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

2,506 篇 会议
4 篇 期刊文献

馆藏范围

2,510 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,355 篇 工学
- 1,103 篇 计算机科学与技术...
- 599 篇 信息与通信工程
- 484 篇 软件工程
- 393 篇 电气工程
- 194 篇 光学工程
- 159 篇 控制科学与工程
- 92 篇 生物工程
- 90 篇 电子科学与技术（可...
- 77 篇 生物医学工程（可授...
- 67 篇 网络空间安全
- 57 篇 安全科学与工程
- 51 篇 交通运输工程
- 44 篇 机械工程
- 41 篇 动力工程及工程热...
- 39 篇 建筑学
- 38 篇 土木工程
- 36 篇 化学工程与技术
- 33 篇 材料科学与工程（可...
- 27 篇 石油与天然气工程
426 篇 理学
- 253 篇 物理学
- 125 篇 数学
- 106 篇 生物学
- 39 篇 统计学（可授理学、...
- 28 篇 化学
420 篇 医学
- 407 篇 临床医学
- 29 篇 基础医学(可授医学...
196 篇 管理学
- 127 篇 管理科学与工程(可...
- 85 篇 图书情报与档案管...
- 28 篇 工商管理
28 篇 法学
- 26 篇 社会学
18 篇 农学
11 篇 经济学
10 篇 文学
9 篇 教育学
6 篇 军事学

主题

388 篇 visual communica...
371 篇 visualization
265 篇 image coding
206 篇 training
191 篇 feature extracti...
187 篇 image processing
180 篇 deep learning
144 篇 accuracy
116 篇 image segmentati...
106 篇 semantics
101 篇 convolutional ne...
98 篇 three-dimensiona...
80 篇 video coding
80 篇 computational mo...
79 篇 image reconstruc...
72 篇 image recognitio...
70 篇 image color anal...
67 篇 transformers
65 篇 object detection
63 篇 neural networks

机构

27 篇 shanghai jiao to...
24 篇 institute of ima...
21 篇 shanghai jiao to...
21 篇 school of electr...
20 篇 university of sc...
16 篇 tianjin univ sch...
15 篇 beijing universi...
13 篇 school of remote...
10 篇 shenzhen interna...
10 篇 university of el...
9 篇 zhejiang univers...
9 篇 shanghai jiao to...
9 篇 peking universit...
9 篇 shanghai jiao to...
8 篇 school of marine...
8 篇 univ sci & techn...
8 篇 peng cheng labor...
8 篇 school of electr...
8 篇 cas key laborato...
8 篇 school of electr...

作者

27 篇 zhai guangtao
23 篇 sumei li
22 篇 guangtao zhai
22 篇 li sumei
19 篇 song li
19 篇 shan liu
18 篇 andré kaup
17 篇 li li
15 篇 xiongkuo min
15 篇 zhenzhong chen
15 篇 min xiongkuo
14 篇 dong liu
12 篇 li song
12 篇 xie rong
12 篇 xin jin
11 篇 kei kawamura
10 篇 heming sun
10 篇 zhibo chen
10 篇 zhu li
9 篇 sun heming

语言

2,390 篇 英文
120 篇 其他
19 篇 中文

检索条件"任意字段=2024 IEEE International Conference on Visual Communications and Image Processing, VCIP 2024"

共 2510 条记录，以下是21-30 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：

Intelligent Computing System for Breast Cancer Identification utilizing U-Net for Digital image Segmentation 3

Intelligent Computing System for Breast Cancer Identificatio...

引用

3rd international conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Goli, Ranadheer Reddy Jadala, Vijaya Chandra Jamalpur, Bhavana Department of Computer Science and Artificial Intelligene School of Computer Science and Artificial Intelligence SR University Telangana Warangal506371 India

ISBN: (纸本)9798331527549

As per WHO calculation of deaths, globally due to Breast Cancer is around one million. Breast cancer can be cured by early detection, in which abnormal breast cells proliferate uncontrollably, leading to tumor formation. Early detection of breast cancer may reduce deaths, as per World Health Organization records there are about one million deaths are caused by 2024 among them only 0.5 percent are of men. The different methodologies adopted in medical image processing related to breast cancer detection methods include mammography. We concentrated on medical image segmentation which helps to get visual information about breast tissue. This paper presents an intelligent computing system designed to support medical image processing through utilizing U-Net methodology for segmentation as part of deep learning methodologies. As part of Experimental Analysis, a BUSI dataset is used for the implementation of Deep Learning methodologies. A graphic analysis based on medical images, followed by an analysis of the results. This Intelligent Computing System based on artificial intelligence helps radiologists, medical professionals, and doctors with early and simplified breast cancer diagnosis. © 2025 ieee.

