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

25,252 篇 会议
277 篇 期刊文献
21 册 图书
3 篇 学位论文

馆藏范围

25,553 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,800 篇 工学
- 9,866 篇 计算机科学与技术...
- 6,079 篇 电气工程
- 5,771 篇 信息与通信工程
- 5,615 篇 软件工程
- 2,016 篇 光学工程
- 1,453 篇 控制科学与工程
- 1,280 篇 机械工程
- 1,155 篇 电子科学与技术（可...
- 873 篇 生物医学工程（可授...
- 833 篇 生物工程
- 793 篇 仪器科学与技术
- 265 篇 网络空间安全
- 253 篇 化学工程与技术
- 245 篇 安全科学与工程
- 239 篇 交通运输工程
- 183 篇 材料科学与工程（可...
- 162 篇 土木工程
- 159 篇 建筑学
5,716 篇 理学
- 3,480 篇 物理学
- 2,207 篇 数学
- 886 篇 生物学
- 564 篇 统计学（可授理学、...
- 420 篇 系统科学
- 310 篇 化学
3,023 篇 医学
- 2,897 篇 临床医学
- 312 篇 基础医学(可授医学...
- 229 篇 药学(可授医学、理...
1,390 篇 管理学
- 850 篇 管理科学与工程(可...
- 612 篇 图书情报与档案管...
- 169 篇 工商管理
181 篇 法学
133 篇 农学
55 篇 教育学
52 篇 文学
51 篇 经济学
51 篇 军事学
22 篇 艺术学

主题

3,122 篇 image processing
2,084 篇 image coding
2,020 篇 visualization
1,752 篇 image segmentati...
1,486 篇 feature extracti...
1,081 篇 image reconstruc...
907 篇 cameras
885 篇 signal processin...
833 篇 image color anal...
756 篇 humans
712 篇 image edge detec...
688 篇 image enhancemen...
667 篇 computer vision
649 篇 training
582 篇 image analysis
567 篇 deep learning
536 篇 image quality
481 篇 conferences
472 篇 object detection
472 篇 robustness

机构

51 篇 school of electr...
50 篇 shanghai jiao to...
39 篇 ieee
38 篇 university of sc...
36 篇 shanghai jiao to...
36 篇 school of comput...
34 篇 shanghai jiao to...
33 篇 university of ch...
32 篇 microsoft resear...
26 篇 national institu...
25 篇 department of el...
24 篇 hendisli&#x011f
23 篇 institute for in...
23 篇 institute of ima...
23 篇 istanbul teknik ...
23 篇 institute of dig...
22 篇 peking univ inst...
21 篇 institute of inf...
21 篇 univ chinese aca...
21 篇 univ sci & techn...

作者

62 篇 guangtao zhai
46 篇 song li
45 篇 zhai guangtao
32 篇 jie yang
27 篇 li li
25 篇 m. vetterli
25 篇 bovik alan c.
25 篇 li sumei
25 篇 li song
25 篇 sarp ertürk
24 篇 jing zhang
24 篇 b. macq
23 篇 zhang lei
23 篇 li zhuo
23 篇 d.r. bull
22 篇 jürgen seiler
21 篇 shi guangming
20 篇 liu yang
20 篇 zhang wenjun
18 篇 mohamed-chaker l...

语言

24,740 篇 英文
489 篇 土耳其文
209 篇 其他
132 篇 中文
2 篇 西班牙文
2 篇 葡萄牙文

检索条件"任意字段=IEEE Visual Communications and Image Processing Conference"

共 25553 条记录，以下是71-80 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：

Independent Package Delivery Rover Using image processing and Obstacle Detection

Independent Package Delivery Rover Using Image Processing an...

