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

15,243 篇 会议
186 篇 期刊文献
55 册 图书

馆藏范围

15,484 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,637 篇 工学
- 5,961 篇 计算机科学与技术...
- 4,109 篇 软件工程
- 2,077 篇 信息与通信工程
- 1,703 篇 光学工程
- 1,225 篇 控制科学与工程
- 1,123 篇 电气工程
- 1,029 篇 生物工程
- 846 篇 生物医学工程（可授...
- 628 篇 电子科学与技术（可...
- 553 篇 安全科学与工程
- 470 篇 网络空间安全
- 450 篇 机械工程
- 441 篇 交通运输工程
- 375 篇 化学工程与技术
- 319 篇 材料科学与工程（可...
- 300 篇 仪器科学与技术
- 278 篇 建筑学
- 262 篇 土木工程
3,294 篇 理学
- 1,527 篇 物理学
- 1,127 篇 数学
- 1,121 篇 生物学
- 369 篇 化学
- 324 篇 统计学（可授理学、...
1,649 篇 管理学
- 1,015 篇 管理科学与工程(可...
- 772 篇 图书情报与档案管...
- 295 篇 工商管理
952 篇 医学
- 797 篇 临床医学
- 479 篇 基础医学(可授医学...
- 365 篇 公共卫生与预防医...
- 258 篇 药学(可授医学、理...
229 篇 法学
220 篇 农学
118 篇 教育学
87 篇 经济学
85 篇 文学
37 篇 军事学

主题

2,357 篇 accuracy
2,051 篇 computer vision
1,739 篇 deep learning
1,354 篇 computational mo...
1,347 篇 feature extracti...
1,307 篇 training
1,216 篇 convolutional ne...
1,089 篇 image segmentati...
982 篇 visualization
762 篇 image processing
746 篇 transformers
689 篇 real-time system...
568 篇 computer archite...
534 篇 object detection
438 篇 three-dimensiona...
424 篇 image recognitio...
405 篇 neural networks
342 篇 image edge detec...
332 篇 data models
329 篇 machine learning

机构

72 篇 chitkara univers...
35 篇 university of sc...
34 篇 school of comput...
34 篇 university of ch...
29 篇 school of comput...
26 篇 chitkara centre ...
26 篇 department of co...
25 篇 centre of resear...
24 篇 department of co...
23 篇 school of comput...
22 篇 shanghai jiao to...
21 篇 tsinghua univers...
21 篇 computer vision ...
21 篇 computer science...
20 篇 computer science...
20 篇 university of el...
20 篇 school of comput...
18 篇 school of comput...
18 篇 school of electr...
18 篇 computer science...

作者

16 篇 chen chen
14 篇 gill kanwarparta...
13 篇 liu jun
13 篇 yang yang
12 篇 chen li
12 篇 wang wei
11 篇 ahmad jalal
11 篇 jia zhenhong
11 篇 li xin
11 篇 li yang
11 篇 li chen
11 篇 deepak upadhyay
10 篇 sharma vikrant
10 篇 roy partha prati...
10 篇 satvik vats
10 篇 li xiaoli
10 篇 kukreja vinay
10 篇 vikrant sharma
9 篇 wei li
9 篇 zhou gang

语言

14,487 篇 英文
988 篇 其他
144 篇 中文
1 篇 土耳其文

检索条件"任意字段=2024 International Conference on Computer Vision and Image Processing, CVIP 2024"

共 15484 条记录，以下是81-90 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：

Research on digital media art creation based on vision and generation algorithm 2

Research on digital media art creation based on vision and g...

引用

2nd international conference on Big Data, Computational Intelligence, and Applications, BDCIA 2024

作者： Li, Siya Jilin Animation College Jilin Changchun130012 China

ISBN: (纸本)9781510689053

This paper aims to explore the application and core position of vision and generation algorithm in digital media art. Through deep learning and computer vision technology, these algorithms not only process image and video data efficiently, but also give new expressive force and freedom to artistic creation. This paper summarizes the basic principles and applications of visual algorithms, including content recognition, video analysis, digital media art creation and scene reconstruction. The specific practices of image classification, target detection, pose estimation and so on are introduced in detail, and the construction of convolutional neural network (CNN) and its application in image classification are discussed in depth. The paper also introduces the common network architectures such as VGg, perception and RESNET, and shows the interest and practicability of the algorithm through the cases of target detection and neural style migration. © 2025 SPIE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Quantum-weighted autoencoder for compression computer-generated holograms 2

Quantum-weighted autoencoder for compression computer-genera...

