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

4,754 篇 会议
55 册 图书
11 篇 期刊文献

馆藏范围

4,820 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,162 篇 工学
- 2,818 篇 计算机科学与技术...
- 2,232 篇 软件工程
- 1,264 篇 信息与通信工程
- 759 篇 控制科学与工程
- 691 篇 生物工程
- 673 篇 光学工程
- 529 篇 电气工程
- 457 篇 生物医学工程（可授...
- 418 篇 电子科学与技术（可...
- 299 篇 网络空间安全
- 182 篇 安全科学与工程
- 163 篇 机械工程
- 160 篇 仪器科学与技术
- 159 篇 交通运输工程
- 152 篇 动力工程及工程热...
- 152 篇 化学工程与技术
- 142 篇 石油与天然气工程
1,644 篇 理学
- 709 篇 生物学
- 637 篇 物理学
- 605 篇 数学
- 242 篇 化学
- 181 篇 统计学（可授理学、...
827 篇 管理学
- 463 篇 图书情报与档案管...
- 443 篇 管理科学与工程(可...
- 119 篇 工商管理
436 篇 医学
- 366 篇 临床医学
- 249 篇 基础医学(可授医学...
- 214 篇 药学(可授医学、理...
- 108 篇 公共卫生与预防医...
125 篇 法学
- 109 篇 社会学
95 篇 农学
45 篇 经济学
44 篇 文学
33 篇 教育学
12 篇 军事学

主题

320 篇 image processing
312 篇 deep learning
234 篇 image segmentati...
191 篇 signal processin...
172 篇 image classifica...
167 篇 image enhancemen...
162 篇 computer vision
140 篇 image recognitio...
138 篇 convolutional ne...
136 篇 feature extracti...
125 篇 training
115 篇 machine learning
96 篇 computer applica...
83 篇 neural networks
83 篇 computational mo...
79 篇 visualization
78 篇 object detection
71 篇 natural language...
69 篇 semantics
68 篇 artificial intel...

机构

24 篇 chitkara univers...
17 篇 maharishi school...
15 篇 lovely professio...
15 篇 tianjin universi...
13 篇 university of ch...
12 篇 the islamic univ...
12 篇 beijing institut...
11 篇 school of comput...
11 篇 centre of interd...
10 篇 peng cheng labor...
10 篇 graphic era hill...
9 篇 national univers...
9 篇 sun yat-sen univ...
9 篇 school of comput...
9 篇 vivekananda glob...
9 篇 college of compu...
8 篇 harbin engineeri...
8 篇 school of comput...
8 篇 maharishi school...
8 篇 gla university d...

作者

13 篇 chauhan rahul
11 篇 yang yang
10 篇 anand vatsala
8 篇 kukreja vinay
8 篇 gupta rupesh
7 篇 luo xiaonan
7 篇 zhao yang
6 篇 bin wang
6 篇 pei jihong
6 篇 kumar ankit
6 篇 choudhury tanupr...
6 篇 zhu ce
6 篇 ce zhu
6 篇 kumar gaurav
6 篇 bing li
6 篇 li wei
6 篇 shin seokjoo
5 篇 gill kanwarparta...
5 篇 zhiguo cao
5 篇 nagaraj p.

语言

4,710 篇 英文
109 篇 其他
21 篇 中文
1 篇 土耳其文

检索条件"任意字段=2023 IEEE International Conference on Image Processing and Computer Applications, ICIPCA 2023"

共 4820 条记录，以下是4281-4290 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：

Perceptual Quality Assessment for Video Frame Interpolation

Perceptual Quality Assessment for Video Frame Interpolation

引用

ieee Visual Communications and image processing (VCIP)

作者： Jinliang Han Xiongkuo Min Yixuan Gao Jun Jia Lei Sun Zuowei Cao Yonglin Luo Guangtao Zhai Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Tencent China

