检索结果-内蒙古大学图书馆

ieee visual communications and image processing (vcip)

作者： Liu, Hangfan Xiong, Ruiqin Fan, Xiaopeng Luo, Chong Gao, Wen Peking Univ Inst Digital Media Beijing 100871 Peoples R China Harbin Inst Technol Dept Comp Sci Harbin 150001 Heilongjiang Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China

ISBN: (纸本)9781538604625

In wireless visual communication systems, it is crucial to effectively utilize channel power and bandwidth in the pursue of optimal performance, and it is worthwhile to adapt the transmission scheme to human vision system (HVS) so as to achieve perceptually appealing results. Inspired by observations that visual quality of an image is closely related to the gradient data, this paper proposes to convey visual information by random projection measurements of image gradients in an analog framework. Since HVS is more sensitive to luminance variations of image contents, which are contained in the gradient data, the proposed scheme achieves better perceptual quality than conventional analog uncoded schemes like SoftCast. Besides, the gradient transform removes the low and medium frequency components of the image hence substantially reduces the power of the signal transmitted in the analog channel, thus evidently improves the power-distortion performance of the system. Furthermore, by applying random projection to the gradients, the number of transmitted data can be adjusted according to bandwidth conditions. Another contribution of this paper is to develop an effective optimization scheme for the compressive gradient based reconstruction problem. Experimental results validate the effectiveness of the the proposed transmission and reconstruction scheme under different channel signal-to-noise ratio and bandwidth conditions.

关键词： Wireless visual communication SoftCast bandwidth power channel signal-to-noise ratio gradient

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-view Embedding in Joint Space for Bidirectional image-Text Retrieval

Learning Multi-view Embedding in Joint Space for Bidirection...

引用

ieee visual communications and image processing (vcip)

作者： Ran, Lu Wang, Wenmin Peking Univ Shenzhen Grad Sch Sch Elect & Comp Engn Lishui Rd 2199 Shenzhen 518055 Guangdong Peoples R China

ISBN: (纸本)9781538604625

In this paper, we propose a framework for learning a joint embedding space for bidirectional image-text retrieval task, which fuses embedding spaces in multi-views. We have implemented two views currently, one is a frame-sentence view and the other is a region-phrase view. In the frame-sentence view, we project each frame of the images and each sentence of the texts into a holistic-level subspace to explore the correlation between them. In the region-phrase view, we extract each region of the frames and each phrase of the sentences and map them into a local-level subspace. We separately mine the semantic correlations in the two views, then merge them by a multi-view fusion ranking method. In each view, to embed heterogeneous data into a common space, we adopt the two-branch neural network to transform the data. Extensive experiments show that our multi-view joint space can preserve more accurate semantic correlations between images and texts in different granularities and can significantly improve the performance on the image-text retrieval task. Our method achieves better results than the state of the art on the Pascal1K and Flickr8K image-sentence datasets.

关键词： Multi-view embedding Joint space Fusion module Bidirectional image-text retrieval Two-branch neural network

来源：评论

学校读者我要写书评

暂无评论

Deep Hashing with Triplet Quantization Loss

Deep Hashing with Triplet Quantization Loss

引用

ieee visual communications and image processing (vcip)

作者： Zhou, Yuefu Huang, Shanshan Zhang, Ya Wang, Yanfeng Shanghai Jiao Tong Univ Cooperat Medianet Innovat Ctr Shanghai Peoples R China

ISBN: (纸本)9781538604625

With the explosive growth of image databases, deep hashing, which learns compact binary descriptors for images, has become critical for fast image retrieval. Many existing deep hashing methods leverage quantization loss, defined as distance between the features before and after quantization, to reduce the error from binarizing features. While minimizing the quantization loss guarantees that quantization has minimal effect on retrieval accuracy, it unfortunately significantly reduces the expressiveness of features even before the quantization. In this paper, we show that the above definition of quantization loss is too restricted and in fact not necessary for maintaining high retrieval accuracy. We therefore propose a new form of quantization loss measured in triplets. The core idea of the triplet quantization loss is to learn discriminative real-valued descriptors which lead to minimal loss on retrieval accuracy after quantization. Extensive experiments on two widely used benchmark data sets of different scales, CIFAR-10 and In-shop, demonstrate that the proposed method outperforms the state-of-the-art deep hashing methods. Moreover, we show that the compact binary descriptors obtained with triplet quantization loss lead to very small performance drop after quantization.

关键词： Convolutional Neural Network supervised hashing fast image retrieval

来源：评论

学校读者我要写书评

暂无评论

Quantitative Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Dataset

Quantitative Evaluation for Dehazing Algorithms on Synthetic...

