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 72 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. Multilevel LSTM for Action Recognition Based on Skeleton Sequence | |||
CHEN Yan-Ru, PAN Hua-Wei | |||
Computer Science and Technology 17 April 2019 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Skeleton-based human action recognition has a broad range of applications in human-computer interaction and intelligent monitoring, and human behavior can be represented by the trajectory of the skeleton joint. Long-term short-term memory (LSTM) networks exhibit outstanding performance in 3D human action recognition because they are capable of modeling dynamics and dependencies in sequential data. In this paper, we propose a skeleton-based multilevel LSTM network for action recognition. First, the data for each joint and parent joint is used as input to a fine-grained subnet based on the action link between them. Then the features of the upper body joint are merged into the upper body subnet, the features of the lower body are merged into the lower body subnet, and finally the features of the two subnets are structured and fused to achieve higher recognition accuracy. Experimental results on the public data set NTU RGB+D demonstrate the effectiveness of the proposed network. | |||
TO cite this article:CHEN Yan-Ru, PAN Hua-Wei. Multilevel LSTM for Action Recognition Based on Skeleton Sequence[OL].[17 April 2019] http://en.paper.edu.cn/en_releasepaper/content/4748531 |
2. Efficient Face Verification Algorithm with Attention Mechanism | |||
LI Runze,LI Wei,XU Tong,QI Qi | |||
Computer Science and Technology 08 March 2019 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Face verification is applied to our life, which benefits from the high-accuracy of the algorithm based on CNN. However,the performance of face verification is still poor on mobile device since limited computation resources. In this paper, we present a class of extremely efficient algorithm with attention mechanism embedded, the algorithm of 20MB size achieves 96.37% face verification TAR(FAR1e-6) on MegaFace Challenge, which is even comparable to hundrads MB size. We compare our algorithm with similar small size models like MobiFace, MobileFaceNet, Goole-FaceNet, the experimental results show the efficent of our algorithm. | |||
TO cite this article:LI Runze,LI Wei,XU Tong, et al. Efficient Face Verification Algorithm with Attention Mechanism[OL].[ 8 March 2019] http://en.paper.edu.cn/en_releasepaper/content/4747624 |
3. Reconstruction-based Robust Pavement Crack Detection | |||
LUO Ling,XU Guosheng,XU Guoai | |||
Computer Science and Technology 21 January 2019 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Pavement crack detection is of great importance for road maintenance. It is still very challenging to establish a unified and robust framework to perform accurate crack extraction from images with cluttered background, various morphological differences and even with shadow influence. In this paper, an improved semantic segmentation model with reconstruction branch is proposed for crack detection. Based on normal segmentation network, a deep convolutional encoder-decoder network is built to learn the image reconstruction mapping. This reconstruction guided semantic segmentation is aimed at improving detection accuracy by introducing reconstruction difference between crack and normal areas. The experiments demonstrated that our algorithm outperforms the convolutional segmentation method on two public datasets. | |||
TO cite this article:LUO Ling,XU Guosheng,XU Guoai. Reconstruction-based Robust Pavement Crack Detection[OL].[21 January 2019] http://en.paper.edu.cn/en_releasepaper/content/4747079 |
4. Density-Sensitive Spectral Clustering Based on Natural Neighbor | |||
LEI Dajiang,Wang Mingda,ZHANG Lisheng | |||
Computer Science and Technology 21 December 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The key of spectral clustering algorithm lies in how to measure the relation between data points. In order to describe the neighbor relation between data points, a fast natural neighbor method is adopted to adaptively select the number of neighbors. Firstly, the natural neighbor is used to construct the neighborhood relationship between the data. Then the similarity matrix is constructed based on the local information density-sensitive. Finally, the clustering results obtained from eigenvalue decomposition of the Laplacian matrix. In this paper, a local information parameter is proposed to solve the low performance problem of density-sensitive spectral clustering methods due to the linear change of Euclidean distance between data points, meanwhile the problem of selecting scaling factor is solved in density-sensitive spectral clustering. With the massive experiments, the proposed algorithm is effective and feasible, and is superior to the classical spectral clustering algorithm | |||
TO cite this article:LEI Dajiang,Wang Mingda,ZHANG Lisheng. Density-Sensitive Spectral Clustering Based on Natural Neighbor[OL].[21 December 2017] http://en.paper.edu.cn/en_releasepaper/content/4742931 |
5. Efficient Bare Metal Auto-Scaling for NFV Platform | |||
Pang Xudong,Wang Jing,Wang Jingyu,QiQi | |||
Computer Science and Technology 19 November 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:There are always a cloud data center behind the Network Function Virtualisation(NFV) system.Typically, elasticity is an essential attribute of cloud data center, which is critical for operating resources in face of peaks and valleys of business. At present, the automatic scaling technique of virtual machines is widely studied, but barely for physical machines. Despite lack of flexibility, we all know that physical server can perform faster and more efficiently than virtualized instances, especially in NFV systems. Some virtual network functions (VNFs) actually require high performance computing, which is a hard task for virtual machines. Besides, good management of bare metal resources can be significant for the data center power cost and human maintenance cost. Accordingly, we think that auto-scaling of physical machine is worth studying. This paper proposes a bare metal automatic scaling scheme based on workload prediction, and finally make tests on an open source NFV platform.The new scheme obtains good result on computation intensive VNFs scenario, including complete the scale in half an hour, guarantee for the continuity of VNF processing business, and can cope with the load fluctuation better. | |||
