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

236 篇 会议
5 册 图书
1 篇 期刊文献

馆藏范围

242 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

186 篇 工学
- 139 篇 软件工程
- 109 篇 计算机科学与技术...
- 37 篇 光学工程
- 32 篇 信息与通信工程
- 24 篇 生物工程
- 21 篇 电气工程
- 12 篇 化学工程与技术
- 10 篇 生物医学工程（可授...
- 7 篇 电子科学与技术（可...
- 7 篇 控制科学与工程
- 6 篇 机械工程
- 5 篇 安全科学与工程
- 4 篇 建筑学
- 4 篇 土木工程
- 3 篇 材料科学与工程（可...
90 篇 理学
- 42 篇 数学
- 42 篇 物理学
- 25 篇 生物学
- 13 篇 统计学（可授理学、...
- 12 篇 化学
- 4 篇 系统科学
- 3 篇 地质学
21 篇 管理学
- 15 篇 图书情报与档案管...
- 6 篇 管理科学与工程(可...
- 3 篇 工商管理
15 篇 医学
- 15 篇 临床医学
- 5 篇 基础医学(可授医学...
- 5 篇 药学(可授医学、理...
5 篇 法学
- 5 篇 社会学
3 篇 教育学
- 3 篇 教育学
2 篇 农学
1 篇 经济学
1 篇 军事学

主题

13 篇 image segmentati...
11 篇 rendering (compu...
11 篇 computer graphic...
10 篇 deep learning
9 篇 training
8 篇 visualization
8 篇 image reconstruc...
7 篇 object detection
7 篇 three-dimensiona...
7 篇 convolution
7 篇 convolutional ne...
6 篇 image enhancemen...
6 篇 cameras
6 篇 image processing
6 篇 industrial elect...
5 篇 application soft...
5 篇 target tracking
5 篇 lighting
5 篇 image recognitio...
5 篇 heuristic algori...

机构

5 篇 key laboratory o...
4 篇 microsoft resear...
3 篇 univ southern de...
2 篇 university of sc...
2 篇 college of softw...
2 篇 univ potsdam fac...
2 篇 ningbo institute...
2 篇 college of data ...
2 篇 guizhou key labo...
2 篇 collage of compu...
2 篇 shanghai spacefl...
2 篇 jiangxi research...
2 篇 school of electr...
2 篇 college of engin...
2 篇 school of comput...
2 篇 the ministry of ...
2 篇 beijing key labo...
2 篇 birmingham city ...
2 篇 key laboratory o...
2 篇 institute of com...

作者

4 篇 sakaue fumihiko
4 篇 feng fujian
4 篇 sato jun
3 篇 liang yihui
3 篇 shiqian wu
2 篇 xu xiang
2 篇 yu lingyun
2 篇 williams ian
2 篇 guo baolong
2 篇 harvey carlo
2 篇 rivadeneira rafa...
2 篇 liu ying
2 篇 anastasios rouss...
2 篇 soechting maximi...
2 篇 yingjie zheng
2 篇 telea alexandru
2 篇 zhai xiaorui
2 篇 wang shen
2 篇 sappa angel d.
2 篇 kim hansung

语言

240 篇 英文
5 篇 中文
2 篇 其他

检索条件"任意字段=15th Conference on Image and Graphics Technology and Applications, IGTA 2020"

共 242 条记录，以下是1-10 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：

15th conference on image and graphics technology and applications, igta 2020

15th Conference on Image and Graphics Technology and Applica...