引用

2025 International conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Dutta, Ashish Kumar Vijayashankar, S. Sheikh, Mohammed Sohail Tejesh Kumar, G.N. EmbedUR Pvt. Ltd. Chennai India Hyundai Motors India Ltd. Chennai India Thiagarajar College of Engineering Dept of Eee Madurai India

ISBN: (纸本)9798331509828

In the era of Industry 4.0, advancements in AI, automation, and robotics are reshaping traditional technologies, particularly in logistics. While automation has streamlined many aspects of logistics operations, the challenge of last-mile package delivery persists. Our prototype tackles some of these challenges by enabling autonomous last-mile delivery. At its core lies a Raspberry Pi microprocessor, driving functionalities such as visual perception through a camera, image processing for obstacle detection and navigation, line following, and a novel RFID-based package collection system. The concept of automating last-mile delivery is gaining traction among industry giants like Amazon, FedEx, and Sodexo. Our prototype offers a straightforward solution, adaptable to dynamic real-world conditions, paving the way for efficient last-mile delivery in the age of automation. © 2025 ieee.

关键词： Obstacle detectors

来源：评论

学校读者我要写书评

暂无评论

Real-Time Dynamic image Stitching Using GNN-Based Feature Matching 11

Real-Time Dynamic Image Stitching Using GNN-Based Feature Ma...

引用

11th International conference on Mechatronics and Robotics Engineering, ICMRE 2025

作者： Suh, Young Hoon Kim, Eun Ho Choi, Yeong Gwang Jeon, JaeWook Sungkyunkwan University Dept. of Electrical and Computer Engineering Suwon16419 Korea Republic of

ISBN: (纸本)9798331509293

Especially in static situations, image stitching has been routinely used to seamlessly merge many photographs into a panorama. Using it in dynamic and real-time environments, however, presents a number of difficulties, such as managing shifting objects, changing surroundings, and processing limitations. An image stitching look at that works well in dynamic real-time situations is presented in this paper. The method makes use of GNN-based feature matching, dynamic object removal, and real-time synthesis techniques. Comparative studies suggest that, in comparison to traditional methods like SIFT and ORB, the suggested approach meets real-time processing requirements while achieving greater registration precision, lower homography RMSE, and consistent panoramic outputs. The findings imply that the algorithm might be used in fields where precision and efficiency are required in dynamic circumstances, like parking management systems, sports broadcasting, and autonomous driving. © 2025 ieee.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

VHS: High-Resolution Iterative Stereo Matching with visual Hull Priors

VHS: High-Resolution Iterative Stereo Matching with Visual H...

引用

2025 ieee/CVF Winter conference on Applications of Computer Vision, WACV 2025

作者： Plack, Markus Dröge, Hannah Van Holland, Leif Hullin, Matthias B. University of Bonn Bonn Germany

ISBN: (纸本)9798331510831

We present a stereo-matching method for depth estimation from high-resolution images using visual hulls as priors, and a memory-efficient technique for the correlation computation. Our method uses object masks extracted from supplementary views of the scene to guide the disparity estimation, effectively reducing the search space for matches. This approach is specifically tailored to stereo rigs in volumetric capture systems, where an accurate depth plays a key role in the downstream reconstruction task. To enable training and regression at high resolutions targeted by recent systems, our approach extends a sparse correlation computation into a hybrid sparse-dense scheme suitable for application in leading recurrent network architectures. We evaluate the performance-efficiency tradeoff of our method compared to state-of-the-art approaches and demonstrate the efficacy of the visual hull guidance. In addition, we propose a training scheme for a further reduction of memory requirements during optimization, facilitating training on high-resolution data. © 2025 ieee.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

A Performance Comparison of Multiple Deep Learning Methodologies in image to Text Synthesis Tasks 3

A Performance Comparison of Multiple Deep Learning Methodolo...

