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

1,621 篇 会议
14 册 图书
12 篇 期刊文献

馆藏范围

1,647 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,161 篇 工学
- 889 篇 计算机科学与技术...
- 588 篇 软件工程
- 312 篇 光学工程
- 272 篇 信息与通信工程
- 258 篇 电气工程
- 174 篇 生物工程
- 148 篇 控制科学与工程
- 119 篇 机械工程
- 107 篇 生物医学工程（可授...
- 56 篇 电子科学与技术（可...
- 48 篇 材料科学与工程（可...
- 48 篇 化学工程与技术
- 47 篇 安全科学与工程
- 37 篇 仪器科学与技术
- 35 篇 交通运输工程
- 25 篇 网络空间安全
- 23 篇 建筑学
545 篇 理学
- 340 篇 物理学
- 196 篇 数学
- 175 篇 生物学
- 57 篇 化学
- 57 篇 统计学（可授理学、...
208 篇 医学
- 195 篇 临床医学
- 60 篇 基础医学(可授医学...
- 45 篇 药学(可授医学、理...
- 25 篇 公共卫生与预防医...
174 篇 管理学
- 96 篇 管理科学与工程(可...
- 80 篇 图书情报与档案管...
- 31 篇 工商管理
28 篇 农学
- 28 篇 作物学
19 篇 法学
17 篇 经济学
7 篇 教育学
5 篇 军事学
1 篇 文学

主题

307 篇 computer vision
228 篇 image processing
102 篇 image segmentati...
92 篇 feature extracti...
71 篇 deep learning
50 篇 object detection
42 篇 cameras
39 篇 image edge detec...
35 篇 convolutional ne...
34 篇 visualization
34 篇 image recognitio...
32 篇 machine learning
32 篇 image reconstruc...
31 篇 neural networks
30 篇 image color anal...
28 篇 computational mo...
28 篇 shape
28 篇 training
26 篇 image analysis
25 篇 face recognition

机构

6 篇 university of ch...
5 篇 comput & inf sci...
5 篇 department of co...
4 篇 chitkara univers...
4 篇 image processing...
4 篇 beijing institut...
4 篇 college of compu...
3 篇 shanghai jiao to...
3 篇 dept of electr &...
3 篇 south china univ...
3 篇 inria sophia-ant...
3 篇 school of comput...
3 篇 department of ma...
3 篇 shenyang institu...
3 篇 department of co...
3 篇 school of electr...
3 篇 school of comput...
3 篇 college of compu...
3 篇 dept of control ...
3 篇 department of in...

作者

6 篇 andayani u.
5 篇 syahputra m.f.
5 篇 mohana
5 篇 siregar b.
4 篇 yang yang
4 篇 hassan ghassemia...
4 篇 li hui
4 篇 shohreh kasaei
4 篇 e.j. delp
3 篇 luo haibo
3 篇 paul joseph sure...
3 篇 wang wei
3 篇 wang qian
3 篇 ying liu
3 篇 maryam imani
3 篇 saurav sumeet
3 篇 weickert joachim
3 篇 muchtar m.a.
3 篇 xin wang
3 篇 aggarwal j.k.

语言

1,615 篇 英文
26 篇 其他
9 篇 中文
1 篇 德文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Computer Vision and Image Processing, CVIP 2018"

共 1647 条记录，以下是1501-1510 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：

Video Captioning Using Large Language Models

Video Captioning Using Large Language Models

引用

Innovation in Technology (INOCON), IEEE international conference for

作者： Priyanshu Malaviya Dhruvit Patel Santosh Bharti Department of Computer Science and Engineering Pandit Deendayal Energy University Gandhinagar Gujarat India

In this research, we delve into the intricate domain of video captioning, a pivotal aspect of multimedia content analysis, by harnessing the synergistic potential of convolutional and recurrent neural networks. Our study meticulously integrates a suite of models, including EfficientNet-LSTM, InceptionV3-LSTM, VGG16-LSTM, and ResNet50-LSTM, capitalizing on the LSTM’s prowess in processing temporal data and CNN’s efficiency in feature extraction. These models are instrumental in interpreting visual inputs and translating them into coherent textual descriptions. We further explore the BLIP model’s effectiveness in bridging the gap between visual perception and language interpretation by finetuning it, thereby enriching our video captioning methodology. A novel experiment in our study involves the fusion of ResNet50 with GPT2, aiming to create a robust framework that marries advanced image recognition with sophisticated language processing capabilities. This hybrid approach is anticipated to enhance the accuracy and context-awareness of caption generation. Additionally, we introduce an Attention-Based CNN+LSTM model, designed to refine the focus on salient aspects in videos, thereby ensuring the generation of more precise and contextually relevant captions. This approach addresses the challenge of varying significance across successive frames, ensuring that the captions accurately reflect the most critical content of the video. Our comprehensive analysis and innovative methodologies contribute significantly to the advancement of video captioning techniques, offering new perspectives and solutions in the intersection of computer vision and natural language processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face Detection with Landmark using YOLOv8