The quality of frames is significant for both research and application of video frame interpolation (VFI). In recent VFI studies, the methods of full-reference image quality assessment have generally been used to evaluate the quality of VFI frames. However, high frame rate reference videos, necessities for the full-reference methods, are difficult to obtain in most applications of VFI. To evaluate the quality of VFI frames without reference videos, a no-reference perceptual quality assessment method is proposed in this paper. This method is more compatible with VFI application and the evaluation scores from it are consistent with human subjective opinions. A new quality assessment dataset for VFI was constructed through subjective experiments firstly, to assess the opinion scores of interpolated frames. The dataset was created from triplets of frames extracted from high-quality videos using 9 state-of-the-art VFI algorithms. The proposed method evaluates the perceptual coherence of frames incorporating the original pair of VFI inputs. Specifically, the method applies a triplet network architecture, including three parallel feature pipelines, to extract the deep perceptual features of the interpolated frame as well as the original pair of frames. Coherence similarities of the two-way parallel features are jointly calculated and optimized as a perceptual metric. In the experiments, both full-reference and no-reference quality assessment methods were tested on the new quality dataset. The results show that the proposed method achieves the best performance among all compared quality assessment methods on the dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on a Modified MMMU-BA Framework for Multimodal Sentiment Analysis

Research on a Modified MMMU-BA Framework for Multimodal Sent...

引用

Advances in Electrical Engineering and computer applications( AEECA), 2020 ieee international conference on

作者： Yanrong Zhang Yun Zou Harbin University of Commerce Harbin China Heilongjiang Key Laboratory of Electronic Commerce and Information Processing Harbin China

In multimodal sentiment analysis, the same attention mechanism is usually used to capture features at the same semantic level without considering the differences in intermodal interactions for sentiment categorization, which leads to problems such as insufficient inter-modal fusion feature extraction. In order to address the problem, this paper proposes a new improvement scheme for the MMMU-BA (Multi-Modal Multi-Utterance-Bi-Modal Attention) model, in which the new modal features formed by forward and backward splicing of the two original modal features are used to replace the original modal features that were originally incoming to the bi-modal attention mechanism, which produces stronger bimodal features. stronger bimodal features. In addition, the original modal features are replaced with modal features that have gone through the self-attention mechanism, which enhances the model’s representational ability. The model is validated on the publicly available datasets CMU-MOSI (Multimodal Opinion-level Sentiment Intensity) dataset and CMU-MOSEI (CMU Multimodal Opinion Sentiment and Emotion Intensity) dataset, and the accuracy is improved by 0.57% and 0.32%, and the F1 is improved by 1.6% and 0.7%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

image-Feature Parallel Compression for Indoor Surveillance Video

Image-Feature Parallel Compression for Indoor Surveillance V...

引用

ieee Workshop on Multimedia Signal processing

作者： Yiang Meng Hongkui Wang Haibing Yin Li Yu Changcai Lai Guoxiang Wang Tiansong Li College of Communications Engineering Hangzhou Dianzi University Hangzhou China Collage of Communication Engineering Huazhong Uninversity of Science and Technology Wuhan China Collage of Business Lishui University Lishui China College of Computer and Information Science Chongqing Normal University Chongqing China

Intelligent applications such as metaverse built on IoT technology are usually inseparable from the collection of surveillance video data. Yet, how to effectively compress indoor surveillance video has always been a huge challenge for data transmission. In this paper, we propose an image-feature parallel compression framework for indoor surveillance video. In other words, the video is divided into images and features which are compressed separately. Specifically, according to the Mean-shift algorithm, the background image is generated, encoded and shared among frames. Based on a series of detection and matching algorithms, a human feature (HF) extractor is designed to extract a frontage body image, identity features, boundary features and structural features which are used for the generation of foreground body images. At the same time, body masks are generated in order to segment body areas from body images. Finally, with the guidance of body mask and boundary features, the body area covers the corresponding area of generated background image to reconstruct the video, and its quality is improved by a quality enhancement network. Experimental results show that the proposed compression scheme achieves coding gain up to 66.91% and 51.84% averagely compared with HEVC and VVC respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedded Zero-shot Learning Algorithm Based on Semantic Attributes

Embedded Zero-shot Learning Algorithm Based on Semantic Attr...

