检索结果-内蒙古大学图书馆

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Jun Huang Xiaokang Yang Rui Zhang Xiangzhong Fang Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781424444618

The paper focuses on two mechanisms, multiscale relevance and visual saliency, in web image search. First, in most current web image search engines, such as Google image Search, Yahoo image Search and so on, people judge the relevance of search results by the thumbnails and then click through the thumbnails to check if the corresponding image is really relevant. Basically the thumbnail and the corresponding image give the multiscale representations of the image. The second is that from visual point of view, it is obvious that salient images would be easier to catch users' eyes and more likely to be clicked than cluttered ones in low-level vision. In this paper, we build a multiscale saliency model and apply it to re-rank the results from web image search engines. Experimental results show that the model can achieve an average precision (AP) of as high as 97%, and it improves the results of Google image search significantly.

关键词： Search engines Airplanes Humans Support vector machines Information retrieval image communication Information processing Laboratories Eyes Internet

来源：评论

学校读者我要写书评

暂无评论

THz Spectrum Deconvolution with Total Variation Regularization

THz Spectrum Deconvolution with Total Variation Regularizati...

引用

International Congress on image and Signal processing

作者： Lizhen Deng Hu Zhu Guanming Lu State Key Laboratory of Advanced Electromagnetic Engineering and Technology Huazhong University of Science and Technology Wuhan 430074 China Jiangsu Province Key Lab on Image Processing & Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9781479927654

Deconvolution has become one of the most used methods for improving spectral resolution, and blind deconvolution as a typical method has been researched widely. However, the predefined point spread function (PSF) used in blind deconvolution method is not known exactly in practice. In general, the PSF is estimated simultaneously from the observed spectrum, but it becomes difficult when the spectroscopic data are polluted by strong noise. In this paper, we present a deconvolution method used to improve the resolution of THz spectrum. In the method, the energy function is constructed, which includes the likelihood term, Total variation of spectrum term and L2 norm of the PSF term. The PSF is modeled as a parametric function combination with the a priori knowledge about the characteristics of the instrumental response. The spectrum and the parameter of PSF are obtained by minimizing the energy functional using alternate minimization approach. Experimental results are shown to demonstrate the efficiency of the proposed method used for THz spectrum.

关键词： THz spectrum Total variation deconvolution alternate minimization approach

来源：评论

学校读者我要写书评

暂无评论

Edge region color autocorrelogram: A new low-level feature applied in CBIR

Edge region color autocorrelogram: A new low-level feature a...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Xiaolin Chen Xiaokang Yang Rui Zhang Anwen Liu Shibao Zheng Institute of Image Communication and Information Processing and Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781424444618

Simple yet effective feature extraction is crucial for content- based image retrieval (CBIR). In this paper we propose a novel type of regional feature, which is called edge region color autocorrelogram (ERCAC). It aims to combine the color and shape characteristics of image jointly, by capturing both color distribution of image and spatial correlation of edge points with a structure-based early fusion. Hence, both color information and sketch information are encoded into a single representation. Experimental results show that our method has better performance on the task of TRECVID 2005 concept detection.

关键词： Feature extraction image communication Information processing image retrieval Shape image edge detection Content based retrieval image storage Data mining Histograms

来源：评论

学校读者我要写书评

暂无评论

Technical Analysis on Application Layer Error Control in IPTV

引用

ZTE communications 2010年第1期8卷 55-59页

作者： Xia Hongfei Lue Xiaopeng Liu Feng ZTE Corporation Nanjing 210012 P. R. China Image Processing and Image Communication Laboratory of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing 210003 P. R. China

When they provide Internet Protocol Television （IRTV） services, IP networks face difficulties such as reduced transmission bandwidth, delay, jitter, and packet loss. A terminal-centric solution can improve the image quality by adding control policies like congestion control and error control to the receiving terminal and source code. An end-to-end application layer reliability method is usually required to satisfy IPTV requirements in the IP network. Application Layer Forward Error Correction （AL-FEC） technology solves the problem of packet loss, and can ensure the end-to-end reliability for IPrV services.

关键词： IPTV Error Control Application Layer Forward Error Correction transmission bandwidth reliability packet loss congestion control Internet Protocol services image quality error control difficulties technology solution required improve jitter delay face

来源：评论

学校读者我要写书评

暂无评论

image classification based on pyramid histogram of topics

Image classification based on pyramid histogram of topics

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Fuxiang Lu Xiaokang Yang Rui Zhang Songyu Yu Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiaotong University Shanghai China

In this paper we propose PHOTO (pyramid histogram of topics), a new representation for image classification. We partition the image into hierarchical cells and learn the topic histogram using pLSA over each cell with EM algorithm. Then we concatenate the topic histograms over the cells at all levels to form a ldquolongrdquo vector, i.e. pyramid histogram of topics. Finally AdaBoost classifiers are used to select the topics most discriminative for class recognition. Experimental results on two diverse databases show that our method performs significantly better than general topic representation.

关键词： image classification Histograms Partitioning algorithms Layout image databases Support vector machines Support vector machine classification Linear discriminant analysis image representation image communication

来源：评论

学校读者我要写书评

暂无评论

Attentive Feature Focusing for Person Search by Natural Language 18th

Attentive Feature Focusing for Person Search by Natural La...