Face Detection with Landmark using YOLOv8

引用

Emerging Frontiers in Electrical and Electronic Technologies (ICEFEET), international conference on

作者： Nehith Sai Vemulapalli Pruthvi Paladugula Guggilam Sai Prabhat S Abhishek Anjali T Dept. of Computer Science and Engineering Amrita School of Computing Amritapuri India

The advent of deep learning combined with computer vision has brought forth unparalleled advancements in facial detection and landmark identification. One pivotal player in this transformation has been the YOLO (You Only Look Once) series, setting new milestones in object detection methodologies. Our research is centered on harnessing the YOLOv8 model to optimize face detection processes. We incorporate the OpenCV library for image processing, enhancing detection fidelity through adjustable parameters like confidence and intersection over union (IoU) thresholds. A standout feature of our methodology is its innate ability to adjust to diverse image proportions. This is achieved by innovatively resizing and padding input images, which not only maintains consistency in detection but also augments accuracy. The proposed technique not only demarcates the face but also pinpoints facial landmarks, thus offering a comprehensive spatial map for each detected face. Preliminary results on benchmark datasets underscore the model's dual advantage of speed and precision. Our approach promises not only improved face detection but also paves the way for its amalgamation into expansive facial recognition and analytic platforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Plug-and-Play with POA based Maximum a Posteriori Denoisers for image

Plug-and-Play with POA based Maximum a Posteriori Denoisers ...

引用

Mysore Sub Section international conference (MysuruCon), IEEE

作者： Adithya Padthe Sapna Kadakadiyavar Ramya Thatikonda Madhura G K Department of Information Technology University of the Cumberlands USA AI &ML Department Vemana Institute of Technology Kormangala Bangalore PhD in Information Technology at University of the Cumberlands AI &ML Department Nitte Meenakshi Institute of Technology Bengaluru

Restoring damaged images has been an issue in the fields of image processing and basic computer vision for decades. Due to their improved performance, techniques based on discriminative convolutional neural networks (CNNs) have recently garnered a lot of interest. However, most of these frameworks only operate well on one type of picture restoration assignment, hence their performance on other types of image restoration is usually subpar. Research techniques leverage the fact that the Maximum a Posteriori (MAP) optimisation may be broken down into smaller sub-problems, such as a MAP denoising optimisation, to resolve this issue. We introduce the first full-stack method for MAP estimation in deep neural network image denoising. We prove that our approach will always result in a smaller MAP denoising goal, which can subsequently be employed in the general picture restoration optimisation technique known as the Puzzle Optimisation technique (POA). Our technique is theoretically analysed, and its quantitative efficacy is demonstrated through a number of tests. Our experiments validate the theoretical foundations of MAP and demonstrate that the suggested approach can reach 70x quicker presentation than the state-of-the-art.

关键词：

来源：评论

学校读者我要写书评

暂无评论

computer Aided System For Early Detection Of Nuclear Cataract Using Circle Hough Transform

Computer Aided System For Early Detection Of Nuclear Catarac...

引用

international conference on Trends in Electronics and Informatics (ICEI)

作者： A. B. Jagadale S.S. Sonavane D.V. Jadav E&TC JSPM RSCOE Savitribai Phule Pune University Pune India E&TC.Indira gandhi college of Engineering Savitribai Phule Pune University Pune India DTE Maharashtra Amrawati India

