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

50,667 篇 会议
1,420 册 图书
1,040 篇 期刊文献
1 篇 学位论文

馆藏范围

53,125 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,959 篇 工学
- 24,945 篇 计算机科学与技术...
- 12,662 篇 软件工程
- 5,168 篇 光学工程
- 4,781 篇 电气工程
- 4,528 篇 信息与通信工程
- 4,271 篇 机械工程
- 4,075 篇 控制科学与工程
- 2,477 篇 生物工程
- 1,730 篇 生物医学工程（可授...
- 1,597 篇 仪器科学与技术
- 1,330 篇 电子科学与技术（可...
- 796 篇 化学工程与技术
- 724 篇 安全科学与工程
- 567 篇 交通运输工程
- 383 篇 建筑学
- 335 篇 土木工程
11,916 篇 理学
- 6,479 篇 物理学
- 5,450 篇 数学
- 2,763 篇 生物学
- 1,922 篇 统计学（可授理学、...
- 838 篇 化学
- 668 篇 系统科学
5,349 篇 医学
- 5,118 篇 临床医学
- 727 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,416 篇 管理学
- 1,991 篇 图书情报与档案管...
- 1,595 篇 管理科学与工程(可...
- 484 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
438 篇 法学
- 411 篇 社会学
298 篇 农学
202 篇 教育学
165 篇 经济学
70 篇 文学
49 篇 军事学

主题

17,437 篇 computer vision
9,033 篇 pattern recognit...
4,198 篇 training
3,834 篇 feature extracti...
3,136 篇 cameras
2,873 篇 computational mo...
2,791 篇 image segmentati...
2,623 篇 visualization
2,576 篇 shape
2,538 篇 face recognition
2,177 篇 robustness
2,125 篇 computer science
1,983 篇 object detection
1,960 篇 computer archite...
1,882 篇 layout
1,855 篇 object recogniti...
1,801 篇 three-dimensiona...
1,724 篇 neural networks
1,706 篇 humans
1,699 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
135 篇 national laborat...
105 篇 univ sci & techn...
104 篇 zhejiang univers...
103 篇 shanghai jiao to...
94 篇 university of sc...
94 篇 microsoft resear...
85 篇 zhejiang univ pe...
84 篇 shanghai ai lab ...
74 篇 school of comput...
69 篇 computer vision ...
68 篇 peking univ peop...
68 篇 chinese acad sci...
65 篇 chinese univ hon...
63 篇 institute of inf...
62 篇 google res mount...
61 篇 univ oxford oxfo...
59 篇 univ toronto on
57 篇 swiss fed inst t...

作者

92 篇 van gool luc
86 篇 umapada pal
77 篇 zhang lei
64 篇 lee seong-whan
50 篇 vittorio murino
42 篇 yang yi
34 篇 nassir navab
33 篇 ling haibin
33 篇 li xin
33 篇 jie yang
32 篇 liu yang
31 篇 escalera sergio
31 篇 loy chen change
30 篇 h. bischof
29 篇 zhou jie
29 篇 vasconcelos nuno
29 篇 jan-michael frah...
28 篇 blumenstein mich...
27 篇 jia yunde
27 篇 luo ping

语言

50,125 篇 英文
2,767 篇 其他
253 篇 中文
22 篇 土耳其文
4 篇 西班牙文
2 篇 日文
2 篇 葡萄牙文
2 篇 俄文

检索条件"任意字段=IEEE Conference on Computer Vision and Pattern Recognition"

共 53128 条记录，以下是4111-4120 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：

Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action recognition 22

Domain Generalization through Audio-Visual Relative Norm Ali...

引用

22nd ieee/CVF Winter conference on Applications of computer vision (WACV)

作者： Planamente, Mirco Plizzari, Chiara Alberti, Emanuele Caputo, Barbara Politecn Torino Turin Italy Ist Italiano Tecnol Genoa Italy CINI Consortium Turin Italy

ISBN: (纸本)9781665409155

First person action recognition is becoming an increasingly researched area thanks to the rising popularity of wearable cameras. This is bringing to light cross-domain issues that are yet to be addressed in this context. Indeed, the information extracted from learned representations suffers from an intrinsic "environmental bias". This strongly affects the ability to generalize to unseen scenarios, limiting the application of current methods to real settings where labeled data are not available during training. In this work, we introduce the first domain generalization approach for egocentric activity recognition, by proposing a new audiovisual loss, called Relative Norm Alignment loss. It rebalances the contributions from the two modalities during training, over different domains, by aligning their feature norm representations. Our approach leads to strong results in domain generalization on both EPIC-Kitchens-55 and EPIC-Kitchens-100, as demonstrated by extensive experiments, and can be extended to work also on domain adaptation settings with competitive results.