引用

2nd international conference on Optical Communication and Optical Information processing, OCOIP 2024

作者： Hu, Chengcheng Yang, Guanglin School of Software and Microelectronics Peking University Beijing102600 China Laboratory of Signal and Information Processing School of Electronics Peking University Beijing100871 China

ISBN: (数字)9781510688995

ISBN: (纸本)9781510688988

We propose a quantum-weighted autoencoder network for compression computer-generated holograms. And the quantum-weighted autoencoder consists of embedding, entanglement, and measurement layers. Experimental results show that the image quality of computer-generated holograms reconstructed by this quantum network is generally better than that of traditional autoencoders. The training stability of the network is better than that of a traditional autoencoder, and the convergence of the network is faster. © 2025 SPIE.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Proceedings of international conference on computer vision and image processing: cvip 2016, Volume 1 1st ed.

引用

丛书名： Advances in Intelligent Systems and Computing

2017年

作者： Balasubramanian Raman, Sanjeev Kumar, Partha Pratim Roy, Debashis Sen (eds.)

ISBN: (数字)9789811021046

ISBN: (纸本)9789811021039;9789811021046

This edited volume contains technical contributions in the field of computer vision and image processing presented at the First international conference on computer vision and image processing (cvip 2016). The contributions are thematically divided based on their relation to operations at the lower, middle and higher levels of vision systems, and their applications. The technical contributions in the areas of sensors, acquisition, visualization and enhancement are classified as related to low-level operations. They discuss various modern topics reconfigurable image system architecture, Scheimpflug camera calibration, real-time autofocusing, climate visualization, tone mapping, super-resolution and image resizing. The technical contributions in the areas of segmentation and retrieval are classified as related to mid-level operations. They discuss some state-of-the-art techniques non-rigid image registration, iterative image partitioning, egocentric object detection and video shot boundary detection. The technical contributions in the areas of classification and retrieval are categorized as related to high-level operations. They discuss some state-of-the-art approaches extreme learning machines, and target, gesture and action recognition. A non-regularized state preserving extreme learning machine is presented for natural scene classification. An algorithm for human action recognition through dynamic frame warping based on depth cues is given. Target recognition in night vision through convolutional neural network is also presented. Use of convolutional neural network in detecting static hand gesture is also discussed. Finally, the technical contributions in the areas of surveillance, coding and data security, and biometrics and document processing are considered as applications of computer vision and image processing. They discuss some contemporary applications. A few of them are a system for tackling blind curves, a quick reaction target acquisition and tracking sys

关键词：

来源：评论

学校读者我要写书评

暂无评论

Probing the Efficacy of Federated Parameter-Efficient Fine-Tuning of vision Transformers for Medical image Classification 9th

Probing the Efficacy of Federated Parameter-Efficient Fine-T...

引用

27th international conference on Medical image Computing and computer Assisted Intervention (MICCAI)

作者： Alkhunaizi, Naif Almalik, Faris Al-Refai, Rouqaiah Naseer, Muzammal Nandakumar, Karthik Mohamed Bin Zayed Univ Artificial Intelligence Abu Dhabi U Arab Emirates