Survey done by world health organization for probing causes of blindness indicates that cataract is major cause of blindness. Even age related cataract is most commonly observed, it is serious cause to think because of its appearance in minors and children for both eyes. Detecting cataract at earlier stage is challenge as it has less affecting vision. The three most general types of cataract are nuclear cataract, cortical cataract and post subcapsular cataract. Slit lamp observation with lens opacity classification system (LOCS-III) is used for detection and medical diagnosis by ophthalmologists. Lens replacement surgery is most common treatment suggested on cataract for correcting vision. Literature survey indicates towards the success and correctness of computer added detection and grading is function of correctness of lens localization from cataract eye image. The work presented in this paper uses slit lamp images from ophthalmologist at eye hospital with computer aided image processing to detect cataract at earlier stage. The challenge of detection of cataract at earlier stage is attended in steps like lens detection, lens segmentation, feature extraction and categorization. The overall accuracy is enhanced by use of Hough circle detection transform for lens detection and support vector machine for categorization. The detection and categorization is performed using statistical feature extraction with prior trained support vector machine.

关键词： Cataracts Lenses Feature extraction Transforms Support vector machines Hospitals Lighting

来源：评论

学校读者我要写书评

暂无评论

Activity Recognition in Video Frames for Enhancing Human-Robot Collaboration: A Machine Learning Perspective

Activity Recognition in Video Frames for Enhancing Human-Rob...

引用

Advancement in Electronics & Communication Engineering (AECE), international conference on

作者： Ved Prakash Chaubey Shamneesh Sharma Aman Kumar Arun Malik Praveen Malik Isha Batra Delivery and Student Success UpGrad Campus upGrad Education Private Limited Bangalore Karnataka India School of Computer Science & Engineering Lovely Professional University Punjab India School of Electronics and Communication Engineering Lovely Professional University Punjab India

Human activity recognition is a prominent area of investigation within computer vision research. Its potential applications span diverse fields such as security monitoring, healthcare, and human-computer interaction. The identification and classification of human activity through the utilization of machine learning techniques has yielded a plethora of proposed models within this dynamic field of scientific inquiry. By employing diverse kinetic models that are linked to the learning of spatial or temporal features, the characteristics of a collection of image or video data are extracted. The primary aim of this model is to identify and classify ongoing activities. This objective has been successfully achieved by various deep-layer trained models that have been implemented in this field. To fulfill the specified criteria, the proposed approach utilizes the Long Recurrent Convolutional Network (LRCN) and Long Short-Term Memory (LSTM) convolutional neural network architectures. The implementation of vision-Based Human Activity Recognition utilizes the 3D Convolutional Neural Network (CNN) model. The model undergoes training utilizing the UCF-50 dataset. The classification of the photos by the model is contingent upon the action being performed. The model will receive videos as input, which will undergo appropriate pre-processing before being classified based on the activity. The vision-based human activity identification system offers several advantages, including but not limited to accuracy, cost-effectiveness, and user-friendliness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel method for moving object detection based on block based frame differencing

A novel method for moving object detection based on block ba...

引用

international conference on Recent Advances in Information Technology (RAIT)

作者： Sandeep Singh Sengar Susanta Mukhopadhyay Department of Computer Science and Engineering Indian School of Mines Dhanbad India

ISBN: (纸本)9781479985807

Moving-object detection is one of the basic and most active research domains in the field of computer vision. This paper proposes a novel and efficient approach for moving object detection under a static background. Proposed approach first performs pre-processing tasks to remove noise from video frames. Secondly, it finds the difference between the current frame and previous consecutive frame as well as current frame and next consecutive frame separately. The algorithm then selects the maximum pixel intensity value between both the difference frames, which we consider as an improvement over the previous approaches. Next we divide the resultant difference frame into non-overlapping blocks and calculate the intensity sum and mean of each block. Subsequently, it finds the foreground and background pixels of each block using threshold and intensity mean. In the next step morphology operation along with connected component analysis are applied to correctly detect the target objects. The proposed approach is accurate for detecting the moving object with varying object size and numbers. This work has been formulated, implemented and tested on real video data sets and the results are found to be satisfactory as it evident from the performance analysis.

关键词： Optical imaging image segmentation Object detection

来源：评论

学校读者我要写书评

暂无评论

Time Optimized Digital image processing of Ball and Plate System Using Artificial Neural Network

Time Optimized Digital Image Processing of Ball and Plate Sy...