引用

15th conference on image and graphics technology and applications, igta 2020

ISBN: (纸本)9789813360327

the proceedings contain 24 papers. the special focus in this conference is on image and graphics technology and applications. the topics include: Infrared Small Target Recognition with Improved Particle Filtering Based on Feature Fusion;single image Super-Resolution Based on Generative Adversarial Networks;Simplifying Sketches with Conditional GAN;Improved Method of Target Tracking Based on SiamRPN;An Improved Target Tracking Method Based on DIMP;target Recognition Framework and Learning Mode Based on Parallel images;view Consistent 3D Face Reconstruction Using Siamese Encoder-Decoders;an Angle-Based Smoothing Method for Triangular and Tetrahedral Meshes;AUIF: An Adaptive User Interface Framework for Multiple Devices;A Striping Removal Method Based on Spectral Correlation in MODIS Data;deep Attention Network for Remote Sensing Scene Classification;thin Cloud Removal Using Cirrus Spectral Property for Remote Sensing images;accurate Estimation of Motion Blur Kernel Based on Genetic Algorithms;graph Embedding Discriminant Analysis and Semi-Supervised Extension for Face Recognition;3D Human Body Reconstruction from a Single image;abnormal Crowd Behavior Detection Based on Movement Trajectory;image Recognition Method of Defective Button Battery Base on Improved MobileNetV1;preface;control and on-Board Calibration Method for in-Situ Detection Using the Visible and Near-Infrared Imaging Spectrometer on the Yutu-2 Rover;full Convolutional Color Constancy with Attention;fast and Accurate Face Alignment Algorithm Based on Deep Knowledge Distillation;multi-modal 3-D Medical image Fusion Based on Tensor Robust Principal Component Analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internal Embeddings of Multi-modal LLMs as Generalizable Representations for image Quality Assessment 24

Internal Embeddings of Multi-modal LLMs as Generalizable Rep...

引用

15th Indian conference on Computer Vision graphics and image Processing

作者： Totade, Sanjot Sagar Babu, Nithin C. Rao, Shika Soundararajan, Rajiv Indian Inst Sci Bangalore Elect Commun Engn Bangalore Karnataka India

ISBN: (纸本)9798400710759

One of the major challenges in no-reference (NR) image quality assessment (IQA) is the ability to generalize to diverse quality assessment applications. Recently, multi-modal vision-language models are found to be very promising in this direction. they are beginning to form a part of several state of the art NR IQA methods. On the other hand, multi-modal large language models (LLMs) are increasingly being studied for various computer vision applications including IQA. In this work, we perform a thorough study of the ability of multi-modal LLMs for NR IQA by training some of its components and testing for its generalizability. In particular, we keep the LLM frozen and learn parameters corresponding to the querying transformer, LLM prompt and some layers that process the embedding output by the LLM. We observe that some of these components offer a generalization performance far superior to any existing NR IQA algorithm.

关键词： image quality assessment large language models

来源：评论

学校读者我要写书评

暂无评论

PAN Source image Data Reconstruction based on Data Hiding 15

PAN Source Image Data Reconstruction based on Data Hiding

引用

15th International conference on graphics and image Processing, ICGIP 2023

作者： Mengyao, Liu Quan, Zhou Xiaosong, Zheng Yi, Zhang Yanlang, Hu Juanni, Liu Jiayuan, Wei Xi’an China

ISBN: (纸本)9781510675018

Although the fusion of Panchromatic(PAN) images and Multi-spectral(MS) images can improve the resolution of remote sensing MS images, the joint adjustments of PAN images and MS images will lead to the original data being completely lost. With the requirement of on-orbit image processing and multiple applications, obtaining fusion images while retaining the source images has become a problem that must be considered. To deal with the problem that the original data is lost after fusion, this proposed method embeds the PAN image object and compression data into the fused image. the experimental results show that the proposed method can reconstruct the object data of the PAN image losslessly and reconstruct the entire PAN image in high quality. the fused image indicators also have no impact. © 2024 SPIE. All rights reserved.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Dynamic Optical Model for Time-Based Enhancement of Augmented Reality Environments 15

Dynamic Optical Model for Time-Based Enhancement of Augmente...

引用

15th IEEE Annual Computing and Communication Workshop and conference, CCWC 2025

作者： Zhang, Qi School of Information Technology Illinois State University NormalIL United States

ISBN: (纸本)9798331507695

Dynamic lighting is essential for creating realistic day-night cycles and enhancing augmented reality (AR) experiences. In this paper, we introduce a dynamic optical model that simulates the natural progression of light from sunrise to sunset and into nighttime, bringing environments to life. Our model leverages six photographic images as backgrounds for AR scenes and incorporates advanced rendering techniques to generate textured models and geometries. these textures are enhanced using novel image processing methods to improve contrast and visibility, particularly in low-light conditions. Our algorithm ensures a seamless blend between virtual elements and the natural world by matching AR lighting conditions with the real environment. the environment's light transitions dynamically, from daylight brightness to ambient nighttime light, with the sun acting as the primary light source, rotating around the virtual world to simulate realistic lighting and shading effects. this texture-sampling-based lighting algorithm adapts to real-time conditions, interactively adjusting the lighting to enhance AR elements, highlight critical information, and create immersive, believable experiences in virtual simulations and AR applications. © 2025 IEEE.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Enabled Optical Characteristics Analysis Under Varying Illumination Conditions 15

Machine Learning Enabled Optical Characteristics Analysis Un...