TO cite this article:Pang Xudong,Wang Jing,Wang Jingyu, et al. Efficient Bare Metal Auto-Scaling for NFV Platform[OL].[19 November 2017] http://en.paper.edu.cn/en_releasepaper/content/4742224 |
6. DOTE: Automatic Domain-specific Term Extraction from Wikipedia | |||
WEI Bifan,LIU Jun,MA Jian,ZHENG Qinghua | |||
Computer Science and Technology 08 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Wikipedia contains a large number of domain-specific terms, which can be used in ontology construction, summary generation and other natural language processing tasks. Extracting domain-specific terms automatically is a fundamental task in knowledge acquisition and ontology construction. However, the massive and rapid increasement of domain-specific terms make this task very challenging for conventional rule-based and statistic-based methods. In this paper, we propose an automatic DOmain-specific Term Extraction method (DOTE) from Wikipedia articles. This method is based on three features: (1) the domain focusing of Wikipedia category, (2) domain specificity of Wikipedia revision history and (3) domain indication of first sentence's terms. Our method consists of three stages: (1) generate some domain seed articles from layer 1 according to the domain name; (2) use Feature Voting Model (FVM) to filter domain artilces in layer 1 and 2; (3) expand domain-specific terms from selected categories using subtree expansion. Experimental results show fairly good performance and the practicability of the proposed method.In this paper. | |||
TO cite this article:WEI Bifan,LIU Jun,MA Jian, et al. DOTE: Automatic Domain-specific Term Extraction from Wikipedia[OL].[ 8 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4731848 |
7. Fine-tuning and visualization of Convolutional Neural Networks | |||
YIN Xiangnan,CHEN Weihai | |||
Computer Science and Technology 19 January 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Image classification is a widely discussed topic in the field of computer vision. In recent years, with the application of Convolutional Neural Networks (CNNs), the state-of-the-art in this area has progressed rapidly. To yield a well performed CNNs, the advanced GPU and large amount of training data are employed, thus training an entire CNNs from scratch is difficult. In practice, fine-tuning a pre-trained CNNs is a simple yet effective method to solve a target task. In this paper, we address on the issue of visualizing a fine-tuned CNNs, comparing with a small CNNs trained from scratch on the same task, to explain how fine-tuning achieve such good performance. | |||
TO cite this article:YIN Xiangnan,CHEN Weihai. Fine-tuning and visualization of Convolutional Neural Networks[OL].[19 January 2017] http://en.paper.edu.cn/en_releasepaper/content/4715829 |
8. Face Recognition based on Simplified CNN and Median Pooling | |||
XIONG Feng-ye, DONG Yuan, BAI Hong-liang | |||
Computer Science and Technology 13 October 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Convolution neural network(CNN) is increasingly used by the groups studying face recognition. CNN dramatically improves the performance on many datasets such as LFW and IJB-A. But most of the groups extract features from big networks with large amount of parameters and FLOPS. In this work, a simplified CNN architecture, which achieves comparable results to the state of the art, with only 0.8M training data, 4.4M parameters and 0.6B FLOPS, is proposed. In addition, an anti-noise median pooling method is introduced when dealing with template-based comparison. | |||
TO cite this article:XIONG Feng-ye, DONG Yuan, BAI Hong-liang. Face Recognition based on Simplified CNN and Median Pooling[OL].[13 October 2016] http://en.paper.edu.cn/en_releasepaper/content/4706549 |
9. Name Based Socket : An approach for Android Based System | |||
Ahmed M.A. Alsayadi,Xu Mingwei | |||
Computer Science and Technology 21 September 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:IP address management has become more and more complex. For mobile applications, what makes IP management more complicated is the updates of IP address and the address translation of gateways. With the rapid growth of smartphones worldwide (Global sales of smartphones to end users totaled 349 million units in the first quarter of 2016, a 3.9 percent increase over the same period in 2015, according to Gartner, Inc.), this challenge has become even more urgent to be solved. In this paper, a method is introduced to solve IP management-related issues in Android based system using name based socket scheme (NBS). Android NBS relieves mobile applications from IP management and moves it down to the operation system level. Thus, the application itself is relieved from re-implementing features such as multi-homing, mobility, NAT traversal. And the complication of application developing will be reduced. In the meanwhile, the Android NBS is configurable and backward compatible, and it doesn't influence connection performance in any way, it also doesn't require any changes on the network architecture during using. | |||
TO cite this article:Ahmed M.A. Alsayadi,Xu Mingwei. Name Based Socket : An approach for Android Based System[OL].[21 September 2016] http://en.paper.edu.cn/en_releasepaper/content/4705039 |
10. A multiple-steps linear representation based classification for face recognition | |||
Tao Liu,Jian-Xun Mi | |||
Computer Science and Technology 19 February 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Error detection is an important approach to improve the robustness of face recognition (FR) method. However, it is hard to directly detect the outliers in a facial image. We decompose the hard problem into many simpler sub-problems in this paper. That is, the process of detecting distorted pixels is divided into multiple easier steps and a part of invalid pixels are detected in every step. The goal is to decrease the ratio of outlier in the testing image, which reduces the influence of outliers in a recognition process. The performance that our method deals with occlusion and corruption problems is evaluated on different databases. In addition, we compare our method with state-the-of-art face recognition based methods, and the proposed method achieves the best results in face occlusion and disguise issues. | |||
TO cite this article:Tao Liu,Jian-Xun Mi. A multiple-steps linear representation based classification for face recognition[OL].[19 February 2016] http://en.paper.edu.cn/en_releasepaper/content/4676937 |
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