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

4,508 篇 会议
47 篇 期刊文献
18 册 图书
1 篇 学位论文

馆藏范围

4,574 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,611 篇 工学
- 1,701 篇 计算机科学与技术...
- 1,115 篇 信息与通信工程
- 992 篇 软件工程
- 699 篇 电气工程
- 282 篇 光学工程
- 125 篇 电子科学与技术（可...
- 119 篇 控制科学与工程
- 119 篇 生物工程
- 105 篇 仪器科学与技术
- 100 篇 网络空间安全
- 95 篇 生物医学工程（可授...
- 72 篇 机械工程
- 45 篇 化学工程与技术
- 32 篇 安全科学与工程
- 31 篇 动力工程及工程热...
- 26 篇 轻工技术与工程
1,247 篇 医学
- 1,237 篇 临床医学
- 35 篇 基础医学(可授医学...
- 29 篇 药学(可授医学、理...
1,045 篇 理学
- 748 篇 物理学
- 339 篇 数学
- 128 篇 生物学
- 105 篇 统计学（可授理学、...
- 50 篇 化学
- 48 篇 系统科学
192 篇 管理学
- 105 篇 管理科学与工程(可...
- 98 篇 图书情报与档案管...
- 32 篇 工商管理
77 篇 军事学
- 74 篇 军队指挥学
38 篇 法学
- 30 篇 社会学
10 篇 文学
8 篇 经济学
7 篇 农学
6 篇 教育学

主题

552 篇 image coding
471 篇 image processing
353 篇 visual communica...
317 篇 visualization
276 篇 image segmentati...
260 篇 feature extracti...
181 篇 image compressio...
168 篇 video coding
165 篇 image reconstruc...
158 篇 cameras
153 篇 humans
137 篇 image quality
132 篇 image retrieval
126 篇 training
123 篇 image edge detec...
123 篇 image color anal...
115 篇 image enhancemen...
115 篇 image analysis
113 篇 signal processin...
110 篇 motion estimatio...

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
28 篇 school of electr...
24 篇 school of electr...
21 篇 university of sc...
18 篇 shanghai jiao to...
17 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
14 篇 institute for in...
11 篇 school of comput...
11 篇 university of el...
11 篇 cas key laborato...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 zhejiang univers...
10 篇 peking univ inst...
10 篇 institute of ima...
9 篇 microsoft resear...
9 篇 tsinghua univ de...

作者

34 篇 zhai guangtao
26 篇 sumei li
25 篇 song li
22 篇 li sumei
21 篇 guangtao zhai
19 篇 li song
18 篇 li li
17 篇 min xiongkuo
16 篇 dong liu
16 篇 wen gao
16 篇 shan liu
15 篇 andré kaup
15 篇 yang xiaokang
14 篇 chen zhibo
13 篇 m. vetterli
13 篇 xie rong
13 篇 xiongkuo min
13 篇 gao wen
11 篇 heming sun
11 篇 zhibo chen

语言

4,365 篇 英文
152 篇 其他
49 篇 土耳其文
49 篇 中文

检索条件"任意字段=Conference on Visual Communications and Image Processing 2003"

共 4574 条记录，以下是1071-1080 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：

Deep Inter Prediction via Reference Frame Interpolation for Blurry Video Coding

Deep Inter Prediction via Reference Frame Interpolation for ...

引用

IEEE visual communications and image processing (VCIP)

作者： Zezhi Zhu Lili Zhao Xuhu Lin Xuezhou Guo Jianwen Chen School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781728173221

In High Efficiency Video Coding (HEVC), inter prediction is an important module for removing temporal redundancy. The accuracy of inter prediction is much affected by the similarity between the current and reference frames. However, for blurry videos, the performance of inter coding will be degraded by varying motion blur, which is derived from camera shake or the acceleration of objects in the scene. To address this problem, we propose to synthesize additional reference frame via the frame interpolation network. The synthesized reference frame is added into reference picture lists to supply more credible reference candidate, and the searching mechanism for motion candidates is changed accordingly. In addition, to make our interpolation network more robust to various inputs with different compression artifacts, we establish a new blurry video database to train our network. With the well-trained frame interpolation network, compared with the reference software HM-16.9, the proposed method achieves on average 1.55% BD-rate reduction under random access (RA) configuration for blurry videos, and also obtains on average 0.75% BD-rate reduction for common test sequences.