关键词： Training Visualization computer vision Measurement units Limiting Activity recognition Cameras

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Dataset and Study

NTIRE 2021 Challenge on Quality Enhancement of Compressed Vi...

引用

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

作者： Yang, Ren Timofte, Radu Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland

ISBN: (纸本)9781665448994

This paper introduces a novel dataset for video enhancement and studies the state-of-the-art methods of the NTIRE 2021 challenge on quality enhancement of compressed video. The challenge is the first NTIRE challenge in this direction, with three competitions, hundreds of participants and tens of proposed solutions. Our newly collected Large-scale Diverse Video (LDV) dataset is employed in the challenge. In our study, we analyze the solutions of the challenges and several representative methods from previous literature on the proposed LDV dataset. We find that the NTIRE 2021 challenge advances the state-of-theart of quality enhancement on compressed video.

关键词： computer vision Databases conferences Benchmark testing Solids pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Indian Sign Language recognition Using Video vision Transformer 3

Indian Sign Language Recognition Using Video Vision Transfor...

引用

3rd International conference for Advancement in Technology, ICONAT 2024

作者： Ojaswee Sreemathy, R. Turuk, Mousami Jagdale, Jayashree Anish, Mohammad Pune Institute of Computer Technology Department of E&TC Engineering Pune India Pune Institute of Computer Technology Department of Information Technology Pune India

ISBN: (纸本)9798350354171

Sign language is a way of communication that uses hand shapes, orientation, movements, and facial expressions to express instead of spoken words like normal language. Different regions have developed their own versions of sign language. In India, Indian sign language (ISL) is the primary mode of communication for more than 5 million speech or hearing impaired people. However, the knowledge of signing and understanding the ISL is only limited to the deaf community, which can make it hard to communicate with the people who don't understand the language. Thus, effective recognition of ISL gestures is vital for seamless interaction between these impaired people and the broader society. The rise of artificial intelligence and computer vision models has provided us with many effective tools to tackle this challenge. While there has been some progress in this field, most research has focused on static signs or American Sign Language, leaving video-based recognition for ISL largely unexplored. To bridge this gap, our paper proposes an approach that utilizes Video vision Transformer (ViViT) architecture for ISL recognition. We have experimented with different layers and different numbers of attention heads to get a model that works best for the assigned task. Our architecture gives an overall accuracy of 96.69% and a top-5 accuracy of 99.55% on the sign recognition task using our own created VISL-PICT dataset. © 2024 ieee.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Chatbotification for Web Information Systems: A pattern-based Approach 48

Chatbotification for Web Information Systems: A Pattern-base...

引用

48th Annual ieee International computers, Software, and Applications conference (COMPSAC) - Digital Development for a Better Future

作者： Liang, Yan-Cih Ma, Shang-Pin Lin, Chih-Ying Natl Taiwan Ocean Univ Dept Comp Sci & Engn Keelung Taiwan

ISBN: (纸本)9798350376975;9798350376968

With the exponential expansion of information on the internet, users are increasingly encountering challenges in locating the necessary information within an intricate web information system (WIS). Meanwhile, developers struggle to craft user interfaces that deliver optimal user experiences (UX) within complex web architectures. Chatbots, emerging as integral components within new WISs, serve as complementary elements to traditional graphical user interfaces (GUIs). However, the absence of established methods providing clear guidelines or practices for implementing Chatbots on an existing WIS remains a notable gap. This study aims to address this gap by proposing an approach that transforms existing web functionalities into conversational interfaces (i.e., Chatbot interfaces). We present a comprehensive step-by-step guideline and a set of patterns to facilitate the conversion, referred to as "Chatbotification." To validate the feasibility of our proposed approach, we implemented Chatbots1 using two distinct frameworks, Rasa and GPT. The conducted experimental results show that all participants also found that the Chatbots are easy to use and understandable, while it takes an average of a few interactions to complete a given task with the Chatbots.

关键词： Chatbot Web Information System (WIS) Intent recognition Design pattern Large Language Model (LLM)

来源：评论

学校读者我要写书评

暂无评论

Research on Machine vision Intelligent Detection System Based on Faster R-CNN 4

Research on Machine Vision Intelligent Detection System Base...