ISBN: (纸本)9783031776090;9783031776106

With the advent of large pre-trained transformer models, fine-tuning these models for various downstream tasks is a critical problem. Paucity of training data, the existence of data silos, and stringent privacy constraints exacerbate this fine-tuning problem in the medical imaging domain, creating a strong need for algorithms that enable collaborative fine-tuning of pre-trained models. Moreover, the large size of these models necessitates the use of parameter-efficient fine-tuning (PEFT) to reduce the communication burden in federated learning. In this work, we systematically investigate various federated PEFT strategies for adapting a vision Transformer (ViT) model (pre-trained on a large natural image dataset) for medical image classification. Apart from evaluating known PEFT techniques, we introduce new federated variants of PEFT algorithms such as visual prompt tuning (VPT), low-rank decomposition of visual prompts, stochastic block attention fine-tuning, and hybrid PEFT methods like low-rank adaptation (LoRA)+VPT. Moreover, we perform a thorough empirical analysis to identify the optimal PEFT method for the federated setting and understand the impact of data distribution on federated PEFT, especially for out-of-domain (OOD) and non-IID data. The key insight of this study is that while most federated PEFT methods work well for in-domain transfer, there is a substantial accuracy vs. efficiency trade-off when dealing with OOD and non-IID scenarios, which is commonly the case in medical imaging. Specifically, every order of magnitude reduction in fine-tuned/exchanged parameters can lead to a 4% drop in accuracy. Thus, the choice of the initial model is critical for the effectiveness of federated PEFT - rather than starting with general vision models, it is preferable to use medical foundation models (if available) learned using in-domain medical image data. Code: https://***/Naiftt/PEFT.

关键词： vision Transformers Parameter-Efficient Fine-tuning Out-of-Domain Transfer Federated Learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Multimodal Large Language Models for Solving Cognitive Puzzles 24

Empowering Multimodal Large Language Models for Solving Cogn...

引用

2nd international conference on Electronics, computers and Communication Technology, CECCT 2024

作者： Zhang, Wentao School of Computer Science University of Science and Technology of China Anhui Hefei China

ISBN: (纸本)9798400710193

Multimodal Large Language Models have been showing their powerful ability for solving general vision-language tasks, such as image captioning, vision question answering, which usually on par with or even better than human does. However, when it comes to cognitive puzzles, we find it struggling for multimodal large language models to solve this type of tasks. In this paper, we study the capacity of MLLMs for solving cognitive puzzles. We experiments with cutting-edge open-sourced MLLMs such as Qwen2-VL and LLaMA 3.2 and compare their ability in solving cognitive puzzles at different aspects. After recognizing the shortcomings with careful examination, we develop a multi-step chain-of-thought based solution to enhance the MLLM to reasoning on the sophisticated image. To verify generalization, we include several sources of cognitive puzzles such as Raven’s Progressive Puzzles and CVR. © 2024 Copyright held by the owner/author(s).

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Application of computer vision Technology in the Field of Automatic Target Reporting 14th

Application of Computer Vision Technology in the Field of Au...

引用

14th international conference on Frontier Computing, FC 2024

作者： Zhu, Rui Yu, Jie Yao, Fushan Shi, Wenhua Army Academy of Armored Force Jilin Changchun China The Army of 95795 Guangxi Guilin China

ISBN: (纸本)9789819627936

computer vision is to measure and judge by machine instead of man, and convert the captured target scene into image signal through camera device. Transmitting it to the image processing system and converting it into a digital signal through the significant mark of the image;Through the calculation of the digital signal, the characteristics of the target are obtained, so as to analyze, sort out, or obtain the judgment results. It is applied to the field of automatic target reporting, so as to improve the efficiency and quality. In view of the problems existing in manual target detection, combined with the actual needs, this paper intends to apply computer vision technology to automatic target reporting, focusing on the basic principle and system composition of automatic target reporting. Combined with the actual application, this paper studies and demonstrates the highly feasible automatic target reporting technology and forms a summary report, Lay a foundation for the subsequent research and development of automatic target reporting system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Saliency detection method for Panoramic images based on GCN-ELM 4

Saliency detection method for Panoramic Images based on GCN-...

引用

4th international conference on computer vision, Application, and Algorithm, CVAA 2024

作者： An, Nan Yu, Haiyang Zhang, Ripei Hu, Xiaojuan Li, Yanfeng School of Computer Science and Technology Changchun University of Science and Technology Changchun130022 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

In the field of saliency detection for panoramic images, traditional equirectangular and cube projection methods in panoramic image saliency detection often face issues like distortion and discontinuities, impacting detection accuracy. This study introduces an innovative image resampling technique and a GCN-ELM joint model. By evenly distributing spherical pixels onto a 2D plane, the method reduces pixel redundancy from equirectangular projection. Experimental results show that this approach significantly enhances saliency detection performance compared to existing methods. © 2025 SPIE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Automatization of Analysis Behavior in Crayfish 47th