引用

ieee visual communications and image processing (vcip)

作者： Li, Yufei Wang, Keyan Xu, Ning Li, Yunsong Xidian Univ State Key Lab Integrated Serv Network Xian 710071 Shaanxi Peoples R China Northwest Elect Power Design Inst Xian 710075 Shaanxi Peoples R China Xian Inst Space Radio Technol Xian 710100 Shaanxi Peoples R China

ISBN: (纸本)9781538604625

Dehazing is an important image processing technique that has been paid increasing attention in the recent years. But how to quantitatively evaluate the existing dehazing algorithms is still an open issue. In this paper we introduce an effective approach to evaluate the performance of the dehazing algorithms based on a synthetic outdoor dataset. Since it is difficult to simultaneously acquire hazy images and clear reference images, we synthesize haze in real images with complex and multiple scenes, and built an outdoor dataset that contains ground truth reference images, synthetic hazy images, depth maps and transmission maps of the same scene. Due to the fact that the generation of synthetic haze images are based on physical model which is strongly related to the depth information, we propose an effective depth estimation method which combines the geometry and edge information. With our estimated depth map, we are able to create a corresponding hazy scene with high fidelity. Finally, we perform a comprehensive full-reference evaluation of several typical single-image dehazing algorithms on our dataset.

关键词： image evaluation dehazing depth map sky segmentation atmospheric scattering model

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks for No-Reference and Full-Reference image Quality Assessment

引用

ieee TRANSACTIONS ON image processing 2018年第1期27卷 206-219页

作者： Bosse, Sebastian Maniry, Dominique Mueller, Klaus-Robert Wiegand, Thomas Samek, Wojciech Fraunhofer Heinrich Hertz Inst Dept Video Coding & Analyt D-10587 Berlin Germany Berlin Inst Technol Machine Learning Lab D-10587 Berlin Germany Korea Univ Dept Brain & Cognit Engn Seoul 136713 South Korea Max Planck Inst Informat D-66123 Saarbrucken Germany Fraunhofer Heinrich Hertz Inst D-10587 Berlin Germany Berlin Inst Technol Media Technol Lab D-10587 Berlin Germany

We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression, which makes it significantly deeper than related IQA models. Unique features of the proposed architecture are that: 1) with slight adaptations it can be used in a no-reference (NR) as well as in a full-reference (FR) IQA setting and 2) it allows for joint learning of local quality and local weights, i.e., relative importance of local quality to the global quality estimate, in an unified framework. Our approach is purely data-driven and does not rely on hand-crafted features or other types of prior domain knowledge about the human visual system or image statistics. We evaluate the proposed approach on the LIVE, CISQ, and TID2013 databases as well as the LIVE In the wild image quality challenge database and show superior performance to state-of-the-art NR and FR IQA methods. Finally, cross-database evaluation shows a high ability to generalize between different databases, indicating a high robustness of the learned features.

关键词： Full-reference image quality assessment no-reference image quality assessment neural networks quality pooling deep learning feature extraction regression

来源：评论

学校读者我要写书评

暂无评论

Low Rank Regularization Exploiting Intra and Inter Patch Correlation for image Denoising

Low Rank Regularization Exploiting Intra and Inter Patch Cor...

引用

ieee visual communications and image processing (vcip)

作者： Liu, Hangfan Xiong, Ruiqin Liu, Dong Wu, Feng Gao, Wen Peking Univ Inst Digital Media Beijing 100871 Peoples R China Univ Sci & Technol China Hefei 230026 Anhui Peoples R China

ISBN: (纸本)9781538604625

Based on the observation that a matrix X consisted of non-local highly-correlated patches is of low rank, many image restoration methods use low-rank regularization to exploit correlation between image contents, so that the uncertainty of the unknown image signal can be reduced. To tackle the problem that the underlying cost function to pursue minimal rank is hard to solve, an effective way is to employ smooth non-convex surrogate log vertical bar XXT vertical bar for the rank penalty. Essentially, such technique only considers to utilize correlation within image patches. In this paper, we propose to jointly exploit both intra- and inter-patch correlation of the input image, so as to further reduce the uncertainty of the signal, and thus improve the prediction of the latent image. The corresponding two surrogates are integrated to incorporate both intra- and inter-patch correlation. To solve the optimization problem, we use iterative alternating direction technique to divide the problem into two subproblems, each of which is solved via an empirical Bayesian procedure built upon variational approximation. Experimental results show that the proposed approach outperforms several state-of-the-art methods in terms of PSNR and perceptual quality.

关键词： Denoising low-rank regularization inter-patch correlation intra-patch correlation non-local similarity

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Mutual Feature Convolutional Neural Network for Depth image Denoise and Enhancement

Multi-Scale Mutual Feature Convolutional Neural Network for ...

引用

ieee visual communications and image processing (vcip)

作者： Liao, Xuan Zhang, Xin South China Univ Technol Sch Elect & Informat Guangzhou 510641 Guangdong Peoples R China

ISBN: (纸本)9781538604625

RGB-D images captured by consumer camera can provide pair-wise color and depth information but depth image usually contains strong noise and large holes. Due to different modalities of RGB-D, the intensity-guided depth enhancement easily causes artifacts and blurred edges. To solve this problem, we propose the multi-scale mutual feature convolutional neural network (MSMF-CNN) to learn essential mutual features of RGB-D. This end-to-end framework has two stages, i.e., mutual feature learning and depth regeneration. Firstly, we design two parallel separated subnetworks as intensity and depth mutual feature generator. Specifically, we design a multi-scale mutual feature generator to enforce the depth mutual feature learning and incorporate various structure characteristic. Secondly, depth transformation sub-network combines two mutual features to recover clean depth image. We tested our model on two well-known datasets in terms of PSNR, visual effect and computing speed. Compared with state-of-art algorithms, our method provides better performance of all three criteria.