引用

3rd International conference on Electronics and Renewable Systems, ICEARS 2025

作者： Martinez, Jude Joseph Lamug Winata, Edward Kevin Bina Nusantara International University Computer Science Department Faculty of Computing and Media Central Jakarta11480 Indonesia

ISBN: (纸本)9798331509675

Generating textual descriptions from visual inputs has become a critical area of research in the intersection of computer vision and natural language processing called image captioning. This study deep dives towards comparing a few popular image captioning methodologies, going from traditional encoder decoder architectures to more advanced techniques that incorporate attention mechanisms, transformers, and reinforcement learning. We evaluate the performance of these models on publicly available datasets containing logs from the online community Flickr on several dimensions including caption accuracy, diversity and computational efficiency. Captions are evaluated in terms of both quantitative metric(BLEU, ROUGE-N, METEOR, CIDEr, SPICE) and qualitative analysis(contextual relevance besides creativity) for the caption quality. The results show clear advantages and trade offs of each method, allowing for a holistic assessment of how each approach is suitable for real world problems. Thus, this work sheds important light on the trade offs between model complexity, efficiency and performance in image captioning tasks and provides a useful reference for researchers making similar decisions about model design in similar tasks. © 2025 ieee.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Prompting with image Token for Continual Learning

Semantic Prompting with Image Token for Continual Learning

引用

2025 ieee/CVF Winter conference on Applications of Computer Vision, WACV 2025

作者： Han, Jisu Na, Jaemin Hwang, Wonjun Ajou University Korea Republic of Tech. Innovation Group Kt Korea Republic of

ISBN: (纸本)9798331510831

Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the reliance on the rehearsal buffer. Although this approach has demonstrated outstanding results, existing methods depend on preceding task-selection process to choose appropriate prompts. However, imperfectness in task-selection may lead to negative impacts on the performance particularly in the scenarios where the number of tasks is large or task distributions are imbalanced. To address this issue, we introduce a novel task-agnostic approach that focuses on the visual semantic information of image tokens eliminating the preceding task prediction. By leveraging the ability of the pre-trained model to discriminate between similar tokens, our method not only subdivides the prompt but also eliminates the need for additional forward pass. Consequently, we achieve competitive performance on four benchmarks while significantly reducing training time compared to state-of-the-art methods. The code is available at https://***/pilsHan/I-Prompt © 2025 ieee.

关键词： continual learning prompt-based learning task-agnostic

来源：评论

学校读者我要写书评

暂无评论

MDCN-PS: Monocular-Depth-Guided Coarse Normal Attention for Robust Photometric Stereo

MDCN-PS: Monocular-Depth-Guided Coarse Normal Attention for ...

引用

2025 ieee/CVF Winter conference on Applications of Computer Vision, WACV 2025

作者： Yamaguchi, Masahiro Shibata, Takashi Yachida, Shoji Yokoyama, Keiko Hosoi, Toshinori Nec Corporation Visual Intelligence Research Laboratories 1753 Shimonumabe Nakahara-ku Kanagawa Kawasaki211-8666 Japan

ISBN: (纸本)9798331510831

Photometric Stereo (PS) is a technique for estimating surface normals from images illuminated by multiple light sources. However, when the target object has a complex shape or the light sources are not appropriately arranged, certain regions may experience severe shadows, leading to insufficient information for accurate estimation. In this paper, we propose a Monocular-Depth-guided Coarse Normal attention for Photometric Stereo (MDCN-PS). The MDCN-PS can effectively combine monocular depth from a single image with PS with multiple light sources by a Photometric Stereo network Adaptor (PS Adaptor) with Coarse Normal Attention. The key is to use the coarse normals obtained from Monocular Depth Estimation as supplementary information, which can improve accuracy in regions where the light source is limited due to severe shadows or inhomogeneous light source distribution. Comprehensive experiments on real-world and synthetic datasets show that the proposed method achieved an accuracy improvement of 1.2 points in real-world datasets when limited to two input images and of 3.1 points in synthetic datasets in mean angular error compared to existing methods. Qualitative results also demonstrated that our method improves accuracy in areas with insufficient lighting patterns due to shadows. © 2025 ieee.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Recipe Generation

Retrieval Augmented Recipe Generation

引用

2025 ieee/CVF Winter conference on Applications of Computer Vision, WACV 2025

作者： Liu, Guoshan Yin, Hailong Zhu, Bin Chen, Jingjing Ngo, Chong-Wah Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Singapore Management University Singapore

ISBN: (纸本)9798331510831

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method - first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset. © 2025 ieee.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

Prompt Driven image Creation: A Comparative Evaluation of Generative AI Tools 8

Prompt Driven Image Creation: A Comparative Evaluation of Ge...