引用

4th ieee International conference on Data Science and computer Application, ICDSCA 2024

作者： Wang, Xueting Zeng, Fanshuo Song, Weizhao Zhang, Zhipeng He, Huitong Zhou, Zheyuan Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9798350368239

With the rapid development of artificial intelligence technology, visual inspection and image processing algorithms have been continuously improved in accuracy and efficiency, and intelligent inspection systems based on machine vision have been widely used in product quality control, defect detection and process monitoring. In this paper, a machine vision intelligent inspection system based on Faster Region-based Convolutional Network (Faster R-CNN) is proposed, which aims to improve the detection accuracy and efficiency. In this paper, the overall architecture of the system is introduced, including the image acquisition module, the data preprocessing module and the detection module based on Faster R-CNN. In the data preprocessing module, the Deep Convolution Generative Adversarial Networks (DCGAN) algorithm was proposed for image expansion generation, and high-resolution image samples that were basically consistent with the collected image datasets were obtained. Then, the Faster R-CNN model was optimized and adjusted for specific application scenarios, so that the average accuracy (mAP) of the model reached 78.23% and the FPS value reached 11.0. ©2024 ieee.

关键词： Faster R-CNN Image Processing image recognition Machine vision intelligent inspection system

来源：评论

学校读者我要写书评

暂无评论

Accurate Angle Detection of Rotated Rectangles Using Hybrid Architecture of Convolutional Neural Networks with Multi-Layer Perceptron and SVR 4

Accurate Angle Detection of Rotated Rectangles Using Hybrid ...

引用

4th International conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Ahmed, Nayeem Technische Universität Dresden Faculty of Electrical and Computer Engineering Dresden Germany

ISBN: (纸本)9798350353266

This study presents a novel approach for detecting the angles of the rotated rectangles precisely using the hybrid architecture of Convolutional Neural Networks (CNN) with Multi-Layer Perceptron (MLP) and Support Vector Regression (SVR). This work also shows the comparative assessment between the two hybrid models, CNN & MLP only and CNN & MLP along with the SVR for unrolling the angles of the rectangles. In the automated image analysis and pattern recognition domain, the complexity of rotated rectangles-especially in different orientations and scales-presents formidable challenges. Our study begins with the dataset comprised of 10000 images of rectangles with varying rotation angles and coordinates. Then, CNN, an effective model in the image analysis and computer vision field, effectively captures the spatial dependencies and characteristics of rotated rectangles from the raw images by extracting and learning the hierarchical feature representations. To further process the pieces of information, the MLP and SVR are used, giving the learning model more depth and improving its capacity to recognize complex patterns. Evaluation metrics such as MSE, RMSE, MAPE, MAE, and R2 determine the model's accuracy. This research enhances the fields of machine learning and image processing and also potentially benefits robotics, com-puter vision, and remote sensing-all of which depend on precise geometric interpretation. The evaluation metrics corroborate that the algorithm based on CNN and MLP along with the SVR has better accuracy compared to the model that relies only on CNN and MLP. © 2024 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of vision Transformer Based Architecture for Cursive Handwritten Text recognition 26

Performance Analysis of Vision Transformer Based Architectur...

引用

26th International conference on computer and Information Technology, ICCIT 2023

作者： Chowdhury, Avishek Hossen, Md. Ahasan Hasan, Mohammad Rukunuddin Osmani, Sheikh Md Premier University Dept. of Computer Science & Engineering Chattogram Bangladesh

ISBN: (纸本)9798350359015

computers have been given vision by researchers across the world for many years. Now it is the era of digitization. Recognizing handwritten text is a must for a computer vision system. Due to the variation and complexity of the cursive writing style, the holistic approach is mostly used for the recognition of cursive scripts. Though Convolutional Neural Network (CNN) based models have been employed in literature for Holistic Handwritten Text recognition (HTR) of different domains, recent breakthroughs in the image classification vision Transformer (ViT) based models have not been utilized for HTR so far. In this research, we have designed a ViT-based model for the HTR of various cursive scripts. To validate the performance of the model, various handwritten datasets of cursive scripts have been used. The notable finding includes that the accuracy of the designed model has increased by up to 26% after applying the image data augmentation techniques. © 2023 ieee.

关键词： Augmentation Cursive Handwritten Text recognition (HTR) vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Traffic Police Command Gesture recognition Technology Based on Machine vision and Two-Stream Spatio-Temporal Attention Graph Convolutional Network 3

Traffic Police Command Gesture Recognition Technology Based ...

