Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 231 papers published in subject: > since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Risk Quantification Contributes To Service Stability | |||
Liu Funiu | |||
Computer Science and Technology 07 August 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This article shows the design and implementation of a system called risk quantification platform. On the whole, the risk quantification platform is designed to standardize the changes in the product line from the perspective of prevention. We use the quantified data to conduct a risk assessment and combine the case improvement module to drive the business side to optimize the stability of online services, achieving the goal of reducing the occurrence of the online cases. By automatically collecting user platform operation and maintenance data, and automatically calculating and quantifying the operation and maintenance risks, each bussiness line gets risk scores of various dimentions. Finally, a ranking and competition mechanism is formed to achieve the purpose of promoting long-term implementation of standards and assisting in the construction of service stability. | |||
TO cite this article:Liu Funiu. Risk Quantification Contributes To Service Stability[OL].[ 7 August 2020] http://en.paper.edu.cn/en_releasepaper/content/4752636 |
2. MobiPDF: Reconstructing PDF contents for Mobile Devices | |||
Peng Jin,Ligang He,Yilian Zhou,Cheng Chang,Liangtang Lei,Xiaorui Zhang,Hao Chen | |||
Computer Science and Technology 22 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The PDF format is widely used in academia with its elegant style and unmodifiable features. With the popularity of mobile terminals, more and more people use mobile devices to browse and obtain documents. However, once the PDF document is generated, the style is fixed. It is difficult to read on a small-sized mobile screen. In this work, we develop a system called MobiPDF to reconstruct the content in a PDF document and render it in a way so that it can viewed properly on a mobile screen. In particular, the content of the PDF document is first decomposed into different areas. The PDF file is then converted into an HTML format file and also to an image file. Next, the texts and their rendering information are extracted from the HTML file according to the positions of the decomposed areas. In addition, the non-text information such as figures and tables is extracted from the image file based on its positions. The extracted text and non-text contents together with the rendering information are reconstructed as a new HTML file according to the size of the user\'s mobile screen. We have developed MobiPDF as a web service, which is hosted on the Tencent Cloud and can be accessed publically. | |||
TO cite this article:Peng Jin,Ligang He,Yilian Zhou, et al. MobiPDF: Reconstructing PDF contents for Mobile Devices[OL].[22 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4752113 |
3. A generality enhanced forensic towards GAN facial images | |||
Xiong Xiao-Fang,Yang Gao-Bo | |||
Computer Science and Technology 13 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:\justifying Recent advances in GAN technique have made it much easier than ever to generate believable face images, which brings some potential security issues to the public. Currently a variety of architectures have been proposed to detect these generated fake images, but few works address the problem of generalization ability of forensics models, which means most of them need prior knowledge of the structure of GAN model when detecting a specific GAN fake face images, and unable to detect unseen fake images generated by other GAN models. In this work, we tackle the generality enhanced problem by adding a fixed weight convolutional layer before CNN structure, which contain three designed high-pass filters. Firstly, we convert RGB images to YCbCr color space to get more obvious edge information. Then, EfficientNet is adopted as our basic CNN structure to extract inhenrent features and classify them. Finally, a fixed weight layer is added to the first convolutional layer, which could greatly suppress the semantic image content and magnify microscopic characteristics of images, thus help to enhance the generalization ability of the model. A series of experiments demonstrate that our approach achieve superior performance compare with the state-of-the-art work in terms of the generality of forensics model. | |||
TO cite this article:Xiong Xiao-Fang,Yang Gao-Bo. A generality enhanced forensic towards GAN facial images[OL].[13 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4752048 |
4. Super-resolution Reconstruction of Mosaic Face Images Based on GAN | |||
Xu Yonghui,Yang Gaobo | |||
Computer Science and Technology 11 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the rapid development of artificial intelligence technologies, image super-resolution which is one of the hottest topics in computer vision community, has achieved attractive progresses. To restore mosaic face images, we present an effective model, namely DemosaicGAN. It combines existing SRGAN and RDN and optimizes the perceptual loss functions. As far as we concerned, our experimental results show that the proposed DemosaicGAN achieves the best results in super-resolution reconstruction of mosaic face images so far. | |||