关键词： Interpolation image coding visual communication Databases Redundancy Cameras Software

来源：评论

学校读者我要写书评

暂无评论

Alignment-Free Video Compression Artifact Reduction

Alignment-Free Video Compression Artifact Reduction

引用

IEEE visual communications and image processing (VCIP)

作者： Dengyan Luo Mao Ye Shengjie Chen Xue Li University of Electronic Science and Technology of China The University of Queensland

ISBN: (纸本)9781728173221

The past few years have witnessed the great success of using multi-frame information to enhance the quality of compressed video. Most existing methods do frame or feature alignments to bring similar information from neighborhood frames much closer to enhance frame quality. However, inaccurate motion estimation will bring new artifacts. In this paper, we propose a new approach without alignment, which takes each non-Peak Quality Frame (non-PQF) and its two adjacent Peak Quality Frames (PQFs) as input. A Pre-processing module based on multi-scale feature extraction strategy is used to broaden receptive field of the network. Then, an enhancement module uses a two-stream feature extraction architecture to combine deep architecture and attention mechanism to further gather similar information. In this module, the lost high-frequency and similar information can be further retrieved from the adjacent PQFs. The proposed network is trained in an end-to-end manner. Compared with the alignment based methods, the competitive results can be obtained. A large number of qualitative and quantitative experimental results demonstrate the robustness and effectiveness of the proposed method.

关键词： image coding visual communication Motion estimation Deep architecture Video compression Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification

Seq-Masks: Bridging the gap between appearance and gait mode...

引用

IEEE visual communications and image processing (VCIP)

作者： Zhigang Chang Zhao Yang Yongbiao Chen Qin Zhou Shibao Zheng Institute of Image Processing and Network Engineering Shanghai Jiao Tong University Shanghai China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781728173221

Video-based person re-identification (Re-ID) aims to match person images in video sequences captured by disjoint surveillance cameras. Traditional video-based person Re-ID methods focus on exploring appearance information, thus, vulnerable against illumination changes, scene noises, camera parameters, and especially clothes/carrying variations. Gait recognition provides an implicit biometric solution to alleviate the above headache. Nonetheless, it experiences severe performance degeneration as camera view varies. In an attempt to address these problems, in this paper, we propose a framework that utilizes the sequence masks (SeqMasks) in the video to integrate appearance information and gait modeling in a close fashion. Specifically, to sufficiently validate the effectiveness of our method, we build a novel dataset named MaskMARS based on MARS. Comprehensive experiments on our proposed large wild video Re-ID dataset MaskMARS evidenced our extraordinary performance and generalization capability. Validations on the gait recognition metric CASIA-B dataset further demonstrated the capability of our hybrid model. Our codes and dataset MaskMARS will be open-sourced as a strong baseline.

关键词： Measurement Mars image recognition Codes visual communication Surveillance Video sequences

来源：评论

学校读者我要写书评

暂无评论

Learn to overfit better: finding the important parameters for learned image compression

Learn to overfit better: finding the important parameters fo...

引用

IEEE visual communications and image processing (VCIP)

作者： Honglei Zhang Francesco Cricri Hamed Rezazadegan Tavakoli Maria Santamaria Yat-Hong Lam Miska M. Hannuksela Nokia Technologies Finland

ISBN: (纸本)9781728173221

For most machine learning systems, overfitting is an undesired behavior. However, overfitting a model to a test image or a video at inference time is a favorable and effective technique to improve the coding efficiency of learning-based image and video codecs. At the encoding stage, one or more neural networks that are part of the codec are finetuned using the input image or video to achieve a better coding performance. The encoder en-codes the input content into a content bitstream. If the finetuned neural network is part (also) of the decoder, the encoder signals the weight update of the finetuned model to the decoder along with the content bitstream. At the decoding stage, the decoder first updates its neural network model according to the received weight update, and then proceeds with decoding the content bitstream. Since a neural network contains a large number of parameters, compressing the weight update is critical to reducing bitrate overhead. In this paper, we propose learning-based methods to find the important parameters to be overfitted, in terms of rate-distortion performance. Based on simple distribution models for variables in the weight update, we derive two objective functions. By optimizing the proposed objective functions, the importance scores of the parameters can be calculated and the important parameters can be determined. Our experiments on lossless image compression codec show that the proposed method significantly outperforms a prior-art method where overfitted parameters were selected based on heuristics. Furthermore, our technique improved the compression performance of the state-of-the-art lossless image compression codec by 0.1 bit per pixel.