关键词： depth enhancement depth denoise mutual feature multi-scale convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

image Super-Resolution Based on Adaptive Joint Distribution Modeling

Image Super-Resolution Based on Adaptive Joint Distribution ...

引用

ieee visual communications and image processing (vcip)

作者： Liu, Hangfan Xiong, Ruiqin Song, Qiang Wu, Feng Gao, Wen Peking Univ Inst Digital Media Beijing 100871 Peoples R China Univ Sci & Technol China Hefei 230026 Anhui Peoples R China

ISBN: (纸本)9781538604625

This paper combines an adaptive reconstruction based approach and a learning based technique into an effective scheme for single image super-resolution. Unlike conventional schemes that adopt pre-trained dictionaries to tell the relationship between high-resolution (HR) image and the low-resolution (LR) observation, the proposed method attempts to learn the joint distribution of highly-correlated patch couples from the input image itself instead of an external dataset, so that the learnt models are specially tailored for the current patches and thus can better fit the image data of interest. To be specific, we first apply spatially adaptive gradient sparsity regularization in the reconstruction of the HR image using the contour information, and then utilize the generated HR output to guide the joint distribution learning to infer the relationship between the highly-correlated HR and LR patches. In this way, we simultaneously exploit the inter-scale correlation as well as the local and non-local correlation of the image contents. Empirical results show that the performance of the proposed method is highly competitive with state-of-the-art schemes in terms of peak signal-to-noise ratio (PSNR) and perceptual quality.

关键词： Super-resolution content adaptive joint distribution modeling non-local similarity gradient sparsity

来源：评论

学校读者我要写书评

暂无评论

Portable Information Security Display System via Spatial Psychovisual Modulation

Portable Information Security Display System via Spatial Psy...

引用

ieee visual communications and image processing (vcip)

作者： Li, Xiang Zhai, Guangtao Wang, Jia Gu, Ke Shanghai Jiao Tong Univ Inst Image Commun & Info Proc Shanghai Peoples R China Beijing Univ Technol Fac Informat Technol Beijing Peoples R China Beijing Key Lab Computat Intelligence & Intellige Beijing Peoples R China

ISBN: (纸本)9781538604625

With the rapid development of visual media, people prefer to pay more attention to privacy protection in public situations. Currently, most existing researches on information security such as cryptography and steganography mainly concern transmission and yet little has been done to keep the information displayed on screens from reaching eyes of the bystanders. At the same time, the reporter just stands in front of the screen during traditional meetings. Limited time, screen area and report forms, which inevitably leads to limited information. As a result, we design a portable screen for assisting the reporter to present any information in a new form. In some public occasions, the reporter can show private content with important information to authorized audience while the others can not see that. In this paper, we propose a new Spatial Psychovisual Modulation (SPVM) based solution to the privacy problem. This system uses two synchronized projectors with linear polarization filters and polarization glasses, and a camera with linear polarization filter the metallic screen. It can guarantee the system shows private information synchronously. We have implemented the system and experimental results demonstrate the effectiveness and robustness of the proposed information security display system.

关键词： Spatial Psychovisual Modulation (SPVM) Display technology Information security Multimedia technology Portable display

来源：评论

学校读者我要写书评

暂无评论

Deep Fully Convolutional Regression Networks for Single image Haze Removal

Deep Fully Convolutional Regression Networks for Single Imag...

引用

ieee visual communications and image processing (vcip)

作者： Zhao, Xi Wang, Keyan Li, Yunsong Li, Jiaojiao Xidian Univ State Key Lab Integrated Serv Network Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781538604625

Haze removal for a single image is known to be a challenging ill-posed problem in computer vision. The performance of existing prior-based image dehazing methods is limited by the effectiveness of hand-designed features. The emerging convolutional neural network (CNN) based approaches can remove haze with the automatically learned intrinsic mapping between the input hazy images and their corresponding transmission maps, but the recovered haze-free images sometimes are still unsatisfactory. In order to improve the dehazed images, we aim to develop an effective deep fully convolutional regression network for more accurate transmission estimation. Our network is an end-to-end regression system which take input of arbitrary size hazy image and predict correspondingly-sized transmission map. To train and evaluate deep network for image dehazing efficiently, we develop new outdoor synthetic training set respectively. In addition, we fully compare the existing CNN-based haze removal approaches with our algorithm on real-world images and our synthesized benchmark dataset. The experimental results demonstrate that our trained regression model achieves superior dehazing performance than the current state-of-the-art methods.

关键词： Haze removal convolutional neural network transmission regressed model deconvolution

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：