引用

18th International Forum of Digital Multimedia communication, IFTC 2021

作者： Pan, Renjie Yang, Hua Yang, Xinxin Xiaodong, Mao Ye, Long Pan, Da The Institute of Image Communication and Network Engineering Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai China Science and Technology Department of Shanghai Public Security Bureau Shanghai China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China

ISBN: (纸本)9789811922657

Cross-modal Retrieval has made great improvement since social media and artificial intelligence is gradually changing our life style. Human interaction is no longer limited to a single mode. Cross-modal retrieval brings greater portability to users. Extracting more sufficient feature from multimedia data and better fusing the feature have become the focus of academic research. In response to these two issues, this paper applies deep learning as the foundation for person search by natural language, combining CNN and Transformer. Meanwhile, we utilize BERT, the most effective feature extraction network in Natural Language processing and proposed a network architecture using attention mechanism. The framework is divided into a global branch and a fine-grained branch. At the same time, a human parsing network is designed to classify different parts of the characters to obtain feature representation in attribute level. In the visual-textual alignment, the k-reciprocal sampling algorithm is used to construct a more comprehensive sample pair. The proposed framework has achieved state-of-the-art performance in CUHK-PEDES, which proves its great capacity and prospect. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Disparity estimation algorithm for stereo video coding based on edge detecetion

Disparity estimation algorithm for stereo video coding based...

引用

International Conference on Wireless communications and Signal processing (WCSP)

作者： Jingjing Fan Feng Liu Weibin Bao Hongfei Xia Image Processing and Image Communication Jiangsu Key Laboratory Nanjing University of Posts and Telecommunications Nanjing China Zhijiang College Zhejiang University of Science and Technology Hangzhou China ZTE Telecom Company Limited Nanjing China

Disparity estimation is an important technique in stereo video coding. This paper presents a disparity estimation algorithm based on edge detection. The algorithm makes full use of the human visual characteristics, that is, the human eye is more sensitive to the distortion of the edge region. Therefore, joint estimation is used for edge detection. The large code block size for coding the background region and the flat areas while small size for coding the edge region were used in this paper. Compared to the disparity estimation algorithm proposed in, the proposed algorithm can greatly improve the encoding speed of stereo video without affecting subjective image quality.

关键词： Video coding image coding image edge detection Humans Motion estimation Educational institutions Scalability Redundancy image processing image communication

来源：评论

学校读者我要写书评

暂无评论

Visual perception preserving decolorization method

International Journal of Signal Processing, Image Processing...

引用

International Journal of Signal processing, image processing and Pattern Recognition 2016年第7期9卷 65-78页

作者： Chen, Jie Li, Xin Zhu, Xiuchang Wang, Jin Key Lab of Image Processing and Image Communication of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing210003 China College of Information Engineering Yangzhou University Yangzhou225009 China

This paper presents a decolorization method using gradient and saliency as the maintained features in the conversion to preserve the local and global visual perception. First, we construct a linear parametric mapping function of RGB color channels. Then, we calculate the feature value of each pixel in the color image and the parameterized grayscale image, the feature value integrates the pixel gradient and region saliency. Finally, we search for the parameters which can get the minimum of the total differences between the feature values of color and grayscale images, and substitute into the linear parametric function to get the decolorization result. To enhance the efficiency of getting the best parameters, we properly relax the strict computation formulas of the gradient and saliency to construct a linear least square problem, and obtain the optimal parameters by solving optimization. Experimental results show that our method using the discrete searching strategy can maintain the contrasts meanwhile avoid the excessive enlargement of the contrasts during the color-to-gray conversion, this property guarantees the preserving of the visual perception. Our method using the linear least square strategy can reduce the computation time and frequently get the similar results with our discrete searching method. © 2016 SERSC.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Top-down saliency by multi-scale contextual pooling

Top-down saliency by multi-scale contextual pooling

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

作者： Qiu, Yuanyuan Zhu, Jun Zhang, Rui Huang, Jun Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai China Shanghai Advanced Research Institute Chinese Academy of Sciences China

ISBN: (纸本)9783642347771

Goal-driven top-down mechanism plays an important role in the case of object detection and recognition. In this paper, we propose a top-down computational model for goal-driven saliency detection based on a coding-based classification framework. It consists of four successive steps: feature extraction, descriptor coding, local pooling and saliency prediction. In the step of local pooling, we investigate the effect of multi-scale contextual information for saliency detection and find that there exists an optimal contextual scale to achieve the patch-level feature presentation. On basis of this observation, we propose an approach for automatic scale selection in saliency prediction step. The experimental results demonstrate that our method can effectively improve the performance of goal-driven saliency detection as well as related object detection. © 2012 Springer-Verlag.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Visual Attention Data for image Quality Assessment Databases

Visual Attention Data for Image Quality Assessment Databases

引用

IEEE International Symposium on Circuits and Systems

作者： Xiongkuo Min Guangtao Zhai Zhongpai Gao Ke Gu Institute of Image Communication and Information Processing Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Digital Media Processing and Transmissions

ISBN: (纸本)9781479934331

images usually contain areas that particularly attract people's attention and visual attention is an important feature of human visual system (HVS). Visual attention had been shown to be effective in improving performance of existing image quality assessment (IQA) metrics. However, with the quick advancement of IQA research, the booming of open IQA databases calls for associated comprehensive and accurate visual attention dataset. Despite of the large number of existing computational attention/saliency models, the most accurate measure of human attention is still human based. In this research, we first conduct extensive eye tracking experiments for all the pristine images from the seven widely used IQA databases (LIVE, TID2008, CSIQ, Toyama, LIVE Multiply Distortion, IVC and A57 databases). Then we propose a gaze-duration adaptive weighting approach to generate saliency maps from the eye tracking data. When applied on the IQA databases, experimental results suggest that accuracy of benchmark quality metrics, e.g. PSNR and SSIM can be systematically improved, outperforming existing saliency datasets. Both the eye tracking data and the saliency maps in this research will be made publicly available at ***.

关键词： important HVS IQA

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：