引用

RSI/ISM international conference on Robotics and Mechatronics

作者： Yasaman Parandian Hannaneh Z. Arabshahi Ali Nasr S. Ali A. Moosavian Center of Excellence in Robotics and Control Advanced Robotics and Automated Systems (ARAS) Lab. Department of Mechanical Engineering K.N. Toosi University of Technology Tehran Iran

ISBN: (纸本)9781467372350

Regarding robot interaction with moving objects and the necessity for robot controller to react in a timely manner having the objects current position, finding an efficient positioning method has always been a challenge. As ball and plate system is considered to be a standard experimental system in control laboratories. The system is consisted of the following pieces: a horizontal plate which gets tilted along each horizontal axes. The ball, which is located on the plate;is controlled by the system in a way to be placed in any point on the plate. In fact, the ball and plate system is an extension of the classical ball on beam experiment that is often used to study various types of control and stability problems.

关键词： Forward Kinematics Neural Networks Real-Time computer vision 3RRS Parallel Robot Ball and Plate

来源：评论

学校读者我要写书评

暂无评论

Optimal Analysis of Target Dynamic Tracking Strategy Based on computer vision

Optimal Analysis of Target Dynamic Tracking Strategy Based o...

引用

Electronic Information Technology and computer Engineering (EITCE), international conference on

作者： Shuo Liu School of Data Science and Computer Sun Yat-sen University Guangzhou China

ISBN: (数字)9781728135847

ISBN: (纸本)9781728135854

computer vision is a highly intensive interdisciplinary subject which combines artificial intelligence and advanced algorithms, and its target tracking has become a hot research topic at present. At the operational level of target tracking, PF(Particle Filter) technology has its own technical advantages in processing image interpretation interference and target movement change. On the one hand, BPNN(Back Propagation Neural Network) technology is introduced to improve the diversity of particles and improve the accuracy of target information at the next moment so as to meet the dual requirements of dynamic intelligent capture and timeliness at the next moment of target tracking; on the other hand, PSO(Particle Swarm Optimization) technology is introduced to prevent particle degradation and quickly find the global optimal solution of particle information. The simulation results show that the method of using BPNN + PSO to improve the particle filter algorithm, not only improves the accuracy of target tracking information, but also reduces the timeconsuming of target tracking.

关键词： Particle filters Optimization Target tracking Mathematical model Analytical models

来源：评论

学校读者我要写书评

暂无评论

Research on Digital image Recognition Scheme Based on 3D Technology

Research on Digital Image Recognition Scheme Based on 3D Tec...

引用

IEEE international conference of Safety Produce Informatization (IICSPI)

作者： Yue Gao Beijing Institute of Technology Beijing China

ISBN: (数字)9781728177380

ISBN: (纸本)9781728177397

image is a reflection of objective reality in a certain sense, which conveys information to human beings in different modes. As an important information carrier, image is intuitive, rich in content and easy to communicate, which is an important content of multimedia. With the wide application of 3D images, image recognition based on 3D technology has attracted more researchers' attention, and there are more and more recognition methods. Human beings rely on two-dimensional images to perceive the three-dimensional world, and using computers to accomplish the same thing is the main research content in the field of computer vision. At any particular moment, the points on the target in the image correspond one-to-one with the points on the real three-dimensional target object. The images acquired by the imaging system are often not directly applicable due to various conditions and random interference. Based on the three-dimensional technology, this paper studies the digital image recognition scheme, and analyzes the image processing such as grayscale correction and noise filtering.

关键词： image segmentation image recognition Three-dimensional displays Digital images Imaging Interference Wavelet coefficients

来源：评论

学校读者我要写书评

暂无评论

Application of Multi-task and Real-time Communication Technology Based on DM642

Application of Multi-task and Real-time Communication Techno...

引用

2010 The 3rd international conference on Computational Intelligence and Industrial Application (PACIIA2010)

作者： Kai Liang School of Optical-Electronical and computer Engineering University of Shanghai for Science and Technology Shanghai, China Shuguang Dai School of Optical-Electronical and computer Engineering University of Shanghai for Science and Technology Shanghai, China

We have completed a project named "car navigation by machine vision technology", which was consisted of several smaller projects, and one of them was to schedule all the tasks in a real-time manner. This article tries to give some views about how to use the DSP / BIOS real-time operating system to cope with multi-task communication by solving the following problems: "how to achieve synchronization of image processing and car motion"," how to use the image threshold to control the state transition of car motion", and "how to arrange the required schedule of various states of car motion". Finally, we made the car move in a similar "8" shaped path periodically.

关键词： DM642 DSP/BIOS RTOS Machine 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165页 << < 147 148 149 150 151 152 153 154 155 156 > >>

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：