关键词： Learning systems image coding visual communication Neural networks Bit rate Rate-distortion Machine learning

来源：评论

学校读者我要写书评

暂无评论

Person search by natural language description in Vietnamese using pre-trained visual-textual attributes alignment model 13

Person search by natural language description in Vietnamese ...

引用

13th International conference Knowledge and Systems Engineering, KSE 2021

作者： Thuy Pham, Thi Thanh Nguyen, Van-Thanh Nguyen, Hong-Quan Le, Minh-Quan Phan, Hoai Do, Thi-Ngoc-Diep Nguyen, Thuy-Binh Tran, Thanh-Hai Le, Thi-Lan Academy of People Security Faculty of Information Security Hanoi Viet Nam Hanoi University of Science and Technology School of Electronics and Telecommunications Hanoi Viet Nam Viet-Hung Industrial University Faculty of Information Technology Hanoi Viet Nam Hanoi University of Science and Technology Mica Hanoi Viet Nam University of Transport and Communications Faculty of Electrical and Electronics Engineering Hanoi Viet Nam

ISBN: (纸本)9781665499750

Person search by natural language description is a challenging task as it has to model and learn visual-text semantic embedding. While several works have been dedicated to person search by English descriptions, few attempts have been made for other languages. As a result, it lacks of available resource for person search in these languages. Inspired by transfer learning idea in image classification, in this paper, we propose a method for person search by natural language description in Vietnamese using a model whose weights are trained on a large scale dataset for person search in English. To this end, first, the published network architecture of ViTAA that allows to learn effectively the alignment between visual and textual attributes is employed in this work. Then, we propose to apply different techniques for Vietnamese language processing to analyze and extract relevant elements from descriptions in Vietnamese to feed to the network. Finally, to leverage the information learnt from a large scale dataset, we employ model weights trained from a large scale dataset to a dataset dedicated to person search by natural language description in Vietnamese - VnPersonSearch. The obtained accuracies at Top-1, Top-5 and Top-10 for VnPersonSearch are 61.57%, 83.93% and 90.67% respectively. This means that the proposed method can return relevant persons with very high accuracy in first ten results. © 2021 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on image text generation based on word2vec visual vocabulary attention

Research on image text generation based on word2vec visual v...

引用

communications Technology and Computer Science (ACCTCS), Asia-Pacific conference on

作者： Danyang Li Yahui Zhao Rongyi Cui Linlin Zhao Intelligent Information Processing Lab. Yanbian University Yanji Jilin China

ISBN: (纸本)9781665447034

A method of image text generation based on the combination of word2vec keyword extraction and attention mechanism is proposed. First, the co-occurring words with visual entities in the description set were extracted for each image in the dataset; Then the similarity was calculated for the extracted keywords, the similar words were filtered out to expand the keyword list, and the words in the vocabulary were retained to create new descriptions for the images. Finally, the test set images were combined with attention mechanism to generate description text. The experiments prove that the method proposed in this paper can achieve automatic annotation of images and can effectively solve the attention diffusion problem in the process of image text generation.

关键词： Computer science Vocabulary visualization Annotations communications technology

来源：评论

学校读者我要写书评

暂无评论

JADD-GAN: A Joint Attention Generative Adversarial Data Fusion Network for Object Detection and Tracking

JADD-GAN: A Joint Attention Generative Adversarial Data Fusi...

引用

IEEE International conference on High Performance Computing and communications (HPCC)

作者： Guoxia Xu Hao Wang Meng Zhao Hu Zhu Department of Computer Science Norwegian University of Science and Technology Gjøvik Norway School of Computer Science and Engineering Tianjin University of Technology Tianjin China School of Communications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China

image fusion is the fusion of images captured by different sensors to generate a single image with enhanced information, and fusion technology, as one of the important branches in the field of information fusion, mainly realizes the processing of multi-source image information. However, many commonly used fusion methods usually ignore the visual naturalness and information fidelity of the fused images and lack emphasis on the salient information, which makes the fused images unsuitable for human visual perception. To address these shortcomings of existing methods, in this paper, we propose the Joint Attention and Dual Discriminator Generative Adversarial Data Fusion Network JADD-GAN. In the generator module, to increase the extraction of multi-level information by the network, we firstly adopt a dual encoder structure and give information fusion in the decoder part. Secondly, different discriminators are used for infrared and visible images in order to highlight the thermal radiation information and key textures. The effectiveness of the method is verified by experiments on four datasets, and the results show that the method can effectively highlight the thermal radiation information and key texture details of the fused images, fully demonstrating its great potential and performance in solving the infrared and visible images fusion (IVF) problem.

关键词： visualization Data integration Object detection Sensor fusion Feature extraction Generators Sensors

来源：评论

学校读者我要写书评

暂无评论

image Captioning Using Deep Learning Models: A Comprehensive Overview 6th

Image Captioning Using Deep Learning Models: A Comprehensive...

引用

6th International conference on Artificial Intelligence and Speech Technology, AIST 2024

作者： Nisha Kamble, Shailesh D. Mittal, Himanshu Department of Artificial Intelligence and Data Science Indira Gandhi Delhi Technical University for Women New Delhi India

ISBN: (纸本)9783031913396

Person with impaired vision have faced issues while understanding and interacting with pictures and videos. image captioning enhance their capacity to deal with visual content by creating descriptive language, that makes the images more accessible and engaging. This technique generates relevant captions from visual data by connecting visual feature extraction and language modeling. It acts as a key connector between computer vision and natural language processing, that allows machines to analyze and describe pictures. This article examines the developments of models, such as encoder-decoder frameworks and attention processes, that combine visual feature extraction with language creation and focusing on how object identification improves caption accuracy and contextual relevance. The study discusses on various deep learning models and also highlights various evaluation metrics like BLEU, ROUGE, and CIDEr, which measure the quality of generated captions. Moreover, the paper addresses potential improvements and prospects in image captioning systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cross Component Sample Adaptive Offset for AVS3

Enhanced Cross Component Sample Adaptive Offset for AVS3

引用

IEEE visual communications and image processing (VCIP)

作者： Yunrui Jian Jiaqi Zhang Junru Li Suhong Wang Shanshe Wang Siwei Ma Wen Gao Shenzhen Graduate School Peking University Shenzhen China University of Chinese Academy of Science Beijing China Institute of Digital Media Peking University Beijing China

ISBN: (纸本)9781728173221

Cross-component prediction has great potential for removing the redundancy of multi-components. Recently, cross-component sample adaptive offset (CCSAO) was adopted in the third generation of Audio Video coding Standard (AVS3), which utilizes the intensities of co-located luma samples to determine the offsets of chroma sample filters. However, the frame-level based offset is rough for various content, and the edge information of classified samples is ignored. In this paper, we propose an enhanced CCSAO (ECCSAO) method to further improve the coding performance. Firstly, four selectable 1-D directional patterns are added to make the mapping between luma and chroma components more effectively. Secondly, one four-layer quad-tree based structure is designed to improve the filtering flexibility of CCSAO. Experimental results show that the proposed approach achieves 1.51%, 2.33% and 2.68% BD-rate savings for All-Intra (AI), Random-Access (RA) and Low Delay B (LD) configurations compared to AVS3 reference software, respectively. A subset improvement of ECCSAO has been adopted by AVS3.

关键词： image coding visual communication Simulation Urban areas Redundancy Information filters Software

来源：评论

学校读者我要写书评

暂无评论

Probability-based decoder-side intra mode derivation for VVC

Probability-based decoder-side intra mode derivation for VVC

引用

IEEE visual communications and image processing (VCIP)

作者： Yang Wang Li Zhang Kai Zhang Yuwen He Hongbin Liu Multimedia Lab Bytedance Inc.

ISBN: (纸本)9781728173221

Intra prediction is typically used to exploit the spatial redundancy in video coding. In the latest video coding standard Versatile Video Coding (VVC), 67 intra prediction modes are adopted in intra prediction. The encoder selects the best one from 67 modes and signals it to the decoder. Bits consuming of signaling the selected mode may limit the coding efficiency. To reduce the overhead of signaling the intra prediction mode, a probability-based decoder-side intra mode derivation (P-DIMD) is proposed in this paper. Specifically, an intra prediction mode candidate set is constructed based on the probabilities of intra prediction modes. The probability of an intra prediction mode is mainly estimated in two ways. First, the textures are typically continuous within a local region and intra prediction modes of neighboring blocks are similar to each other. Second, some intra prediction modes are preferable to be used than others. For each intra prediction mode in the constructed candidate set, intra prediction is processed on a template to calculate a cost. The intra prediction mode with the minimum cost is determined as the optimal mode and used in the intra prediction of the current block. Experimental results demonstrate that P-DIMD can achieve 0.56% BD-rate saving on average compared to VTM-11.0 under all intra configuration.

关键词： Video coding Costs image coding visual communication Redundancy Decoding Artificial intelligence

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458页 << < 104 105 106 107 108 109 110 111 112 113 > >>

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：