引用

Advances in Electrical Engineering and computer applications( AEECA), 2020 ieee international conference on

作者： Zhibin Zhen Huadong Sun Yinghui Liu Pengyi Zhang Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin University of Commerce Harbin China

Zero-shot learning is a technique capable of recognizing target categories even when labeled samples for these categories are completely absent. Traditional zero-shot learning methods based on embedding models usually have a low utilization rate of semantic attributes and exhibit a bias towards seen classes during testing. Addressing this, we propose an embedding-based ZSL method grounded on semantic attributes. This method uses a spatial attention mechanism during the construction of the semantic attribute embedding space, enabling the model to focus on more distinctive attribute features within the images. Consequently, it can utilize these distinctive features for similarity classification. Furthermore, a category calibration loss function is introduced to assign a greater weight to unseen classes and a lesser weight to seen classes, aiming to reduce the bias towards seen classes during testing. Extensive experiments were carried out on three mainstream ZSL benchmark datasets. Compared with some of the existing classical algorithms, our method demonstrated improved results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stable Implementation Of Voice Activity Detector using Zero-Phase Zero Frequency Resonator On FPGA

Stable Implementation Of Voice Activity Detector using Zero-...

引用

Real Time Communications at IIT (RTC), ieee international conference and Expo on

作者： Syed Abdul Jabbar Purva Barche Krishna Gurugubelli Syed Azeemuddin Anil Kumar Vuppala Speech processing Laboratory LTRC IIIT-H Hyderabad India CVEST and Department of Electrical and Computer Engineering IIIT-Hyderabad and The University of Mississippi Mississippi USA

Voice activity detection (VAD), is a signal processing technique used to determine whether a given speech signal contains voiced or unvoiced segments. VAD is used in various applications such as Speech Coding, Voice Controlled Systems, speech feature extraction, etc. For example, in Adaptive multi-rate (AMR) speech coding, VAD is used as an efficient way of coding different speech frames at different bit rates. In this paper, we implemented the application of a Zero-Phase Zero Frequency Resonator (ZP-ZFR) as VAD on hardware. ZP-ZFR is an Infinite Impulse Response (IIR) filter that offers the advantage of requiring a lower filter order, making it suitable for hardware implementation. The proposed system is implemented on the TIMIT database using the Nexys Video Artix-7 FPGA board. The hardware design is carried out using Vivado 2021.1, a popular tool for FPGA development. The Hardware Description Language (HDL) used for implementation is Verilog. The proposed system achieves good performance with low complexity. Therefore this work is implemented on hardware, which can be used in various applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved ECA-DenseNet Framework for Brain MRI image Classification

Improved ECA-DenseNet Framework for Brain MRI Image Classifi...

引用

ieee Signal processing and Communications applications (SIU)

作者： Halise Nur AYDIN Oktay YILDIZ Bilgisayar Mühendisliği Bölümü Gazi Üniversitesi Ankara Türkiye

Early diagnosis is very important in brain tumors. Although Magnetic Resonance (MRI) is widely used for brain tumor detection, it is difficult to detect the tumor manually. Therefore, computer-aided diagnosis systems have been frequently utilized in recent years. In this study, an Efficient Channel Attention-Dense Convolutional Network (ECA-DenseNet) framework is proposed to detect tumors in patients based on brain MRI images. While detecting the tumor, it is tried to determine which type of tumor is present in the patient. In the developed ECA-DenseNet structure, an ECA block has been added to the dense blocks. The ECA block aimed to discard unimportant information and thus reduce the computation time. The improved DenseNet model has been tested on an open-source dataset. The improved model is compared with DenseNet-121, DenseNet-169, DenseNet-201, and DenseNet-264. The experimental results show the improving model has better classification performance than the others. The accuracy of the proposed model was 95.07%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Eff-Large SNN: A Lightweight and Versatile Approach for One-Shot image Classification in Face Recognition

Eff-Large SNN: A Lightweight and Versatile Approach for One-...

引用

ieee international conference on Engineering Education: Innovative Practices and Future Trends (AICERA)

作者： A. Lenin Fred Sam Nijin S Ajay Kumar H Computer Science and Engineering Mar Ephraem College of Engineering and Technology Elavuvilai Marthandam India