引用

8th International conference on Electronics, Materials Engineering and Nano-Technology, IEMENTech 2025

作者： Das, Soma Santra, Debabrata Chhari, Trinanjan Roy, Shubhasri Mukherjee, Shreejita Department of Computer Science and Engineering India

ISBN: (纸本)9798331520762

This paper presents a comparative analysis of four generative AI models namely ChatGPT, Gemini, Copilot, and Stable Diffusion - evaluated on metrics such as visual quality, prompt adherence, creativity, usability, and processing time. visual and quantitative results highlight Gemini and Copilot's superiority in artistic and imaginative tasks, while Stable Diffusion excels in customization for advanced users. ChatGPT demonstrates ease of use but is limited in complexity. We also provides the best practices in selecting and using such tools to improve creative work. This study emphasizes the importance of evaluating generative AI tools based on diverse requirements and practical use cases. © 2025 ieee.

关键词： Usability engineering

来源：评论

学校读者我要写书评

暂无评论

Tropical Monsoon Cyclone Intensity Estimator using INSAT 3-D image 6

Tropical Monsoon Cyclone Intensity Estimator using INSAT 3-D...

引用

6th International conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Gilmary, Rosario Arunkumar, R. Kaviya, N. Information Technology IFET College of Engineering Villupuram India

ISBN: (纸本)9798331522667

Tropical cyclones (TC) are very destructive meteorological events that mostly affect coastal regions. For early warning and catastrophe management, TC intensity estimation is essential. One important source of real-time data for cyclone behavior prediction is satellite photography, especially that provided by INSAT-3D. Cyclone intensity may be precisely approximated by utilizing machine learning methods like as convolutional neural networks (CNNs) in conjunction with sophisticated image processing techniques like feature extraction and segmentation. The goal of this work is to develop a reliable model for cyclone strength estimates by integrating deep learning methods with INSAT-3D satellite data. The algorithm makes predictions based on visual characteristics such as wind speeds, sea surface temperatures, and cloud patterns. The suggested approach has the potential for real-time application and shows up to 95% accuracy in intensity prediction. By decreasing human interaction in TC estimates and increasing forecast accuracy, this method improves preparedness for disasters. © 2025 ieee.

关键词： Tropical cyclone

来源：评论

学校读者我要写书评

暂无评论

MCU-Enhanced Underwater image processing 8

MCU-Enhanced Underwater Image Processing

引用

8th International conference on Electronics, Materials Engineering and Nano-Technology, IEMENTech 2025

作者： Bhowmick, Sumanta Ghosh, Avra Chakrabarty, Ratna Chaidhuri, Sheli Sinha Institute of Engineering and Management Electronics and Communication Kolkata India Jadavpur University Electronics and Telecommunication Engineering Kolkata India

ISBN: (纸本)9798331520762

Underwater image dehazing is a critical challenge due to light absorption, scattering, and color degradation. This paper presents a comprehensive dehazing methodology combining physical modeling and image enhancement techniques. The approach begins by computing the dark channel to estimate transmission and atmospheric light, enabling accurate haze removal. A multi-scale guided filter refines the transmission map, enhancing edge preservation. Scene radiance is then recovered, followed by brightness adjustment and contrast enhancement using CLAHE in the LAB color space. To further enhance visual clarity, the method applies unsharp masking for sharpening. This pipeline effectively addresses underwater image degradation, producing dehazed images with improved visibility, contrast, and sharpness. The proposed method demonstrates significant potential for applications in underwater exploration, marine biology, and robotic vision. © 2025 ieee.

关键词： Photointerpretation

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 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：