引用

3rd International conference on computer vision and pattern Analysis, ICCPA 2023

作者： Li, Yuan College of Computer Science and Technology Xi’an University of Science and Technology Xi’an China

ISBN: (纸本)9781510667563

For the requirement of automatic recognition of traffic police gestures in complex backgrounds based on vision sensors for driverless cars, We propose a method for traffic police gesture action recognition based on two-stream spatio-temporal attention graph convolutional network (2s-AGCN) with two different dimensional skeletal data. Firstly, detect the commanding traffic policeman in the video, extract the 2D and 3D skeletal data with the pose estimation algorithm to reduce the influence of complex background and joint overlap on action recognition, then, build the spatio-temporal graph model;After that, we construct a 2s-AGCN network, input 2D and 3D skeletal sequences into the network to learn the spatio-temporal features of gesture actions. Finally, a fusion of the two-stream information is done and then output the final traffic police gesture category. 2s-AGCN uses Non-Local and TopK at the spatial level to focus on all nodes directly, selecting the strongest K neighbors of interaction strength;Temporal attention is used to focus on the frames that have higher contribution. The ablation study is done on the dataset CTPGD, and the results show that the method significantly improves the recognition accuracy of traffic police command gesture actions, especially those with overlapping skeleton points. © 2023 SPIE.

关键词： Law enforcement

来源：评论

学校读者我要写书评

暂无评论

Adapting Spatial Transformer Networks Across Diverse Hardware Platforms: A Comprehensive Implementation Study 6

Adapting Spatial Transformer Networks Across Diverse Hardwar...

引用

6th International conference on AI Circuits and Systems (AICAS)

作者： Bettayeb, Meriem Hassan, Eman Khan, Muhammad Umair Halawani, Yasmin Saleh, Hani Mohammad, Baker Khalifa Univ Syst On Chip SoC Lab Comp & Commun Engn Dept Abu Dhabi U Arab Emirates Univ Dubai Coll Engn & IT Dubai U Arab Emirates

ISBN: (纸本)9798350383638;9798350383645

The field of artificial intelligence (AI) holds a variety of algorithms designed with the goal of achieving high accuracy at low computational cost and latency. One popular algorithm is the vision transformer (ViT), which excels at various computer vision tasks for its ability to capture long-range dependencies effectively. This paper analyzes a computing paradigm, namely, spatial transformer networks (STN), in terms of accuracy and hardware complexity for image classification tasks. The paper reveals that for 2D applications, such as image recognition and classification, STN is a great backbone for AI algorithms for its efficiency and fast inference time. This framework offers a promising solution for efficient and accurate AI for resource-constrained Internet of Things (IoT) and edge devices. The comparative analysis of STN implementations on the central processing unit (CPU), Raspberry Pi (RPi), and Resistive Random Access Memory (RRAM) architectures reveals nuanced performance variations, providing valuable insights into their respective computational efficiency and energy utilization.

关键词： Spatial Transformer Network Image Classification vision transformer raspberry Pi hardware platforms artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

HIERARCHICAL VERTEX-WISE INTENSIFICATION GRAPH CONVOLUTION FOR SKELETON-BASED ACTIVITY recognition 31

HIERARCHICAL VERTEX-WISE INTENSIFICATION GRAPH CONVOLUTION F...

引用

2024 International conference on Image Processing

作者： Li, Yun Xie, Hao Xiao, Jun Zhang, Cong Liu, Tianshan Lam, Kin-Man Hong Kong Polytech Univ Hong Kong Peoples R China Nanjing Univ Posts & Telecommun Nanjing Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Graph convolutional networks (GCNs), which can effectively captures the spatial and temporal relationships between skeleton joints through graph topology, have shown promising performances in skeleton-based activity recognition in recent years. These methods typically learn the semantic features of the vertices of a skeleton and the associated adjacency matrix. However, how to efficiently establish relationships between vertices still remains a substantial problem. To solve this problem, we propose a novel Hierarchical Vertex-wise Intensification Graph Convolution Network (HVI-GCN) for skeleton-based action recognition. The proposed module dilates input features into higher dimensions to broaden the temporal horizon, and builds a vertex-wise topology based on self-adaptively learned attention. With the adjacency matrix, features from other positions can be collected to aid the prediction of the current position. The proposed module provides a better receptive field and semantic understanding of both the spatial and temporal domains than related methods. Experiments were mainly conducted on the at NTU-RGB-D, NTU-GRB-D 120, and NW-UCLA datasets with joint and bone integrated with motion sequences. Experimental results show that HVI-GCN can improve accuracy by up to 1.1% on the RGB-D 120 dataset. Meanwhile, the accuracy on RGB-D 60 dataset and NW-UCLA dataset can be boosted by 1.4% and 1.2%, respectively.

关键词： Skeleton Skeleton-based activity recognition Activity recognition Graph convolutional network computer vision

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 << < 408 409 410 411 412 413 414 415 416 417 > >>

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：