TO cite this article:Xu Yonghui,Yang Gaobo. Super-resolution Reconstruction of Mosaic Face Images Based on GAN[OL].[11 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4752050 |
5. Image completion algorithm based on label differentiation | |||
Ye Zixiao, Tan Guanghua | |||
Computer Science and Technology 29 April 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Image completion is an important research direction in computer vision and has broad application prospects. Deep learning based image completion methods are generally based on three technologies, namely the autoencoder-based method, the generation of adversarial networks based method and the recurrent network based method. However, the output results of most methods are very single, for each masked Image input can only generate one completion result. Because the probability space corresponding to the possible results of each defective image is very large, in order to obtain the diversity of the completion results, this paper proposes an image completion method based on label differentiation, called LD-PICNet (Label Differentiation PICNet) This method can not only generate a complete image with clear and good semantic information, but also actively edit the tags on the generated results to maximize the diversity of the output. Specifically, this paper introduces an auxiliary classifier similar to ACGAN, which uses a single label of the image ground truth to reconstruct the image, and uses the label to actively increase the difference of the latent vectors during image completion to achieve variability of output. In addition, this paper also introduces a depth-weighted loss function through information entropy. The deeper the position of the image masked area, the lower the weight is given to further enhance the ability of the model to diversify the output. In order to evaluate the ability of LD-PICNet, this paper conducted experiments on 4 different data sets, and tested the model's ability to complete different types of targets, namely face (CelebA), architecture (Paris), landscape (Place2) ,and ordinary pictures (ImageNet). The results show that this method has the ability to generate diversified results, and it has higher clarity than the more advanced methods. | |||
TO cite this article:Ye Zixiao, Tan Guanghua. Image completion algorithm based on label differentiation[OL].[29 April 2020] http://en.paper.edu.cn/en_releasepaper/content/4751876 |
6. DMOO:Dynamic Mobility Oriented Task Offloading in Vehicular Edge Computing | |||
Cheng Ziqing, LI Zhiyong, Wang Qi, Nouioua Mourad | |||
Computer Science and Technology 29 April 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The rapid development of smart vehicles and their applications constrained by computing resource and time response pose crucial problems in vehicle-to-vehicle (V2V) communications, such as how to provide the required computation capabilities and how to ensure the accomplishment of tasks within a limited time. Mobile edge computing (MEC) has emerged as a new paradigm that can be used to improve vehicular services through computation offloading among smart vehicles. However, new challenges may be encountered in MEC for V2V communication due to the highly dynamic mobility of vehicles. In this paper, we propose a dynamic-mobility-oriented offloading solution(DMOO) for delay-constrained vehicular computation offloading. Specifically, to overcome the problems caused by mobility and limited resources, we design a risk assessment model to estimate the probability for vehicles to be out of range and then develop a discrete artificial bee colony algorithm based on this model to balance the offloading utility and potential risks. Extensive experiment result demonstrate that our solution can significantly enhance the utility and reduce risk compared to other baselines. | |||
TO cite this article:Cheng Ziqing, LI Zhiyong, Wang Qi, et al. DMOO:Dynamic Mobility Oriented Task Offloading in Vehicular Edge Computing[OL].[29 April 2020] http://en.paper.edu.cn/en_releasepaper/content/4751873 |
7. Model of dynamic division of distribution area based on ant colony algorithm | |||
Zhang Yazhou,Zhuang Yufeng | |||
Computer Science and Technology 16 April 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In recent years, with the rapid popularization of mobile terminals, China\'s express delivery has developed rapidly, and with the continuous increase in express delivery volume, the pressure of express delivery has increased year by year. Under the existing distribution area division model, problems such as warehouse outages have become increasingly serious. This article mainly proposes a model of dynamic division of distribution areas from the perspective of dynamic adjustment of express delivery volume to solve existing problems. The main idea of the entire model is to first ensure that the delivery volume of the delivery point is not overstock as possible under the conditions of limited delivery capacity. the express delivery volume forms a dynamic balance between express delivery points, and then optimizes the delivery distance under this condition to solve the problems mentioned in this article. | |||
TO cite this article:Zhang Yazhou,Zhuang Yufeng. Model of dynamic division of distribution area based on ant colony algorithm[OL].[16 April 2020] http://en.paper.edu.cn/en_releasepaper/content/4751656 |
