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

25,250 篇 会议
280 篇 期刊文献
21 册 图书
3 篇 学位论文

馆藏范围

25,554 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,801 篇 工学
- 9,866 篇 计算机科学与技术...
- 6,079 篇 电气工程
- 5,768 篇 信息与通信工程
- 5,611 篇 软件工程
- 2,017 篇 光学工程
- 1,448 篇 控制科学与工程
- 1,280 篇 机械工程
- 1,153 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
- 794 篇 仪器科学与技术
- 261 篇 网络空间安全
- 253 篇 化学工程与技术
- 244 篇 安全科学与工程
- 238 篇 交通运输工程
- 183 篇 材料科学与工程（可...
- 164 篇 土木工程
- 161 篇 建筑学
5,714 篇 理学
- 3,481 篇 物理学
- 2,204 篇 数学
- 886 篇 生物学
- 563 篇 统计学（可授理学、...
- 420 篇 系统科学
- 310 篇 化学
3,021 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...
1,387 篇 管理学
- 849 篇 管理科学与工程(可...
- 610 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

3,121 篇 image processing
2,084 篇 image coding
2,021 篇 visualization
1,752 篇 image segmentati...
1,488 篇 feature extracti...
1,082 篇 image reconstruc...
907 篇 cameras
885 篇 signal processin...
833 篇 image color anal...
756 篇 humans
714 篇 image edge detec...
688 篇 image enhancemen...
665 篇 computer vision
650 篇 training
582 篇 image analysis
568 篇 deep learning
536 篇 image quality
481 篇 conferences
473 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

24,744 篇 英文
489 篇 土耳其文
206 篇 其他
131 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 25554 条记录，以下是401-410 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：

DATASET-LEVEL DIRECTED image TRANSLATION FOR CROSS-DOMAIN CROWD COUNTING 30

DATASET-LEVEL DIRECTED IMAGE TRANSLATION FOR CROSS-DOMAIN CR...

引用

30th ieee International conference on image processing (ICIP)

作者： Tan, Xin Ishikawa, Hiroshi Waseda Univ Dept Comp Sci & Engn Tokyo Japan

ISBN: (纸本)9781728198354

Most crowd counting methods rely on a large amount of manually labeled data to train a supervised model. With the availability of synthetic dataset, one way to alleviate the scarcity of large-scale dataset is to use an image-to-image translation method to adapt synthetic data for training. However, previous methods focus on adapting local visual feature of the image, which leads to distorted and blurry translation results. In this paper, we propose a novel CLIP-guided image-to-image translation method, based on the observation that synthetic and real images can be easily separated in CLIP's embedding space. We make use of the difference between two domains in the CLIP-space as a consistent guide to train an image translator. Then a crowd counting model is trained using images translated from synthetic data by the translator. Experiments on real-world crowd counting datasets demonstrate the effectiveness of the proposed method which enables the crowd counting model to achieve a state-of-the-art performance.

关键词： Crowd counting Domain adaptation image-to-image translation

来源：评论

学校读者我要写书评

暂无评论

TriFormer: Triple Branch Heterogeneous Transformers for UHD image Restoration

TriFormer: Triple Branch Heterogeneous Transformers for UHD ...

引用

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

作者： Ma, Xinchen Lu, Yue School of Communication and Electronic Engineering East China Normal University Shanghai China

ISBN: (纸本)9798350368741

Ultra-high-definition (UHD) image restoration is becoming a critical research area due to the increasing demand for high-quality visual content in various applications, including autonomous driving, remote sensing, digital entertainment, etc. However, UHD image restoration tasks present notable challenges, including the significant computational burden posed by the large image size scale, the difficulty in preserving fine details and textures, and the increased susceptibility to noise and artifacts during the restoration process. In this paper, we propose a novel triple-branched optimized heterogeneous transformer for UHD image restoration, named TriFormer. Specifically, our method embeds a high-resolution CNN branch for high-frequency features, a low-resolution pixel-wise attention branch for low-frequency features, and a channel-wise attention branch for feature fusion. We perform experiments across two UHD image restoration tasks: enhancing low-light images and deblurring. Results demonstrate that our model outperforms state-of-the-art approaches both quantitatively and qualitatively. The code will be made available at https://***/Chloemxxxxc/TRIFORMER. © 2025 ieee.