引用

15th International conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Shirley, C.P. Berin Jeba Jingle, I. Kavin, S. Ebenezer, V. Joe Marshell, M. Joy Kiruba, P. Karunya Institute of Technology and Sciences Coimbatore India SRM Valliammai Engineering College SRM Nagar Kattankulathur Chengalpattu India PSNA College of Engineering and Technology Dindigul India

ISBN: (纸本)9798331300579

this paper presents a system for optical character recognition (OCR) that is both powerful and portable, able to analyse images and graphics taken with a camera and incorporated into text texts. Text section extraction and skew correction are the first steps in the procedure. the defined regions are next subjected to binarization, which separates them into lines and characters in preparation for additional examination. After that, these characters are sent to a recognition module. Extensive testing using a dataset of 100 cell phone-taken business card photographs produced an astounding maximum accuracy of 92.74%. An analysis conducted in comparison with the open-source Tesseract OCR engine, which is commonly used on desktop computers, demonstrates the excellent accuracy of the suggested solution. Most notably, the technique uses less memory and shows off its processing power, making it especially appropriate for mobile devices. this invention is very different from traditional OCR research, which is mostly focused on document images scanned by cumbersome desktop scanners with flatbeds that are connected to computers, making them impractical for mobile applications. © Grenze Scientific Society, 2024.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Transferring Appearance with Mask-Guided Attention 24

Transferring Appearance with Mask-Guided Attention

引用

15th Indian conference on Computer Vision graphics and image Processing

作者： Bandla, Manikanta IISc Bangalore Comp Sci & Automat Bangalore Karnataka India

ISBN: (纸本)9798400710759

Despite significant advancements in large-scale text-to-image generation and text-conditioned image editing, appearance transfer remains relatively unexplored. Transferring appearance aims to transfer an object's appearance in an appearance image to an object in the structure image so that background details are preserved and accurately reflect the transferred object's characteristics. Appearance transfer has practical applications in areas like virtual try-on and e-commerce product placement. Existing methods often require fine-tuning text-to-image diffusion models or are not applicable to virtual try-on and e-commerce scenarios, which is not ideal. In this paper, we introduce a Mask-Guided attention mechanism that replaces the existing self-attention in U-net architecture of Stable diffusion [29]. this approach can be easily integrated into the Masactrl [6] framework, enabling appearance transfer without model fine-tuning and suitable for a wide range of applications. Our method uses masks of objects in images to guide the appearance transfer process, with these masks obtained from the Segment Anything Model (SAM) [17]. this integration of SAM-generated masks allows for precise object localization and more accurate appearance transfer. We have conducted comprehensive experiments on transferring various clothing items (shirts, jeans, t-shirts) onto people, as well as transferring sofas into living spaces.

关键词： Appearance transfer image editing virtual try-on sofa placement masked attention segmentation

来源：评论

学校读者我要写书评

暂无评论

A multiscale circular geodesic model for image segmentation 15

A multiscale circular geodesic model for image segmentation

引用

15th International conference on graphics and image Processing, ICGIP 2023

作者： Chen, Xin Liu, Li Zhou, ShuWang Wang, YaLin School of Mathematics and Statistics Qilu University of Technology Shandong Academy of Sciences China Shandong Artificial Intelligence Institute Qilu University of Technology Shandong Academy of Sciences China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9781510675018

It is a popular way to incorporate the active contour evolution scheme into the multiscale image decomposition and reconstruction procedure, so as to enhance the image segmentation accuracy. However, most of these models are carried out by the level set formulation which cost much computation time. In this paper, we propose a new image segmentation model that combines the circular geodesic model with an adaptive cut and the multiscale image processing. As a consequence, the proposed model can blend the benefits from both of the geodesic models and the multiscale image analysis method. Experimental results show that the proposed multiscale geodesic model indeed outperforms the circular geodesic model with an adaptive cut in solving the image segmentation problem in the presence of strong noise. © 2024 SPIE. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

An effective visual tracking approach under low-light environments 15

An effective visual tracking approach under low-light enviro...