关键词： Breast Cancer Intelligent System Segmentation U-Net

来源：评论

学校读者我要写书评

暂无评论

ALIC: Adaptive Fusion Entropy Model for Learned image Compression

ALIC: Adaptive Fusion Entropy Model for Learned Image Compre...

引用

2025 ieee international conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Li, Lingxue Liu, Meiqin Zhang, Yifan Tang, Qi Yao, Chao Zhao, Yao Institute of Information Science Beijing Jiaotong University Beijing China Visual Intelligence + X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798350368741

Recently, learned image compression algorithms have achieved significant performance. The entropy model is crucial for improving the rate-distortion performance by estimating the probability distribution of latent representation. In this paper, we propose an adaptive fusion entropy model for learned image compression (ALIC). To explore the correlation between channel and global spatial features, an adaptive fusion entropy model (AFEM) is designed. AFEM first slices the latent representation along the channels and leverages the adaptive channel fusion context module (ACFC) to capture correlations between the decoded and current slices. Subsequently, AFEM uses the adaptive spatial fusion context module (ASFC) to further divide the current slice into encoding pixels and reference pixels, thus improving the accuracy of probability estimation. The attention map and modulation parameter are introduced in ACFC and ASFC to interact with channel and spatial features. In addition, the variable-rate residual transformer (VResFormer) is proposed to control dynamic bit-rate by selectively modulating the high-frequency component according to coefficient weight and bias. Experimental results indicate that our ALIC outperforms other learned image compression algorithms. Our ALIC saves 5.89% bit-rate compared with VVC (4:4:4) on Kodak dataset. © 2025 ieee.

关键词： Entropy model Learned image compression Variable-rate

来源：评论

学校读者我要写书评

暂无评论

Imagined Speech and visual imagery as Intuitive Paradigms for Brain-Computer Interfaces 13

Imagined Speech and Visual Imagery as Intuitive Paradigms fo...

引用

13th international Winter conference on Brain-Computer Interface, BCI 2025

作者： Lee, Seo-Hyun Park, Ji-Ha Kim, Deok-Seon Dept. of Brain and Cognitive Engineering Korea University Seoul Korea Republic of Dept. of Artificial Intelligence Korea University Seoul Korea Republic of

ISBN: (纸本)9798331521929

Brain-computer interfaces (BCIs) have shown promise in supporting communication for individuals with motor or speech impairments. Recent advancements such as brain-to-speech or brain-to-image technology aim to reconstruct speech from neural activity. However, robust decoding of communication-related paradigms, such as imagined speech and visual imagery, using non-invasive techniques still remains challenging. This study analyzes brain dynamics in these two paradigms by examining neural synchronization and functional connectivity through phase-locking values (PLV) in noninvasively collected EEG data. Results show that visual imagery produces higher PLV values in visual cortex, engaging spatial networks, while imagined speech demonstrates consistent synchronization, primarily engaging language-related regions. These findings suggest that imagined speech is suitable for language-driven BCI applications, while visual imagery can complement BCI systems for users with speech impairments. Furthermore, the brain connectivity results implies that personalized calibration is crucial for optimizing BCI performance. © 2025 ieee.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

visual Decoding using a Learnable Wavelet-based Spatial-Spectral-Temporal EEG Embedding 13

Visual Decoding using a Learnable Wavelet-based Spatial-Spec...

引用

13th international Winter conference on Brain-Computer Interface, BCI 2025

作者： Choi, Yebin Kim, Jun-Mo Choi, WooHyeok Ji, Chang-Hoon Oh, Ji-Hye Kam, Tae-Eui Dept. Human-Centered Artificial Intelligence Sangmyung University Seoul Korea Republic of Dept. Artificial Intelligence Korea University Seoul Korea Republic of

ISBN: (纸本)9798331521929

visual decoding seeks to identify or reconstruct visual stimuli perceived by individuals based on neural activity. Although functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG) have achieved remarkable success in visual decoding, their high costs, limited portability, and real-time processing challenges necessitate alternative approaches. Electroencephalography (EEG) provides a promising solution due to its cost-effectiveness, high temporal resolution, and suitability for real-time applications. However, conventional EEG-based encoders often rely on simplistic architectures, which limits their ability to fully capture the spatial, spectral, and temporal (SST) features of EEG signals, leading to suboptimal performance. In this study, we propose a novel brain decoding framework utilizing a state-of-the-art EEG encoder specifically designed to capture the SST characteristics of EEG signals. The proposed framework was evaluated on the THINGS-EEG dataset. It achieved a mean top-1 accuracy of 19.7% and a top-5 accuracy of 50.7% in zero-shot retrieval tasks, outperforming conventional EEG encoders. These results demonstrate the potential of our method in advancing EEG-based visual decoding task. © 2025 ieee.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Spatial-Frequency Information Interaction Diffusion for SAR Colorization

Spatial-Frequency Information Interaction Diffusion for SAR ...