关键词： image restoration transformer Ultra-high-definition(UHD)

来源：评论

学校读者我要写书评

暂无评论

EVCAP: Retrieval-Augmented image Captioning with External visual-Name Memory for Open-World Comprehension

EVCAP: Retrieval-Augmented Image Captioning with External Vi...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Jiaxuan Vo, Duc Minh Sugimoto, Akihiro Nakayama, Hideki Univ Tokyo Tokyo Japan Natl Inst Informat Tokyo Japan

ISBN: (纸本)9798350353006

Large language models (LLMs)-based image captioning has the capability of describing objects not explicitly observed in training data;yet novel objects occur frequently, necessitating the requirement of sustaining up-to-date object knowledge for open-world comprehension. Instead of relying on large amounts of data and/or scaling up network parameters, we introduce a highly effective retrieval-augmented image captioning method that prompts LLMs with object names retrieved from External visual-name memory (EVCAP). We build ever-changing object knowledge memory using objects' visuals and names, enabling us to (i) update the memory at a minimal cost and (ii) effortlessly augment LLMs with retrieved object names by utilizing a lightweight and fast-to-train model. Our model, which was trained only on the COCO dataset, can adapt to out-of-domain without requiring additional fine-tuning or re-training. Our experiments conducted on benchmarks and synthetic commonsense-violating data show that EV-CAP, with only 3.97M trainable parameters, exhibits superior performance compared to other methods based on frozen pre-trained LLMs. Its performance is also competitive to specialist SOTAs that require extensive training.

关键词： External Memory image Captioning LLM Open-World Comprehension Retrieval-Augmented

来源：评论

学校读者我要写书评

暂无评论

SignTrack: Advancements in Real-Time Sign Language processing for Inclusive Computing with optimized AI 13

SignTrack: Advancements in Real-Time Sign Language Processin...

引用

13th International conference on Modern Circuits and Systems Technologies (MOCAST)

作者： Piperakis, Stavros Papatsimouli, Maria Argyriou, Vasilis Sarigiannidis, Panagiotis Fragulis, George F. Univ Western Macedonia Dept Elect & Comp Engn ZEP Campus Kozani 50100 Greece Kingston Univ Dept Networks & Digital Media Kingston England

ISBN: (纸本)9798350385434;9798350385427

visual-based translator systems, which utilize image and video data for real-time translation, represent a captivating research area. While previous research has explored text-based translation, limitations exist in capturing the nuances of human communication. visual-based approaches address this gap by leveraging deep learning and image processing to extract information like objects, faces, and environmental context. This research project investigates the application of deep learning in sign language translation using Automated AI. By analyzing visual data, the system recognizes signs and translates them into spoken languages or generates text descriptions. This technology holds significant promise for various fields - education, entertainment, tourism, and healthcare - and can contribute to the advancement of information technology and artificial intelligence systems.

关键词： Automated AI IoT Sign Language Sign language transcription

来源：评论

学校读者我要写书评

暂无评论

OSLO-IC: On-the-Sphere Learned Omnidirectional image Compression with Attention Modules and Spatial Context

OSLO-IC: On-the-Sphere Learned Omnidirectional Image Compres...

引用

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

作者： Wawerek-López, Paul Bidgoli, Navid Mahmoudian Frossard, Pascal Kaup, André Maugey, Thomas Multimedia Communications and Signal Processing Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Lausanne Switzerland Rennes France

ISBN: (纸本)9798350368741

Developing effective 360-degree (spherical) image compression techniques is crucial for technologies like virtual reality and automated driving. This paper advances the state-of-the-art in on-the-sphere learning (OSLO) for omnidirectional image compression framework by proposing spherical attention modules, residual blocks, and a spatial autoregressive context model. These improvements achieve a 23.1% bit rate reduction in terms of WS-PSNR BD rate. Additionally, we introduce a spherical transposed convolution operator for upsampling, which reduces trainable parameters by a factor of four compared to the pixel shuffling used in the OSLO framework, while maintaining similar compression performance. Therefore, in total, our proposed method offers significant rate savings with a smaller architecture and can be applied to any spherical convolutional application. © 2025 ieee.

关键词： 360-degree end-to-end compression image compression spherical transposed convolution

来源：评论

学校读者我要写书评

暂无评论

image Compressed Sensing Based on Vision-Inspired Importance Maps

Image Compressed Sensing Based on Vision-Inspired Importance...

引用

2024 ieee International conference on Imaging Systems and Techniques, IST 2024

作者： Yoshida, Shunra Sun, Zhe Yoshizawa, Shin Michikawa, Takashi Noda, Shigeho Micheletto, Ruggero Yokota, Hideo Yokohama City University Department of Materials System Science 22-2 Seto Kanazawa-ku Yokohama Kanagawa236-0027 Japan Riken Center for Advanced Photonics Riken Image Processing Research Team 2-1 Hirosawa Wako Saitama351-0198 Japan

ISBN: (纸本)9798350378214

This paper presents a novel image compressed sensing framework that leverages human vision-inspired importance maps to guide the compression process. Unlike traditional methods that compress images without considering perceptual relevance, our approach selectively samples pixels based on their visual saliency and geometric significance. The framework begins by generating an importance map that combines visual saliency, obtained through LayerCAM, with geometric features like edge information. These maps dictate the adaptive sampling of pixels, ensuring that the most visually important information is retained. In the decoding stage, the sampled pixels are reconstructed using prior information-based models such as the Deep image Prior and Manifold Modeling in Embedded Space. These models effectively restore the image while preserving its critical visual characteristics. To evaluate the performance of our framework, we introduce two new similarity criteria: Weighted PSNR (WPSNR) and Weighted SSIM (WSSIM), both tailored to assess the perceptual quality of images. Our experimental results demonstrate that the proposed method outperforms conventional image compression techniques, especially in maintaining perceptual quality at low sampling rates. This framework shows great promise for applications in areas where preserving visual fidelity is crucial, such as high-quality image compression and digital brain modeling. The integration of visual importance into the compression process represents a significant advancement in the field of image processing, offering a more efficient and perceptually aware approach to image compression. © 2024 ieee.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

LEARNED image COMPRESSION FOR BOTH HUMANS AND MACHINES VIA DYNAMIC ADAPTATION 31

LEARNED IMAGE COMPRESSION FOR BOTH HUMANS AND MACHINES VIA D...

引用

2024 International conference on image processing

作者： Zhu, Lingyu Li, Binzhe Lu, Riyu Chen, Peilin Mao, Qi Wang, Zhao Yang, Wenhan Wang, Shiqi City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China City Univ Hong Kong Shenzhen Res Inst Shenzhen Peoples R China Commun Univ China Beijing Peoples R China Peking Univ Beijing Peoples R China PengCheng Lab Shenzhen Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Recent advancements in neural image compression have shown great potential in outperforming conventional standard codecs in terms of both rate-distortion and rate-analysis performance. However, there is an issue of divergent preferences in information preservation or reconstruction in the process of compression for humans and machines, respectively. Compression for humans tends to retain the signal fidelity or perceptual quality of visual appearance while compression for machines requires preserving critical semantic information, resulting in the limitation of the bitstream supporting only a single requirement during the compression. To bridge this gap, we propose a dynamic adaptation approach that generates a single bitstream serving both humans and machines. This approach aims to mitigate the domain gap among tasks, which facilitates maintaining the performance of out-of-scope tasks. Specifically, the proposed method concentrates on learning a dynamic adaptation process, i.e., optimizing the latent representation in the compressed domain in an end-to-end manner while adhering to the rate-performance constraint. Extensive results reveal that our paradigm significantly reduces the domain gap, surpassing existing codecs.

关键词： Learned image compression dynamic adaptation and human-machine collaboration

来源：评论

学校读者我要写书评

暂无评论

Lane Type Classification & Distance Measurement System for Autonomous Vehicle

Lane Type Classification & Distance Measurement System for A...

引用

31st ieee conference on Signal processing and communications Applications (SIU)

作者： Ozen, Sinan Kaya, Uygar Semiz, Abdurrahim Yalcin, Mustafa Fatih Celebi, Aysun Tasyapi AVL Arastirma Muhendislik Turkiye Istanbul Turkiye Kocaeli Univ Elekt & Haberlesme Muhendisligi Istanbul Turkiye Ozyegin Univ Bilgisayar Muhendisligi Istanbul Turkiye Istanbul Tech Univ Kontrol & Otomasyon Muhendisligi Istanbul Turkiye Yildiz Tekn Univ Kontrol & Otomasyon Muhendisligi Istanbul Turkiye

ISBN: (纸本)9798350343557

In this paper, lane type classification and lane distance measurement system are proposed for autonomous vehicles. In the proposed system, the perspective transformation method is applied to the image taken from the vehicle camera, so that a bird's-eye view is obtained and the parts with stripes are cropped from the image, and then a multi-class classification model is implemented using neural network-based architectures to determine the stripe type. In addition, with the proposed distance measurement system, the distance of the vehicle to the right and left lanes is calculated during autonomous driving, thus ensuring that the vehicle can drive autonomously on the lane. For this study, our own data set has been created.

关键词： deep learning image processing custom dataset lane type classification lane distance measurement

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Histogram Threshold Segmentation - Auto-terminating High-detail Oversegmentation

Hierarchical Histogram Threshold Segmentation - Auto-termina...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chang, Thomas V. Seibt, Simon Lipinski, Bartosz von Rymon Nuremberg Inst Technol Game Tech Lab Fac Comp Sci Nurnberg Germany

ISBN: (纸本)9798350353013;9798350353006

Superpixels play a crucial role in image processing by partitioning an image into clusters of pixels with similar visual attributes. This facilitates subsequent image processing tasks, offering computational advantages over the manipulation of individual pixels. While numerous oversegmentation techniques have emerged in recent years, many rely on predefined initialization and termination criteria. In this paper, a novel top-down superpixel segmentation algorithm called Hierarchical Histogram Threshold Segmentation (HHTS) is introduced. It eliminates the need for initialization and implements auto-termination, outperforming state-of-the-art methods w.r.t. boundary recall. This is achieved by iteratively partitioning individual pixel segments into foreground and background and applying intensity thresholding across multiple color channels. The underlying iterative process constructs a superpixel hierarchy that adapts to local detail distributions until color information exhaustion. Experimental results demonstrate the superiority of the proposed approach in terms of boundary adherence, while maintaining competitive runtime performance on the BSDS500 and NYUV2 datasets. Furthermore, an application of HHTS in refining machine learning-based semantic segmentation masks produced by the Segment Anything Foundation Model (SAM) is presented.

关键词： Color Histogram Hierarchical Segmentation image Segmentation Superpixel Thresholding

来源：评论

学校读者我要写书评

暂无评论

DEEP FUSION OF VISIBLE AND NEAR INFRARED imageS FOR REGISTRATION AND DEFOGGING USING CROSS MODAL TRANSFORMER 31

DEEP FUSION OF VISIBLE AND NEAR INFRARED IMAGES FOR REGISTRA...

引用

2024 International conference on image processing

作者： Ji, Mengyao Jung, Cheolkon Xidian Univ Sch Elect Engn Xian 710071 Peoples R China

ISBN: (纸本)9798350349405;9798350349399

According to Rayleigh scattering, the density of fog is closely related to the distance of the target from the visible light camera. However, the near infrared (NIR) spectral band is robust to the interference problem but has a single channel without color. In this paper, we propose deep fusion of visible (VIS) and near infrared (NIR) images for registration and defogging using cross modal transformer. The proposed fusion network has two main features: 1) Cross modal transformer deals with the channel and spatial redundancy between two source images while retaining their complementary information;2) Since the blue channel in VIS image can represent the amount of fog in the scene according to Rayleigh scattering, we normalize it to obtain a fog weight map. To synthesize training data, the distance between object and camera is required, thus we use depth estimation to obtain it. Then, we assign different amounts of fog to each image to consider various weather conditions. First, we extract multi-scale features from the source images. Second, we use the cross modal transformer to reflect cross-domain interaction between the source images in spatial and channel domains. Third, we generate the fusion weight for the source images according to the fog weight map and reconstruct a fused result based on it. Various experiments on the widely-used benchmark and real-world datasets show that the proposed method generates natural-looking defogging results with clear textures in distant regions while keeping the original tone in near regions. Moreover, the proposed method outperforms state-of-the-art fusion methods in term of both visual quality and quantitative measurements.

关键词： image fusion cross modal transformer defogging multi-modal images near-infrared registration transfer learning

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 << < 37 38 39 40 41 42 43 44 45 46 > >>

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：