引用

15th International conference on graphics and image Processing, ICGIP 2023

作者： Jin, Hanyu Wang, Zeyuan Cai, Rongtai Key Laboratory of OptoElectronic Science and Technology Medicine of Ministry of Education Fujian Normal University Fuzhou350117 China Fujian Provincial Engineering Technology Research Center Photoelectric Sensing Application Fujian Normal University Fuzhou350117 China College of Photonic and Electronic Engineering Fujian Normal University Fuzhou350117 China

ISBN: (纸本)9781510675018

the performance of visual object detection, tracking, and recognition algorithms significantly degrade under low-light environments. To address this problem, we propose a simple yet effective approach for visual tracking under low-light environments. First, we detect and enhance low light images using Retinex technology, which boosts the contrast of the images to facilitate our algorithms to extract visual features for tracking. then, we apply the kernelized correlation Filter (KCF) to track the object and refine the tracking performance by instance segmentation and bounding box optimization using Mask R-CNN. At last, we introduce re-detection into the proposed algorithm to enable the tracker to catch the object while it appears again after heavy occlusion or out-of-view motion. Consequently, the proposed algorithm is suitable for long-term tracking. Experiments on VOT2016, OTB50, and UAV20L show that the proposed algorithm largely improves the tracking success rate and precision, and the running time meets the need for real-time applications. © 2024 SPIE. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

STURM: Exploiting Swin Transformer Unet with Random Masks for Self-Supervised Anomaly Detection 15

STURM: Exploiting Swin Transformer Unet with Random Masks fo...

引用

15th International conference on graphics and image Processing, ICGIP 2023

作者： Liu, Zhoufeng Ma, Xiaolei Gao, Guangshuai Yang, Ke Chai, Ningyu Zhongyuan University of Technology Zhengzhou China

ISBN: (纸本)9781510675018

Anomaly detection is an essential task in industrial applications. Traditional anomaly detection algorithms based on convolutional neural networks (CNNs) struggle to extract global context information, resulting in poor anomaly detection performance. Moreover, the diversity and inherent uncertainty of anomalous samples present considerable constraints on the effectiveness of traditional anomaly detection algorithms. In this paper, a novel Swin Transformer Unet with Random Masks for self-supervised anomaly detection is proposed. First of all, a random mask strategy (RMS) is adopted to generate simulated anomalies in anomaly-free samples to solve the limited availability of abnormal samples during the training phase. Furthermore, to enhance the overall feature representation for anomaly detection tasks, the Swin Transformer Unet is utilized as the backbone network to extract local features and global contextual information from multi-scale feature maps. Experimental results on the industrial dataset MVTec AD demonstrate that our model achieves comparable performance in terms of anomaly detection. © 2024 SPIE. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

APMSA: Crossmodal Remote Sensing image Retrieval using Attention Pooling and Multimodal Semantic Alignment 24

APMSA: Crossmodal Remote Sensing Image Retrieval using Atten...

引用

15th Indian conference on Computer Vision graphics and image Processing

作者： Aparna, H. Hati, Avik Natl Inst Technol Tiruchirappalli Tiruchirappalli India NIT Tiruchirappalli Tiruchirappalli India

ISBN: (纸本)9798400710759

Crossmodal image retrieval can help in crucial remote sensing (RS) applications like land cover monitoring and disaster management by retrieving complementary information from different data sources. Such retrieval techniques aid in the search and identification images captured by different satellite sensors like optical, thermal, SAR and MS over different geo-locations and time period. However, multi-modal RS data present a variety of challenges like intermodal relationship modelling and modality alignment. To this end, we propose a novel crossmodal image retrieval algorithm designed to deal with multiple RS image modalities like optical, multi-spectral and panchromatic. We make use of a modified version of residual networks (ResNets) which consists of stem convolution to capture salient features and attention pooling replacing the global average pooling to enhance the modelling of relation between image pixels. A combination of objective functions - the triplet loss which helps in identifying the latent details and features present in the images of individual modalities, and the novel multimodal semantic alignment loss which aids in orientation of extracted features in a shared vector space, thereby prompting intermodal comprehension and alignment - are used. We tested the algorithm on EuroSAT and DSRSID datasets, and the proposed method achieved 95.92% and 98.86% top-50 retrieval precision, respectively. Experimental results show that the proposed method exhibits superior performance in comparison to existing techniques in literature.

关键词： Crossmodal retrieval Multimodal semantic alignment Attention pooling Remote Sensing

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25页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：