引用

2025 ieee international conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Zhang, Xupei Qin, Hanlin Li, Jingjing Geng, Jinni Gao, Zihan Yu, Yue School of Optoelectronic Engineering Xidian University Xi'an710071 China Xi'an Key Laboratory of Infrared Technology and System Xi'an710071 China

ISBN: (纸本)9798350368741

The inherent speckle noise and grayscale characteristics of synthetic aperture radar (SAR) images pose challenges to information perception and interpretation. To address this issue, we propose a novel conditional diffusion model with spatial-frequency information interaction for SAR colorization, namely SFI4SC. Specifically, we introduce a learnable wavelet transform module to obtain the global frequency information of the input SAR image and then take it as a guiding condition to assist the diffusion model for SAR colorization. Additionally, we improved the network structure for the diffusion model by designing and introducing a spatial and frequency information interaction module to achieve multidimensional information interaction for the network inputs, further enhancing perceptual details and geometric structures of the SAR colorization results. Experimental results in the real-world remote sensing dataset show that our approach can successfully enhance visual clarity and informational content while preserving the unique characteristics of the SAR images. The code will be made publicly available. © 2025 ieee.

关键词： Diffusion Model image colorization Spatial-Frequency Interaction Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Local Overlapping Attentional Selection with VIT for image Classification in Remote Sensing

Local Overlapping Attentional Selection with VIT for Image C...

引用

2025 international conference on Electronics, Information, and Communication, ICEIC 2025

作者： Zou, ChangMan Jeon, Wang-Su Rhee, Sang-Yong University of Kyungnam Department of IT Convergence Engineering Changwon51767 Korea Republic of College of Computer Science and Technology Beihua University Jilin132013 China University of Kyungnam Department of Computer Engineering Changwon51767 Korea Republic of

ISBN: (纸本)9798331510756

Remote sensing image classification presents unique challenges due to the complexity of the scenes and the variability in visual features caused by the overhead perspective. Traditional convolutional neural networks (CNNs) struggle with long-range dependencies and extracting sufficient context for accurate classification. To address this, we propose the LSViT model, a novel approach that incorporates a local attention selection module into the Transformer architecture, specifically designed for remote sensing scene classification. LSViT enhances the classification performance by selecting discriminative tokens and removing redundant information. Our model leverages the Transformer's capacity for capturing both global and local features, improving the focus on important image regions. We evaluate LSViT on two benchmark datasets, AID and NWPU-RESISC45, and demonstrate its competitive performance, achieving state-of-the-art accuracy compared to traditional CNN and other Transformer-based methods. Notably, the local attention selection module enhances the model's ability to classify scenes with overlapping objects and complex backgrounds, making it an effective solution for large-scale remote sensing image classification tasks. © 2025 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Guided Prompt Learning for Deepfake Facial image Detection

Knowledge-Guided Prompt Learning for Deepfake Facial Image D...

引用

2025 ieee international conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Wang, Hao Deng, Cheng Zhao, Zhidong School of Cyberspace Security Hangzhou Dianzi University Hangzhou China School of Electronic Engineering Xidian University Xi'an China

ISBN: (纸本)9798350368741

Recent generative models demonstrate impressive performance on synthesizing photographic images, which makes humans hardly to distinguish them from pristine ones, especially on realistic-looking synthetic facial images. Previous works mostly focus on mining discriminative artifacts from vast amount of visual data. However, they usually lack the exploration of prior knowledge and rarely pay attention to the domain shift between training categories (e.g., natural and indoor objects) and testing ones (e.g., fine-grained human facial images), resulting in unsatisfactory detection performance. To address these issues, we propose a novel knowledge-guided prompt learning method for deepfake facial image detection. Specifically, we retrieve forgery-related prompts from large language models as expert knowledge to guide the optimization of learnable prompts. Besides, we elaborate test-time prompt tuning to alleviate the domain shift, achieving significant performance improvement and boosting the application in real-world scenarios. Extensive experiments on DeepFakeFaceForensics dataset show that our proposed approach notably outperforms state-of-the-art methods. © 2025 ieee.

关键词： deepfake facial image detection domain shift knowledge-guided prompt learning test-time prompt tuning

来源：评论

学校读者我要写书评

暂无评论

Foveated HDR: Efficient HDR Content Generation on Edge Devices Leveraging User’s visual Attention 24

Foveated HDR: Efficient HDR Content Generation on Edge Devic...

引用

43rd international conference on Computer-Aided Design, ICCAD 2024

作者： Ying, Ziyu Bhuyan, Sandeepa Zhang, Yingtian Kang, Yan Kandemir, Mahmut T. Das, Chita R. The Pennsylvania State University State CollegePA United States

ISBN: (纸本)9798400710773

In recent years, high dynamic range (HDR) content has become increasingly popular for its ability to represent a broader brightness range, enhancing the realism and immersion in applications like augmented reality/virtual reality (AR/VR) on edge devices. While DNN-based solutions are effective for reconstructing high-fidelity HDR content, due to their high computational demands and memory usage, the DNN-based HDR reconstruction takes up to several seconds to generate one HDR image, making it very challenging to deploy such techniques onto the edge devices. Towards this, we propose Foveated HDR for efficient HDR content generation on edge devices by leveraging the "foveation nature" of human vision system and adaptively distributing the compute resources based on visual importance. Unlike the state-of-the-art works which treat all the pixels equally, we prioritize computational resources for the user’s view focus and reduce computation for unimportant regions. Specifically, Foveated HDR does not only dynamically identify the user’s focus of view, but also is a user-driven approach that tailors DNN inference speedup to individual user preferences. Furthermore, Foveated HDR carefully considers the employed DNN model architecture when performing foveated processing to preserve the quality of the generated HDR content. We implement and evaluate the proposed design using an edge GPU SoC (NVIDIA Jetson Orin Nano). The experimental results show that Foveated HDR can speedup the DNN inference by 3.6x, which translates to 75% energy saving, with negligible quality degradation. © 2024 Copyright is held by the owner/author(s).

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Enhancing Person Re-Identification Using Learnable Vision-Language Contexts and Orthogonal Constraints for Body Parts

Enhancing Person Re-Identification Using Learnable Vision-La...

引用

2025 international conference on Electronics, Information, and Communication, ICEIC 2025

作者： Han, Seunghee Park, Hasil Jeong, Dasol Lee, Hyebean Park, Jiwon Paik, Joonki Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Republic of

ISBN: (纸本)9798331510756

Recent advances in vision-language learning have significantly improved the performance of image re-identification (ReID) tasks. The CLIP-ReID approach, which introduced learnable text token sets for each identity, has been especially impactful in this area [1]. However, despite these advancements, current methods fall short in fully utilizing the detailed features of individual body parts. This gap is significant because capturing detailed features from segmented body parts is crucial for distinguishing individuals, especially in complex environments. Furthermore, these methods do not adequately address the issue of partial occlusion, which remains a major challenge in ReID scenarios where parts of the body are frequently obstructed. To tackle these limitations, we propose two complementary methods aimed at enhancing the discriminative power and ro-bustness of ReID systems. First, we suggest integrating learnable text tokens specifically for each body part, allowing the model to capture more granular and distinctive features from these regions. This approach helps the model to differentiate individuals more effectively based on localized visual cues. Second, we introduce Orthogonal Projection Loss (OPL) [2], a novel loss function designed to improve feature discriminability. By enforcing orthogonal constraints on the feature space, OPL promotes better separation between different classes, thus reducing the overlap in feature representations. These methods are essential for reducing the impact of occlusion and improving the reliability of ReID systems, making them more effective in real-world scenarios where parts of the body are frequently obscured by environmental factors. © 2025 ieee.

关键词： visual languages

来源：评论

学校读者我要写书评

暂无评论

Realistic Virtual Try-on with Multi-Loss Geometric Alignment and Attention-Augmented image Synthesis

Realistic Virtual Try-on with Multi-Loss Geometric Alignment...

引用

2025 international conference on Electronics, Information, and Communication, ICEIC 2025

作者： Lee, Hyebean Jeong, Dasol Han, Seunghee Park, Jiwon Paik, Joonki Graduate School of Advanced Imaging Science Multimedia Film Chung-Ang University Seoul Korea Republic of

ISBN: (纸本)9798331510756

We present a two-stage virtual try-on framework that combines complementary loss functions with an attention-augmented U-Net to enhance clothing detail preservation and garment-body interaction modeling. In the first stage, the Geometric Matching Module (GMM) introduces complementary loss functions: shape loss for maintaining the structural integrity of the garment, texture loss for preserving detailed appearance and pattern consistency, edge loss for boundary detail and structural line clarity, and grid loss to prevent pattern distortion during garment deformation. In the second stage, the Try-On Module (TOM) augments the U-Net with encoder-based self-attention for global context capture, skip connection-based cross-attention for selective spatial feature refinement, and positional encoding to establish accurate garment-body spatial correlations. This integration improves both the visual quality and geometric accuracy of generated virtual try-on images, enabling realistic and detailed garment synthesis suitable for practical applications such as online retail platforms, virtual fitting rooms, and personalized styling recommendations. Our approach allows consumers to visualize apparel fit and style on a digital self-representation, offering a seamless, interactive experience that can reduce return rates and enhance customer satisfaction. Experiments show that our method outperforms existing virtual try-on systems, marking a notable advancement in the development of practical, consumer-focused virtual try-on technology. © 2025 ieee.

关键词： Customer satisfaction

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251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：