The field of face recognition has undergone a revolutionary transformation due to the introduction of deep learning algorithms, resulting in significant advancements in accuracy, robustness, and real-world applicability. However, the performance of face recognition systems is still influenced by challenging scenarios such as pose variation, expression, illumination, and occlusions. This paper presents a novel approach for one-shot image classification in face recognition, utilizing a modified Siamese Neural Network (SNN) to improve both speed and accuracy, even when the dataset is limited. The embedding layer of the SNN incorporates the EfficientNetV2L and Xception neural networks, which are then compared to determine the model's convergence. The experimental results were tested and demonstrated using our dataset and LFW dataset and concluded that the Eff-Large SNN is a lightweight and promising solution for one-shot image classification. The result from this Eff-Large SNN makes an accuracy of 91.95%. It outperforms SNN with Xception in terms of efficiency, accuracy, and versatility, making it suitable for a wide range of applications. This model is deployed in real-time CCTV surveillance for face recognition applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Epidemiological image Analysis: Insights, Perspectives, and Challenges

Epidemiological Image Analysis: Insights, Perspectives, and ...

引用

Optimization Techniques for Learning (ICOTL), international conference on

作者： Tatyana Ivanovska Markus Krüger Amro Daboul Department of Electrical Engineering Media and Computer Science East Bavarian Technical University of Applied Sciences Amberg-Weiden Amberg Germany Department of Prosthodontics Gerodontology and Biomaterials University Medicine Greifswald Greifswald Germany

The spotlight on large population-based studies is growing within the research community. Epidemiological studies, amassing extensive data through questionnaires and check-ups, often include imaging data like magnetic resonance imaging (MRI) or ultrasonography from numerous participants. This article offers an exploration of several recent epidemiological studies conducted in Germany, addressing not only the intriguing research tasks but also the multifaceted perspectives and challenges of analyzing image data. This includes potential enhancements in imaging technologies, machine learning applications for data analysis, and collaboration between different research disciplines. Key insights into the methodologies, algorithms, and techniques used for processing and interpreting complex imaging data are detailed. The potential of epidemiological image analysis to guide clinical practices and contribute to personalized medicine is also discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utility Prediction Performance of Finger image Quality Assessment Software

Utility Prediction Performance of Finger Image Quality Asses...

引用

international conference of the Biometrics Special Interest Group (BIOSIG)

作者： Olaf Henniger Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany

A biometric sample is the more utile for biometric recognition the greater the distance between the sample-specific non-mated and mated comparison score distributions. Finger image quality scores turn out to be only weakly correlated with the observed utility. This is worth investigating because finger image quality assessment software is widely used to predict the biometric utility of finger images in many public-sector applications. This paper shows that a weak correlation between predicted and observed utility does not matter if the quality scores are used to decide whether to discard or retain biometric samples for further processing. The important point is that useful samples are not mistakenly discarded or less useful samples are not mistakenly retained. This can be measured by quality-assessment false positive and false negative rates. In cost-benefit analyses, these metrics can be used to chose suitable quality-score thresholds for the use cases at hand.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SpOctA: A 3D Sparse Convolution Accelerator with Octree-Encoding-Based Map Search and Inherent Sparsity-Aware processing

SpOctA: A 3D Sparse Convolution Accelerator with Octree-Enco...

引用

ieee international conference on computer-Aided Design

作者： Dongxu Lyu Zhenyu Lil Yuzhou Chen Jinming Zhang Ningyi Xu Guanghui He School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Huixi Technology MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Point-cloud-based 3D perception has attracted great attention in various applications including robotics, autonomous driving and AR/VR. In particular, the 3D sparse convolution (SpConv) network has emerged as one of the most popular backbones due to its excellent performance. However, it poses severe challenges to real-time perception on general-purpose platforms, such as lengthy map search latency, high computation cost, and enormous memory footprint. In this paper, we propose SpOctA, a SpConv accelerator that enables high-speed and energy-efficient point cloud processing. SpOctA parallelizes the map search by utilizing algorithm-architecture co-optimization based on octree encoding, thereby achieving 8.8-21.2× search speedup. It also attenuates the heavy computational workload by exploiting inherent sparsity of each voxel, which eliminates computation redundancy and saves 44.4-79.1% processing latency. To optimize on-chip memory management, a SpConv-oriented non-uniform caching strategy is introduced to reduce external memory access energy by 57.6% on average. Implemented on a 40nm technology and extensively evaluated on representative benchmarks, SpOctA rivals the state-of-the-art SpConv accelerators by 1.1-6.9× speedup with 1.5-3.1× energy efficiency improvement,

关键词：

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482页 << < 425 426 427 428 429 430 431 432 433 434 > >>

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：