Automatization of Analysis Behavior in Crayfish

引用

47th Mexican conference on Biomedical Engineering

作者： Sepulveda-Hernandez, Mario Hernandez-Falcon, Jesus Mendoza-Angeles, Karina Univ Nacl Autonoma Mexico Fac Ingn Mexico City DF Mexico Univ Nacl Autonoma Mexico Lab Redes Neuronales Fac Med Mexico City DF Mexico

ISBN: (纸本)9783031821226;9783031821233

Nowadays image processing algorithms are widely used in tracking position and posture estimation of animals;for those who study neurophysiology, the automated analysis of recorded videos allows to associate a specific behavior with cerebral activity. The principal purpose is to avoid long tiring observation times and human errors in the validation of the recording. For aquatic animals like crayfish, developing a system that can track position and estimate posture is crucial, as water introduces image distortion. Crayfish is a good model that allows to study behaviors like aggressiveness, sleep and exploration. Developing a computer vision system that detects the position in the aquarium and if the crayfish is lying on one side described as the stereotypical sleep position, will help the observer to just analyze specific moments of the recording to take a decision. The results presented in this work show that it's possible to use image processing to determine the position of a crayfish in the aquarium and to establish when the animal is lying on one side, allowing us to plot a graphic that represents the coordinates of position and the "sleep coordinates", those moments when the crayfish was lying on one side, i.e., a whole hypnogram, in a non-supervised way.

关键词： image processing Automated analysis behavior computer vision

来源：评论

学校读者我要写书评

暂无评论

MSDGAN: Multi-Scale Dilated Generative Adversarial Network for Smoke Removal and image Restoration 24

MSDGAN: Multi-Scale Dilated Generative Adversarial Network f...

引用

2024 5th international Artificial Intelligence and Blockchain conference, AIBC 2024

作者： Gwak, KyungMIn Rho, Young. J Tech University of Korea Siheung Korea Republic of

ISBN: (纸本)9798400710780

This paper presents a novel approach for smoke removal and image restoration using a Multi-Scale Dilated Generative Adversarial Network (MSDGAN). The presence of smoke in images poses significant challenges to both human perception and computer vision tasks, reducing visibility and complicating image processing tasks such as object recognition and segmentation. Traditional techniques like dehazing and defogging often fail to effectively address the irregular and transparent nature of smoke. To overcome these limitations, we propose a network architecture that integrates multi-scale dilated convolutions within a GAN framework, enabling the model to capture contextual information across various scales and improve the restoration of images affected by smoke. The MSDGAN architecture includes an encoder-decoder structure with skip connections, and it leverages perceptual loss and SSIM loss to maintain feature fidelity and reconstruct high-quality images. Extensive experiments demonstrate the effectiveness of the proposed network in removing smoke and restoring image quality across various challenging environments. The results show that MSDGAN outperforms existing dehazing and image restoration methods, offering superior performance as measured by L1, L2, SSIM, PSNR, and LPIPS metrics. This work provides a robust solution for enhancing image clarity in the presence of smoke, with potential applications in fields such as autonomous driving, surveillance, and remote sensing. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fake-GPT: Detecting Fake image via Large Language Model 7th

Fake-GPT: Detecting Fake Image via Large Language Model

引用

7th Chinese conference on Pattern Recognition and computer vision

作者： Fan, Yuming Yang, Dongming Zhang, Jiguang Yan, Bang Zou, Yuexian China Telecom Cloud Technol Co Ltd Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Peking Univ Beijing Peoples R China

ISBN: (纸本)9789819786848;9789819786855

With the development of Artificial Intelligence Generated Content (AIGC), fake image detection has become increasingly challenging. Also leveraging the advanced capabilities of large language models (LLMs) in sequence prediction, we propose a novel perspective on fake image detection by fine-tuning pure LLMs. We introduce Fake-GPT, a LLM with 7 billion parameters which can differentiate between real and fake images. Unlike conventional image processing models, our approach directly process RGB pixel values without relying on any position embedding and visual-language feature alignment, thereby reducing model complexity and processing steps. Our research demonstrates the effective application of LLMs in detecting fake images, thereby expanding their application in non-textual domains. Extensive experiments conducted on various deepfake datasets show that Fake-GPT achieves competitive results compared with conventional image processing models, underscoring its potential as a new paradigm in the realm of image authentication.

关键词： Visual languages

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 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：