8. A Low Bit-Rate Image Compression Method for Tunnel Inspection | |||
ZHU Zhi-Qiang,LI Qing-Yong,WANG Jian-Zhu,JIA Lei | |||
Computer Science and Technology 18 March 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Tunnels play a critical role in civil transportation infrastructures, and keeping them in optimal operation conditions is of great significance. With the development of computer vision technology, manual inspection is gradually being replaced by automatic or interactive vision inspection systems. During the inspection, these systems usually need to process a massive number of images, which inevitably causes storage problem. Therefore, a variety of image compression approaches have been proposed. However, most of the existing methods overlook the property of high consistency and homogeneity of tunnel images and are not fully applicable to tunnel inspection scenarios. In this paper, we propose a content-aware sparse coding based method for tunnel image compression. Firstly, we train a dictionary for predefined image patches. Secondly, an adaptive sparse coding algorithm is designed by considering the diversity of image content. Specifically, coefficients with more and less non-zero elements are adaptively allocated for complex and plain image textures, respectively. Thirdly, a novel non-uniform quantization method is presented, which has been proved to improve effectively the coding performance. Experimental results show that our method enjoys better visual results and outperforms JPEG and JPEG2000 in terms of Peak-Signal-to-Noise Ratio (PSNR) and structural similarity (SSIM) index in lower bitrates. | |||
TO cite this article:ZHU Zhi-Qiang,LI Qing-Yong,WANG Jian-Zhu, et al. A Low Bit-Rate Image Compression Method for Tunnel Inspection[OL].[18 March 2020] http://en.paper.edu.cn/en_releasepaper/content/4751259 |
9. C/S Mode Based Ethereum Node Shared Storage Method | |||
GAO Jiachen,WU Zhigang | |||
Computer Science and Technology 28 February 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Ethereum is one of the classic applications of blockchain technology which is valuable and has important prospects in many fields. With the development of blockchain technology, its supervision has become more inportant. Although there is currently no suitable supervision method, the measurement of blockchain provides support for the blockchian supervision. When measuring the spread of Ethereum transactions, it is necessary to deploy as many probe nodes as possible, which will bring the consumption of storage resources that cannot be underestimated. Thereby the consumption of storage resources reducing the feasibility of the measurement of spread of transaction on Ethereum. This paper proposes a method for Ethereum node shared storage. This method designs and modifies the storage mode of Ethereum ndoes so that enabling multiple nodes to be deployed on the same server at the same time, and this mode guarantees the independence and function completeness of shared storage nodes on Ethereum at the same time. According to the experimental results, the data sharing rate of shared storage between nodes could reach 74% which effectively reduces the storage occupation of the probe nodes during deployment. | |||
TO cite this article:GAO Jiachen,WU Zhigang. C/S Mode Based Ethereum Node Shared Storage Method[OL].[28 February 2020] http://en.paper.edu.cn/en_releasepaper/content/4750956 |
10. Class-balanced and Local Median Loss Jointly Supervised for Wild Facial Expression Recognition | |||
Shi Cong-Cong,TIAN,TIAN Mei | |||
Computer Science and Technology 07 February 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Over the past few years, Convolutional Neural Networks (CNNs) have shown effective performance on facial expression recognition. However, it is still a challenge problem for facial expression in the wild. The facial expression recognition dataset in the wild usually has the problem that imbalanced distribution of facial expression data and large intra-class differences caused by factors such as pose, lighting and gender. In order to solve this problem, this paper presents a novel loss function -- CALM Loss (Class-balanced and Local Median Loss). CALM Loss contains two parts. The first part is the class-balanced softmax loss function, which is uesd to solve the problem of data imbalance. The data set is divided into two classes, with two expressions with less data as one class and the other five as one class. During the network training process, the weight of the class with less data is adaptively increased. The second part is the local median loss function, which uses the median of serveral neatest neighbors in the same class as the center of class, weakens the influence of difficult samples on the selection of class center. Finally, the CALM Loss training network was adopted in this paper. The average recognition accuracy on the RAF dataset reaches 77.34$\%$, which proves the effectiveness of the proposed method. | |||
TO cite this article:Shi Cong-Cong,TIAN,TIAN Mei. Class-balanced and Local Median Loss Jointly Supervised for Wild Facial Expression Recognition[OL].[ 7 February 2020] http://en.paper.edu.cn/en_releasepaper/content/4750634 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated