingly realistic, rendering it nearly difficult to distinguish the content. Auto-encoders with sufficient time can achieve about 92 % accuracy. As the generator improves, the discriminator performance worsens as it struggles to differentiate real or fake data. A perfect generator results in 50% accuracy. With advancements in computational capacity and data availability, the proposed DDM (Deepfake Detection Model) has achieved greater accuracy rate of up to 92.3%.

关键词： Deep learning Deepfakes Accuracy Social networking (online) Streaming media Feature extraction Generators Convolutional neural networks artificial intelligence Research and development

来源：评论

学校读者我要写书评

暂无评论

Learn from Teachers: A Teacher Learner Yoga Pose Classification and Scoring Network 3

Learn from Teachers: A Teacher Learner Yoga Pose Classificat...

引用

2022 3rd International conference on Computer Information and Big Data applications, CIBDA 2022

作者： Shen, Xiaoli School of Artificial Intelligence Southeast University Jiangsu Nanjing211189 China

ISBN: (纸本)9783800758760

Nowadays, computer vision is more and more widely applied in fitness and healthcare. However, little research has been done on yoga in this area, even though Yoga is a very popular sport. To fill this gap, this paper proposes a teacher-learner convolutional network, namely TL-CNN model, to realize yoga pose classification and scoring. The TL-CNN model is a convolutional neural network designed based on the Siamese network. It consists of two neural networks with shared weights, namely Teacher-CNN and Leaner-CNN. Input an image pair, by calculating the cosine similarity of two embedded vector output of the Teacher-CNN and the Learner-CNN, the similarity score can be obtained. At the same time, the yoga pose classification result of the image inputting in Learner-CNN can be also obtained. In this paper, four classic yoga pose categories are selected as datasets. Satisfactory test results have been achieved in both Yoga pose scoring and classification tasks. More specifically, the classification accuracy rate reaches 1, the similarity score of the same class of pose pairs is greater than 0.99, and the similarity score of different class pose pairs is less than -0.2. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Reducing DNN inference latency using DRL 13

Reducing DNN inference latency using DRL

引用

13th International conference on Information and Communication Technology Convergence, ICTC 2022

作者： Kim, Suhwan Jung, Sehun Lee, Hyang-Won Konkuk University Dept. of Cse Seoul Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

With the development of artificial intelligence (AI) technology, many applications are providing AI services. The key part of these AI services is the Deep neural networks(DNNs) requiring a lot of computation. However, it is usually time-consuming to provide an inference process on end devices that lack resources. Because of these limitations, distributed computing, which can perform large amounts of calculations using the processing power of various computers connected to the Internet, is emerging. We develop how to efficiently distribute DNN inference jobs in distributed computing environments and quickly process large amounts of DNN computations. In this paper, we will introduce the learning method and the results of the Deep Reinforcement Learning(DRL) model to reduce end-to-end latency by observing the state of the distributed computing environment and scheduling the DNN job using DRL. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AdaBM: On-the-Fly Adaptive Bit Mapping for image Super-Resolution

AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resol...

引用

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Cheeun Hong Kyoung Mu Lee Dept. of ECE & ASRI IPAI Seoul National University Seoul Korea

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Although image super-resolution (SR) problem has ex-perienced unprecedented restoration accuracy with deep neural networks, it has yet limited versatile applications due to the substantial computational costs. Since differ-ent input images for SR face different restoration difficul-ties, adapting computational costs based on the input image, referred to as adaptive inference, has emerged as a promising solution to compress SR networks. Specifically, adapting the quantization bit-widths has successfully re-duced the inference and memory cost without sacrificing the accuracy. However, despite the benefits of the resul-tant adaptive network, existing works rely on time-intensive quantization-aware training with full access to the origi-nal training pairs to learn the appropriate bit allocation policies, which limits its ubiquitous usage. To this end, we introduce the first on-the-fly adaptive quantization frame-work that accelerates the processing time from hours to sec-onds. We formulate the bit allocation problem with only two bit mapping modules: one to map the input image to the image-wise bit adaptation factor and one to obtain the layer-wise adaptation factors. These bit mappings are cali-brated and fine-tuned using only a small number of calibration images. We achieve competitive performance with the previous adaptive quantization methods, while the processing time is accelerated by × 2000. Codes are available at https://***/Cheeun/AdaBM.

关键词： Training Quantization (signal) Accuracy Adaptive systems Superresolution Bit rate Pipelines

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural Network-Based Novel Framework for Ship Recognition in Poor Visibility Maritime Surveillance Videos

Convolutional Neural Network-Based Novel Framework for Ship ...

引用

image processing and Computer applications (ICIPCA), IEEE International conference on

作者： Haoxiang Gao Yingzheng Hong Shanghai Fire Research Institute of Ministry of Emergency Management SHFRI Shanghai China

Ship recognition is a central component of the information perception for smart ships. Traditionally, the ship recognition mission is completed by remote sensing or synthetic aperture radar (SAR) or manual calibration via maritime surveillance video. However, the difficulty arises in implementing the mission when it suffers the weather with a poor visibility. The recognition accuracy may deteriorate dramatically in such a hostile environment, especially in the heavy fog environment at sea when using conventional methods. In this case, we develop a novel framework for ship recognition based on a smart recognition system that relies on the dark channel defogging and the neural networks. First, a dark-channel defogging algorithm is utilized to remove the adverse impact of poor visibility on recognition. After that, three different neural networks are used to train the defogged images (Specifically: Faster-RCNN, SSD, YOLOv3). Finally, we present qualitative and quantitative analyses of three different neural network models. The results demonstrate the effectiveness of the proposed method in a hostile environment, especially in fog weather with poor visibility at sea.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video Compression and Action Recognition in Self-supervised Learning

Video Compression and Action Recognition in Self-supervised ...

引用

image processing, Electronics and Computers (IPEC), Asia-Pacific conference on

作者： Zongbo Hao Conghui Hao Kecheng He University of Electronic Science and Technology of China Sichuan China

ISBN: (数字)9798350374407

ISBN: (纸本)9798350374414

In computer vision, neural network models typically require a large amount of manually annotated images or video data for training. To reduce annotation costs, self-supervised learning has gained significant attention. This paper proposes a self-supervised learning-based method by introducing an auxiliary task involving spatiotemporal context in videos—extracting video keyframes—to guide self-supervised learning. The neural network learns video stream features by completing this task, thereby understanding the high-level semantics of the video. Additionally, this auxiliary task achieves video content redundancy reduction and video compression through keyframe extraction. To quantitatively evaluate the effectiveness of this method, the neural network is transferred to the domain of action recognition and experiments are conducted on the UCF101 dataset, achieving an accuracy of 66.2% with fewer parameters and training data. The validation of the effectiveness of this method as an auxiliary task for video spatiotemporal features contributes to a better understanding of video semantic features by neural networks and facilitates action recognition, thereby expanding the applications of self-supervised learning.

关键词： Training neural networks Semantics Redundancy Training data Self-supervised learning Streaming media Video compression Feature extraction Spatiotemporal phenomena

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：